EP4128122A1 - Collaborative electronic platform for predicting non-payments for companies and associated method - Google Patents

Collaborative electronic platform for predicting non-payments for companies and associated method

Info

Publication number
EP4128122A1
EP4128122A1 EP21722522.6A EP21722522A EP4128122A1 EP 4128122 A1 EP4128122 A1 EP 4128122A1 EP 21722522 A EP21722522 A EP 21722522A EP 4128122 A1 EP4128122 A1 EP 4128122A1
Authority
EP
European Patent Office
Prior art keywords
company
platform
data
community
companies
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
EP21722522.6A
Other languages
German (de)
French (fr)
Inventor
Jean-Cedric BEKALE BE NTOUTOUME
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tradein Holding
Original Assignee
Tradein Holding
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tradein Holding filed Critical Tradein Holding
Publication of EP4128122A1 publication Critical patent/EP4128122A1/en
Withdrawn legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0635—Risk analysis of enterprise or organisation activities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/08—Payment architectures
    • G06Q20/10—Payment architectures specially adapted for electronic funds transfer [EFT] systems; specially adapted for home banking systems
    • G06Q20/102—Bill distribution or payments
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/08—Payment architectures
    • G06Q20/14—Payment architectures specially adapted for billing systems
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/389—Keeping log of transactions for guaranteeing non-repudiation of a transaction
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/02—Marketing; Price estimation or determination; Fundraising
    • G06Q30/0201—Market modelling; Market analysis; Collecting market data
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q30/00—Commerce
    • G06Q30/04—Billing or invoicing

Definitions

  • the present invention belongs to the general field of financial and insurance technologies (fintech and insurtech), in particular of the automation of risk management, and relates more particularly to a collaborative electronic platform for the prediction of payment defaults between companies, such as that payment delays and unpaid bills, by machine learning, and a process implemented by said platform.
  • the invention also relates to blockchain techniques, big data management and decision support.
  • Effective sales management is important to the overall financial health of a business. Businesses seek to reduce bad debts and guard against the consequences of the accumulation of late payments and bad debts.
  • One of the major problems encountered mainly by small and medium-sized enterprises is that of late payments which often leads to the cessation of activity and the premature shutdown of businesses, including those with great economic potential.
  • the present invention aims to overcome the drawbacks of the prior art described above, in particular the absence of credit risk management solutions suitable for small or medium-sized enterprises and making it possible to establish a community of mutual aid and sharing of information. information between a plurality of companies.
  • the present invention relates to a collaborative electronic platform for the prediction of payment defaults between a company and customers of said company, comprising a data storage system, at least one computer server and processing means and calculation implementing at least one machine learning model, the platform being able to import financial data from the company by means of a secure link between the data storage system and an internal management tool of said the company, said model estimating the occurrence of customer defaults on the basis of the imported financial data.
  • This collaborative platform is remarkable in that it is linked to a plurality of companies forming a community for sharing information in real time on the platform, in that it is able to transmit any information shared by a first company to at least one second enterprise of the community for which said information is of interest, and in that it comprises an application programming interface API making it possible to execute a user program for risk management on terminals of enterprises of the community.
  • the collaborative platform is linked to external data sources, and the processing and calculation means include algorithms for rating making it possible to determine a score for any company from information on said company contained in the external data imported by said platform.
  • the collaborative platform has a cloud architecture with a virtualization layer comprising at least the data storage system and any server, said platform being accessible via an Internet type network.
  • the data storage system comprises a database and the processing and calculation means comprise at least one processor, said database being able to be distributed on a chain of blocks.
  • the information shared by the member companies of the community includes payment histories of the customers of each company, and the imported financial data includes customer portfolios, invoices, quotes, etc.
  • At least one machine learning model constructs a prediction of default on an invoice from attributes relating to said invoice, financial data imported to the platform and contextual data.
  • the present invention also relates to a method for forecasting the risks associated with payment defaults between a company and customers of said company, implemented by a collaborative platform as it has been presented, characterized in that it understand :
  • the analysis and prediction step uses data provided by several companies in the community as well as external data from sources such as financial data providers, and allows also to detect payment defaults, taking into account the deadlines of invoices imported on the platform.
  • the information presentation step produces prevention information comprising at least one item of information from among a risk alert, a credit risk score and an information report, the latter corresponding to the risk profile of a client of the company.
  • the method further comprises an operation or a combination of operations among: a reimbursement of unpaid debts in favor of companies of the community (debt collection), according to a system of pooling of risks centralized in the collaborative platform secured by a blockchain; pooled financing of customer invoices, between member companies of the community, according to a peer-to-peer financing model managed by the collaborative platform and secured on the blockchain; and a cash flow prediction of each business in the community based on the data imported into said platform.
  • FIG. 1 a block diagram of a collaborative platform according to one aspect of the invention
  • FIG. 2 a block diagram of the collaborative platform interacting with a community of companies
  • - Figure 3 an example of system architecture of the collaborative platform according to the invention
  • - Figure 4 an example of information exchanged between the collaborative platform and a company member of the community
  • FIG. 6 an example of a graphical interface on a mobile application for interaction with the collaborative platform
  • FIG. 8 a partial block diagram of a machine learning model executed in the collaborative platform
  • a computer system in the form of a collaborative electronic platform, for the prediction of payment defaults between companies, intended mainly for entities of the small or medium-sized enterprises (SMEs) type in order to allow them better management of the financial risks inherent in payment defaults, such as late payments and unpaid bills, on the part of their customers, but also decision support in the choice of their prospects.
  • SMEs small or medium-sized enterprises
  • FIG. 1 shows in a simplified manner the operating principle of a collaborative platform 10 according to a first aspect of the invention.
  • the collaborative platform 10 makes it possible to bring together a plurality of companies 20 in an information-sharing community, said companies bearing the references E1, E2 and E3 to be distinguished from each other in this case.
  • each company can share in real time with other companies in the community its customer payment experiences, in other words the payment status or the accounting status of its invoices, so as to allow the collaborative platform to establish profiles. behavior of the customers of each company in the community, C1 to C6 in Figure 1.
  • the collaborative platform 100 makes it possible to compile the various data from payment histories provided by companies 20 in the community and to send preventive recommendations to said companies on the basis of statistical analyzes and / or learning models. automatic described below.
  • the collaborative platform 10 assigns a score according to a precise rating to each client of businesses in the community and to any other entity likely to be solicited by a current or future member of said platform, these scores reflect payment behavior. Obviously, the payment defaults observed have a negative impact on the scores assigned by the platform 10 to defaulting companies.
  • the good behavior P25 of the client C5 in his relationship business, especially its financial transactions, with the company E2 is shared on the collaborative platform and positively impacts the S5 score of said customer.
  • the E3 company also a member of the community, by looking for a prospect, is informed in real time of the scores of the prospects it targets, in particular the scores of C1 and C5.
  • the negative S1 score of C1 allows the collaborative platform 10 to advise E3 against a T31 transaction with C1.
  • the good S5 score of prospect C5, a customer of E2 makes it possible to encourage company E3 to initiate a T35 transaction with said prospect.
  • FIG. 2 schematically represents the collaborative platform 10 interacting with the main actors, namely companies 20 members of the community and prospects / customers C, with the aim of providing said companies with decision support, in the form of recommendations and information, allowing them to better manage the risk of payment defaults, to choose reliable prospects and / or to extend or terminate a contract with a customer.
  • the collaborative platform 10 mainly comprises a data storage system 11, one or more computer servers 12, processing and calculation means 13 implementing artificial intelligence algorithms, and an application programming interface API (Application Programming Interface) making it possible to make the link between a local program and consumer programs executed in companies 20.
  • the collaborative platform 10 can be physical or, preferably, virtual, in which case it has a virtualization layer grouping together all or part of the aforementioned elements, in particular the storage system 11 and the servers 12, so as to obtain a cloud architecture, commonly called “cloud (Cloud computing), offering the platform advantageous agility and computing capacity.
  • cloud Cloud computing
  • the collaborative platform 10 is accessible via an Internet-type network and can be in the form of software as a SaaS (Software as a Service) service, or of a supplier program accessible via the API by programs. consumers.
  • the collaborative platform 10 is a web-based SaaS.
  • the storage system 11, is a cloud database to which is connected, in a secure manner, each company 20 of the community by means of internal management software 21 such as an ERP (Enterprise Resource Planning) integrated management software package, to share information on the collaborative platform 10.
  • Information sharing with the platform can be done differently.
  • the database 11 thus allows each company 20 member of the community to contribute data 22 customers / prospects, such as customer portfolios and billing statements, necessary for the training of the machine learning models implemented. by the calculation means 13.
  • the connection between the management software 21 and the database 11 may require a specific interfacing program (gateway) which would for example be installed at the user, namely the member company, beforehand. the use of the collaborative platform 10.
  • the database 11, according to one embodiment, is distributed on a blockchain to secure the internal data provided by the companies 20 of the community to the collaborative platform 10.
  • this blockchain is advantageously used to secure transactions from / between members of the community, provided by the collaborative platform as explained below, by using electronic signatures and smart contracts.
  • the calculation means 13 correspond to processing and calculation units, of the computer type, on which programs Specifics are installed to process data and run machine learning models by one or more processors.
  • the data processing operations carried out relate in particular to big data arriving on the collaborative platform 10 from a multitude of sources.
  • the collaborative platform 10 is available on the network and accessible to companies 20 members of the community, under certain subscription conditions, by various terminals 25 and personal means of communication and assistance, shown in FIG. 3, such as a computer 25a. , via a web interface, a digital tablet 25b and a smartphone 25c, via dedicated mobile applications. Access to the collaborative platform 10 is therefore facilitated to adapt to remote management and an almost permanent connection, according to a way of working more and more adopted by the leaders of companies such as startups.
  • relationship R1 in the case of the company E1 in FIG. 2, through which said platform collects data.
  • various data from the community and C customers and prospects in the community corresponds to data external to the community, which will be called external data 30, and whose sources will be listed below.
  • external data 30 contextual data can be collected through sources and specialized organizations and will participate in the development of predictions of payment defaults suffered by companies 20 and in the calculation of the scores of customers / prospects of said companies.
  • Figure 3 shows the overall system architecture of the collaborative platform 10, which is organized into three paradigms: data collection, data exploitation and information presentation. It is easy to understand that the companies 20 members of the community, by their use of the collaborative platform 10, are both a source of data and a target (recipients) of information transformed on the cloud. This observation will be explained on reading Figure 4.
  • the data collected by the collaborative platform 10 comprises data from companies 20 of the community and data from customers C and other companies not forming part of the community.
  • the community in the broad sense includes active members: companies 20 using the collaborative platform, and passive members: customers and prospects C.
  • a company 20 member of the community can also be a client C of another company 20 that is a member of the community.
  • the data of the members 20 is essentially transactional and includes for example: customer portfolios, billing statements, invoices, quotes, etc.
  • External data from customers / prospects C, are essentially financial, provided by partners such as data providers, and make it possible to estimate the financial health of customers and therefore their predisposition to honor a contractual commitment such as an invoice that is due.
  • the collaborative platform 10 then makes it possible to use the raw data received by performing extraction, processing and prediction operations using the platform's calculation means, before storing the various information that will be communicated on the terminals. 25 users via the different interfaces.
  • the information is then presented on the interfaces available to each company using the platform, namely web interfaces, mobile APP applications, but also by electronic mail (email).
  • the API of the collaborative platform makes it possible to make the link between the user interfaces (consumer programs such as mobile applications and web extensions) and the supplier programs installed in said platform.
  • the aforementioned operations will be explained in more detail when describing the prevention process implemented by the collaborative platform. However, it is necessary to identify beforehand the main data exchanged between the collaborative platform and the companies of the community.
  • FIG. 4 schematically represents a user 20 (member company) in its data exchange relationship with the collaborative platform 10.
  • the company 20 mainly transmits, automatically via the ERP or manually, customer payment histories 210. and payment defaults 220, late payments or unpaid bills, noted.
  • the collaborative platform 10 is able to return to the company 20 prevention information 110 relating to the customers and prospects of said company.
  • the prevention information 110 includes, for example: risk alerts 111, credit risk scores 112 and information reports 113.
  • a risk alert 111 occurs when an analyzed risk becomes critical and informs, for example, of an imminent payment default on the part of a customer, of the approach of the due date of a given invoice, of a general problematic situation of a customer, a worrying deterioration in a customer's score, etc.
  • the risk alert 111 corresponds to an emergency situation and requires priority treatment.
  • a credit risk score 112 simply corresponds to the score assigned by the collaborative platform to a given customer or prospect.
  • the scores are calculated according to known methods such as the scoring system described in "Yoshino, Naoyuki & Taghizadeh-Hesary, Farhad. (2015). Analysis of Credit Ratings for Small and Medium-Sized Enterprises: Evidence from Asia. Asian Development Review. 32. 18-37. 10.1162 / ADEV_a_00050. ".
  • This scoring system makes it possible to calculate for each company an X score ranging from 0 to 10, corresponding to a qualitative financial score (star system on graphical interfaces for example) and to a credit score further framing the decisions to be made.
  • X score ranging from 0 to 10
  • a qualitative financial score star system on graphical interfaces for example
  • a credit score further framing the decisions to be made.
  • An information report 113 can, for its part, contain different information, classified according to its relevance in the decision-making or simply presented in a thematic way, and makes it possible to draw up a risk profile for each client or prospect.
  • the data provided by all companies in the community is centralized in the collaborative platform and is used indifferently according to the models carried out to establish the information intended for each of the aforesaid companies.
  • a given customer can be found in several payment histories provided by different companies, which allows the collaborative platform to reconstruct a payment history specific to the customer audit, which will impact the predictions obtained with respect to the same. client, and which remains accessible to businesses in the community in order to enable them to make informed transactional decisions involving this client.
  • the collaborative platform 10 in addition to the prevention information 110, is able to provide companies 20 members of the community with additional services, depending on the contracts subscribed, such as reimbursement 120 of unpaid debts, or debt collection, thanks to pooling of risks between members of the community; and pooled financing of customer invoices between community members based on a peer-to-peer model, which stems from the collaborative aspect of the platform.
  • FIG. 5 represents the main steps of a method 500, implemented by the collaborative platform 10, for forecasting the risks associated with payment defaults in a company 20, said forecast being broken down into two parts each representing a possible use of said platform: the prediction component of customer defaults 520 and the selection of prospects component 530.
  • each company 20 Before being able to use the collaborative platform 10, each company 20 must make a 510 subscription to create its user account giving it access to more or less personalized services, depending on the needs of the company, its turnover, its customer portfolio volume, etc.
  • the subscription 510 is therefore an initial step of the risk forecasting method 500, and can be carried out by following ordinary steps of registration and online subscription.
  • the subscription of a company 20 to the collaborative platform 10 involves the following steps, some of which are obviously optional:
  • the platform is compatible with various existing ERPs, through specific gateways, and is able to collect information such as customer portfolio, billing history, quotes, etc.
  • the collaborative platform is also able to import information compiled into ordinary spreadsheets such as Excel files (Microsoft Excel).
  • the establishment of the connection between the collaborative platform 10 and the ERP 21 of a member company 20, see FIG. 2 can be done just after the finalization of the subscription 510.
  • the subscriber namely a person from the company receives an email inviting him to download a program that he must install on his computer system.
  • This CDMS program will then allow the company to establish a link between the collaborative platform and its ERP by choosing the gateway corresponding to its type of ERP (among the trademarks CIEL, ORACLE, SAP, Microsoft, etc.).
  • this program constitutes a bridge between the accounting system of the member company and the collaborative platform, and allows an automated transfer, in real time, of information extracted in a targeted manner so as to feed the platform with any relevant data to assessment of the risk of default.
  • the risk forecasting method 500 mainly comprises:
  • the data export step 521 makes it possible to feed the collaborative platform 10 with financial and accounting data from the companies 20 in the community, so that said platform is able to identify and predict possible payment defaults.
  • Data export is carried out through the secure link established between the company's accounting tool, such as the ERP, and the platform's database as described above (automatic export or manual, CDMS, etc.).
  • the customer portfolio exported at the start, with the possibility of adding new customers later; invoices, periodically, preferably daily; customer payment history, also periodically, preferably weekly for better forecasting of defaults.
  • the exported data can be time-stamped 610 in order to establish proof of dates on said data and to avoid any conflict with a company which, for example, would claim not to have been alerted to an unpaid invoice on an exported invoice, when the latter this would have been truly exported after the deadline.
  • the step 522 of data collection by the collaborative platform 10 corresponds to operations of extraction, standardization and classification of the useful data in the database of said platform to allow the execution of the analysis and prediction algorithms. .
  • the collected data is then fed into platform algorithms such as machine learning models implemented in a permanent machine learning step 620.
  • the analysis and prediction step 523 makes it possible both to analyze the status of each imported invoice with a view to detecting a payment default according to well-established calendar rules, and to predict the occurrence of such a default by machine learning, taking into account the risk profile of clients, temporal attributes, contextual data (financial health of customers, economic situation in the customer's country, events, etc.).
  • the prediction of payment defaults is thus based on the construction of a predictive model from contextual data.
  • Different types of learning models supervised or unsupervised, can be used, such as decision tree model, clustering model, Bayesian network model, probabilistic graphical model, rule-based model and / or a support vector machine model.
  • the aforementioned machine learning models can be implemented alone or in combination in an artificial neural network architecture, in which case Deep Learning methods are used.
  • the neural network comprises a certain number of nodes, connected by various branches and divided into layers: input, hidden layers and output.
  • Each node represents a request for one or more attributes associated with an invoice 22, the input attributes being for example the date of issue of the invoice, the name of the customer, the amount excluding tax, etc.
  • the result of a request represented by a current node determines the branch, emanating from the current node, to follow in order to reach another node of the neural network.
  • the last node of a particular branch estimates a default on the invoice such as late payment for example.
  • the analysis and prediction step 523 also makes it possible to predict the cash flow of each company 20 in the community based on the data imported into the collaborative platform. This is a dual prediction of the prediction of defaults. In other words, the prediction of payment defaults for a company conditions, with a few parameters, the prediction of the cash flow of said company.
  • the information and recommendation step 524 allows the collaborative platform 10 to provide prevention information (risk alert, and information report), necessary for a considered decision-making on the part of the company 20, and to suggest the most appropriate action taking into account the result of the analysis and the prediction carried out in the previous step.
  • the information obtained is displayed interactively on the various user interfaces (web and mobile application) to allow easy reading and immediate access to the information.
  • Figures 6, 7A and 7B illustrate examples of graphical interfaces 251 for presenting information on a smartphone 25 via a mobile application.
  • the interface can thus include different sections 252 showing information in the form of curves and graphs 253 (sectors, histograms and others), as well as lists of invoices, quotes, customers and others, allowing access to their elements 254.
  • the risk forecasting method 500 mainly comprises:
  • the prospect search step 531 allows the company 20 to search for prospects through the collaborative platform 10 in order to access the scores assigned to them by said platform.
  • This search can be simple or advanced, with the selection of certain criteria such as industrial sector, turnover, geographical location, etc.
  • the platform is also able to save the preferences of companies that have already carried out prospect research.
  • the score display step 532 makes it possible to list the various prospects found with the scores assigned to them by the collaborative platform according to a scoring system such as that presented above.
  • the presentation of the search result with the score can be graphically similar to the presentation given in Figure 7B for a company's customer portfolio.
  • the choice step 533 consists in selecting the prospects retained by the company 20. However, it should be noted that this choice may not be motivated by the score. attach.
  • the scores are simple indicators and the final decision rests in full power with the company 20 despite the use of the collaborative platform, which is a decision support tool only.
  • the step 534 of adding the prospects chosen by the company 20 ultimately makes it possible to add said prospects to a list that can be consulted via the menu of the web interface or of the mobile application.
  • the collaborative platform 10 also makes it possible, according to another aspect of the invention, to pool the risks incurred by the companies that are members of the community.
  • the collaborative platform makes it possible to reimburse all or part of the unpaid debts suffered by members of the community who have taken out this insurance option on the platform.
  • Figure 9 shows the course of a process for compensating the balance of a member of the community following an unpaid debt, said process, taken independently of the rest of the above prevention process, comprises:
  • a subscription step 510 which may correspond to a first subscription to the collaborative platform with the "insurance” option or to an additional subscription to the "insurance” service;
  • the collaborative platform thus described allows a community of companies to share their customer payment experiences so that each of them can learn about the payment history of a given prospect in time. real when the latter asks them for a quote, for example, and makes the appropriate decision.
  • the collaborative platform allows, thanks to data collected from different sources, to predict payment defaults by machine learning, thus facilitating risk management for the most vulnerable companies such as SMEs.
  • the collaborative platform and the associated processes can be implemented according to variants, for example with the addition and / or modification of certain technical characteristics, without departing from the scope of the invention.
  • the platform can offer functionalities such as the edition of electronic invoices between the members of the community, the periodic sending of a targeted list of prospects which can correspond to the expectations of a member according to data collected in auxiliary sources such as social networks.

Landscapes

  • Business, Economics & Management (AREA)
  • Accounting & Taxation (AREA)
  • Engineering & Computer Science (AREA)
  • Strategic Management (AREA)
  • Finance (AREA)
  • Development Economics (AREA)
  • Economics (AREA)
  • Theoretical Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Human Resources & Organizations (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Marketing (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Educational Administration (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • Data Mining & Analysis (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

Collaborative electronic platform (100) for predicting non-payments between a company (20) and customers of the company, comprising a data storage system (11), at least one computer server (12) and means (13) for processing and calculating which implement at least one machine learning model, the platform being capable of importing the company's financial data, the model estimating the occurrence of non-payments on the part of customers on the basis of the imported financial data, the platform being connected to a plurality of companies (20) forming a real-time information sharing community on the platform, which is capable of sending any information shared by a first company to other companies in the community which are interested in said information, and comprising an application programming interface API for executing a user risk management program on terminals (25) of the companies that are part of the community.

Description

Plateforme électronique collaborative pour la prédiction de défauts de paiement entre entreprises et procédé associé Collaborative electronic platform for the prediction of payment defaults between companies and associated process
DOMAINE TECHNIQUE TECHNICAL AREA
La présente invention appartient au domaine général des technologies financières et d’assurance ( fintech et insurtech), notamment de l’automatisation de la gestion des risques, et concerne plus particulièrement une plateforme électronique collaborative pour la prédiction de défauts de paiement entre entreprises, tels que les retards de paiement et les impayés, par apprentissage automatique ( Machine Learning), et un procédé mis en œuvre par ladite plateforme. The present invention belongs to the general field of financial and insurance technologies (fintech and insurtech), in particular of the automation of risk management, and relates more particularly to a collaborative electronic platform for the prediction of payment defaults between companies, such as that payment delays and unpaid bills, by machine learning, and a process implemented by said platform.
L’invention a également trait aux techniques de blockchain, de gestion de données big data et d’aide à la décision. The invention also relates to blockchain techniques, big data management and decision support.
ÉTAT DE L’ART STATE OF THE ART
La gestion efficace des ventes est importante pour la santé financière globale d’une entreprise. Les entreprises cherchent à réduire les créances impayées et à se prémunir des conséquences de l’accumulation de retards de paiement et d’impayés. Un des problèmes majeurs rencontrés essentiellement par les petites ou moyennes entreprises est celui des retards de paiement qui, souvent, conduit à la cessation d’activité et à l’arrêt prématuré d’entreprises y compris celles à grand potentiel économique. Effective sales management is important to the overall financial health of a business. Businesses seek to reduce bad debts and guard against the consequences of the accumulation of late payments and bad debts. One of the major problems encountered mainly by small and medium-sized enterprises is that of late payments which often leads to the cessation of activity and the premature shutdown of businesses, including those with great economic potential.
En France, à titre d’exemple, le problème des retards de paiement conduit annuellement plus de douze mille entreprises au dépôt de bilan selon certaines estimations. Pourtant, une partie des entreprises concernées a souscrit une assurance-crédit classique pour se prémunir des risques financiers liés en particulier aux défauts de paiement de la part de leurs clients. In France, for example, the problem of late payments leads annually to more than twelve thousand companies filing for bankruptcy according to some estimates. However, some of the companies concerned have taken out traditional credit insurance to protect themselves against the financial risks linked in particular to defaults on the part of their customers.
En outre, les défauts de paiement récurrents subis par une entreprise impactent sa trésorerie et ne lui permettent pas de faire face sereinement à ses divers besoins de financement, besoins auxquels les assureurs n’apportent pas de solutions satisfaisantes. De ce fait, certaines entreprises, surtout sous-traitantes, ne disposent pas d’outils efficaces et bénéfiques de financement. Malgré le fait que la priorité doit aller à la réduction des délais de paiement, il est également essentiel d’aider davantage les entreprises à mieux faire face à leurs besoins de trésorerie. Les sociétés d’assurance-crédit qui dominent actuellement le marché proposent d’aider les entreprises à éviter les créances douteuses et les mauvais payeurs, en leur donnant un avis sur les clients ou prospects avec lesquels lesdites entreprises souhaitent travailler. Ces avis sont simplement basés sur un réseau d’experts en risque, qui analysent en permanence les données financières des sociétés, les secteurs industriels, les risques contextuels (pays, évènements, etc.) et d’autres facteurs, afin d’alerter les entreprises assurées sur les risques potentiels. In addition, the recurring defaults suffered by a company impact its cash flow and do not allow it to calmly face its various financing needs, needs to which insurers do not provide satisfactory solutions. As a result, some companies, especially subcontractors, do not do not have effective and beneficial financing tools. While the priority must be on reducing payment terms, it is also essential to further help businesses cope better with their cash flow needs. The credit insurance companies that currently dominate the market offer to help companies avoid bad debts and bad debtors, by giving them an opinion on the customers or prospects with whom the said companies wish to work. These opinions are simply based on a network of risk experts, who constantly analyze the financial data of companies, industrial sectors, contextual risks (countries, events, etc.) and other factors, in order to alert them. companies insured on potential risks.
Cette approche n’est absolument pas adaptée aux très petites, petites ou moyennes entreprises qui n’ont pas forcément le privilège d’être accompagnées de près par des experts, des experts qui, en plus, ne peuvent pas analyser la quantité phénoménale de données générée par ce tissu économique complexe des TPE/PME, ne peuvent pas se rendre disponibles pour chaque transaction financière douteuse, ne peuvent pas intégrer l’influence de données contextuelles et comportementales comme le ferait un modèle d’apprentissage automatique, etc. Les récentes avancées technologiques comme la blockchain, le big data, l’internet des objets et l’intelligence artificielle permettent aujourd’hui de créer des solutions nouvelles qui ne laissent plus la place à l’intervention humaine dans l’analyse pré décisionnelle d’un problème complexe comme celui de la prévision des défauts de paiement. This approach is absolutely not suitable for very small, small or medium-sized companies which do not necessarily have the privilege of being closely accompanied by experts, experts who, in addition, cannot analyze the phenomenal amount of data. generated by this complex economic fabric of VSEs / SMEs, cannot make themselves available for each questionable financial transaction, cannot integrate the influence of contextual and behavioral data as would a machine learning model, etc. Recent technological advances such as blockchain, big data, the Internet of Things and artificial intelligence now make it possible to create new solutions that no longer leave room for human intervention in the pre-decision analysis of a complex problem such as that of forecasting defaults.
Le document US2019287182A1 , au nom de American Express, décrit un procédé permettant d’établir un score de conformité pour un consommateur à partir d'un historique de transactions, ayant des informations associées à une pluralité de transactions, au moyen d’un réseau de neurones artificiels. Cette solution ne permet pas de prédire un score pour des prospects et ne tient pas compte de données externes au consommateur. Document US2019287182A1, on behalf of American Express, describes a method for establishing a compliance score for a consumer from a history of transactions, having information associated with a plurality of transactions, using a network of artificial neurons. This solution does not predict a score for prospects and does not take into account data external to the consumer.
Le document US2018232814A1 , au nom d’Oracle, propose d’utiliser des modèles d’apprentissage automatique pour estimer un défaut de paiement sur une facture. De multiples modèles d’estimation de défauts de paiements sont générés à partir d’une pluralité de factures réparties en ensembles d’entrainement. Cette solution, également personnelle, ne permet aucune utilisation de données externes ou de données « collectives » issues d’autres utilisateurs. Document US2018232814A1, on behalf of Oracle, proposes to use machine learning models to estimate a default on an invoice. Multiple defaults estimate models are generated from a plurality of invoices divided into training sets. This solution, also personal, does not allow any use of external data or "collective" data from other users.
Aucune solution, à la connaissance du demandeur, ne permet actuellement d’exploiter des informations partagées en temps réel par une communauté d’entreprises autour d’une plateforme centralisée pour prédire des défauts de paiement, y compris vis-à-vis de nouveaux clients pour lesquels l’entreprise concernée ne dispose pas encore d’historique de paiement, les informations manquantes étant fournies par d’autres entreprises lors du partage de données. No solution, to the knowledge of the applicant, currently allows the use of information shared in real time by a community of companies around a centralized platform to predict payment defaults, including vis-à-vis new customers. for which the concerned company does not yet have a payment history, the missing information being provided by other companies during the data sharing.
PRÉSENTATION DE L’INVENTION PRESENTATION OF THE INVENTION
La présente invention vise à pallier les inconvénients de l’art antérieur ci-dessus exposés, notamment l’absence de solutions de gestion de risque de crédit adaptées aux petites ou moyennes entreprises et permettant d’instaurer une communauté d’entraide et de partage d’informations entre une pluralité d’entreprises. The present invention aims to overcome the drawbacks of the prior art described above, in particular the absence of credit risk management solutions suitable for small or medium-sized enterprises and making it possible to establish a community of mutual aid and sharing of information. information between a plurality of companies.
À cet effet, la présente invention a pour objet une plateforme électronique collaborative pour la prédiction de défauts de paiement entre une entreprise et des clients de ladite entreprise, comprenant un système de stockage de données, au moins un serveur informatique et des moyens de traitement et de calcul implémentant au moins un modèle d’apprentissage automatique, la plateforme étant apte à importer des données financières de l’entreprise par le biais d’une liaison sécurisée entre le système de stockage de données et un outil de gestion interne de ladite l’entreprise, ledit modèle estimant l’occurrence de défauts de paiement de la part des clients en se basant sur les données financières importées. Cette plateforme collaborative est remarquable en ce qu’elle est reliée à une pluralité d’entreprises formant une communauté de partage d’informations en temps réel sur la plateforme, en ce qu’elle est apte à transmettre toute information partagée par une première entreprise à au moins une deuxième entreprise de la communauté pour laquelle ladite information présente un intérêt, et en ce qu’elle comprend une interface de programmation applicative API permettant d’exécuter un programme utilisateur de gestion des risques sur des terminaux des entreprises de la communauté. To this end, the present invention relates to a collaborative electronic platform for the prediction of payment defaults between a company and customers of said company, comprising a data storage system, at least one computer server and processing means and calculation implementing at least one machine learning model, the platform being able to import financial data from the company by means of a secure link between the data storage system and an internal management tool of said the company, said model estimating the occurrence of customer defaults on the basis of the imported financial data. This collaborative platform is remarkable in that it is linked to a plurality of companies forming a community for sharing information in real time on the platform, in that it is able to transmit any information shared by a first company to at least one second enterprise of the community for which said information is of interest, and in that it comprises an application programming interface API making it possible to execute a user program for risk management on terminals of enterprises of the community.
Avantageusement, la plateforme collaborative est reliée à des sources de données externes, et les moyens de traitement et de calcul comportent des algorithmes de notation permettant de déterminer un score pour toute entreprise à partir d’informations sur ladite entreprise contenues dans les données externes importées par ladite plateforme. Advantageously, the collaborative platform is linked to external data sources, and the processing and calculation means include algorithms for rating making it possible to determine a score for any company from information on said company contained in the external data imported by said platform.
Selon un mode de réalisation particulièrement avantageux, la plateforme collaborative présente une architecture en nuage avec une couche de virtualisation comprenant au moins le système de stockage de données et tout serveur, ladite plateforme étant accessible via un réseau de type internet. According to a particularly advantageous embodiment, the collaborative platform has a cloud architecture with a virtualization layer comprising at least the data storage system and any server, said platform being accessible via an Internet type network.
Selon un mode de réalisation, le système de stockage de données comprend une base de données et les moyens de traitement et de calcul comprennent au moins un processeur, ladite base de données pouvant être distribuée sur une chaîne de blocs. According to one embodiment, the data storage system comprises a database and the processing and calculation means comprise at least one processor, said database being able to be distributed on a chain of blocks.
De façon avantageuse, les informations partagées par les entreprises membres de la communauté comprennent des historiques de paiement des clients de chaque entreprise, et les données financières importées comprennent des portefeuilles clients, des factures, des devis, etc. Advantageously, the information shared by the member companies of the community includes payment histories of the customers of each company, and the imported financial data includes customer portfolios, invoices, quotes, etc.
Selon l’invention, au moins un modèle d’apprentissage automatique construit une prédiction de défaut de paiement sur une facture à partir d’attributs relatifs à ladite facture, de données financières importées sur la plateforme et de données contextuelles. According to the invention, at least one machine learning model constructs a prediction of default on an invoice from attributes relating to said invoice, financial data imported to the platform and contextual data.
La présente invention a également pour objet un procédé de prévision des risques liés à des défauts de paiement entre une entreprise et des clients de ladite entreprise, mis en œuvre par une plateforme collaborative telle qu’elle a été présentée, caractérisé en ce qu’il comprend : The present invention also relates to a method for forecasting the risks associated with payment defaults between a company and customers of said company, implemented by a collaborative platform as it has been presented, characterized in that it understand :
- une étape initiale de souscription de l’entreprise à la plateforme ; - an initial stage of the company's subscription to the platform;
- une étape d’export de données d’un outil de gestion interne de l’entreprise vers le système de stockage de données de la plateforme ; - a step of exporting data from an internal management tool of the company to the platform's data storage system;
- une étape d’analyse et de prédiction mettant en œuvre au moins un modèle d’apprentissage automatique ; - an analysis and prediction step implementing at least one machine learning model;
- une étape de présentation, sur un terminal de l'entreprise, d’informations basées sur des résultats de l’étape précédente. - a stage of presentation, on a company terminal, of information based on the results of the previous stage.
Plus particulièrement, l’étape d’analyse et de prédiction utilise des données fournies par plusieurs entreprises de la communauté ainsi que des données externes provenant de sources telles que des fournisseurs de données financières, et permet également de détecter des défauts de paiement en tenant compte des délais d’échéance des factures importées sur la plateforme. More specifically, the analysis and prediction step uses data provided by several companies in the community as well as external data from sources such as financial data providers, and allows also to detect payment defaults, taking into account the deadlines of invoices imported on the platform.
De façon avantageuse, l’étape de présentation d’informations produit des informations de prévention comprenant au moins une information parmi une alerte de risque, un score de risque de crédit et un rapport d’information, ce dernier correspondant au profil de risque d'un client de l’entreprise. Advantageously, the information presentation step produces prevention information comprising at least one item of information from among a risk alert, a credit risk score and an information report, the latter corresponding to the risk profile of a client of the company.
Selon un mode de réalisation, le procédé comprend en outre une opération ou une combinaison d’opérations parmi : un remboursement d'impayés en faveur d’entreprises de la communauté (recouvrement de créance), suivant un système de mutualisation des risques centralisé dans la plateforme collaborative et sécurisé par une chaîne de blocs ; un financement mutualisé de factures clients, entre des entreprises membres de la communauté, selon un modèle de financement pair-à- pair géré par la plateforme collaborative et sécurisé sur la chaîne de blocs ; et une prédiction de la trésorerie de chaque entreprise de la communauté sur la base des données importées dans ladite plateforme. According to one embodiment, the method further comprises an operation or a combination of operations among: a reimbursement of unpaid debts in favor of companies of the community (debt collection), according to a system of pooling of risks centralized in the collaborative platform secured by a blockchain; pooled financing of customer invoices, between member companies of the community, according to a peer-to-peer financing model managed by the collaborative platform and secured on the blockchain; and a cash flow prediction of each business in the community based on the data imported into said platform.
Les concepts fondamentaux de l’invention venant d’être exposés ci-dessus dans leur forme la plus élémentaire, d’autres détails et caractéristiques ressortiront plus clairement à la lecture de la description qui suit et en regard des dessins annexés, donnant à titre d’exemple non limitatif des modes de réalisation d’une plateforme collaborative et d’un procédé de prévention de risque associé, conformes aux principes de l’invention. The fundamental concepts of the invention having just been explained above in their most elementary form, other details and characteristics will emerge more clearly on reading the description which follows and with reference to the appended drawings, giving by way of non-limiting example of the embodiments of a collaborative platform and of an associated risk prevention method, in accordance with the principles of the invention.
BRÈVE DESCRIPTION DES FIGURES BRIEF DESCRIPTION OF THE FIGURES
Les figures sont données à titre purement illustratif pour l’intelligence de l’invention et ne limitent pas la portée de celle-ci. Sur l’ensemble des figures, les éléments identiques ou équivalents portent la même référence numérique. The figures are given for illustrative purposes only for the understanding of the invention and do not limit the scope thereof. In all of the figures, identical or equivalent elements bear the same reference numeral.
Il est ainsi illustré en : It is thus illustrated in:
- Figure 1 : un schéma de principe d’une plateforme collaborative selon un aspect de l’invention ; - Figure 1: a block diagram of a collaborative platform according to one aspect of the invention;
- Figure 2 : un schéma synoptique de la plateforme collaborative interagissant avec une communauté d’entreprises ; - Figure 2: a block diagram of the collaborative platform interacting with a community of companies;
- Figure 3 : un exemple d’architecture système de la plateforme collaborative selon l’invention ; - Figure 4 : un exemple d’informations échangées entre la plateforme collaborative et une entreprise membre de la communauté ; - Figure 3: an example of system architecture of the collaborative platform according to the invention; - Figure 4: an example of information exchanged between the collaborative platform and a company member of the community;
- Figure 5 : les principales étapes d’un procédé de prévention des risques de défauts de paiement selon un mode de réalisation de l’invention ; - Figure 5: the main steps of a method for preventing the risk of payment defaults according to one embodiment of the invention;
- Figure 6 : un exemple d’interface graphique sur une application mobile d’interaction avec la plateforme collaborative ; - Figure 6: an example of a graphical interface on a mobile application for interaction with the collaborative platform;
- Figure 7 A : un exemple de présentation d’information sur l’application mobile ; - Figure 7 A: an example of presentation of information on the mobile application;
- Figure 7B : un autre exemple de présentation d’information ; - Figure 7B: another example of presentation of information;
- Figure 8 : un schéma blocs partiel d’un modèle d’apprentissage automatique exécuté dans la plateforme collaborative ; - Figure 8: a partial block diagram of a machine learning model executed in the collaborative platform;
- Figure 9 : les principales étapes d’un procédé de mutualisation des risques entre membres de la communauté selon un mode de réalisation de l’invention. - Figure 9: the main steps of a process for pooling risks between members of the community according to one embodiment of the invention.
DESCRIPTION DÉTAILLÉE DE MODES DE RÉALISATION DETAILED DESCRIPTION OF EMBODIMENTS
Il convient de noter au préalable que certains dispositifs, systèmes et méthodes bien connus sont ici décrits et expliqués pour éviter toute insuffisance ou ambiguïté dans la compréhension de la présente invention. It should be noted beforehand that certain well known devices, systems and methods are described and explained herein in order to avoid any insufficiency or ambiguity in the understanding of the present invention.
Dans les modes de réalisation décrits ci-après, on fait référence à un système informatique, sous forme de plateforme électronique collaborative, pour la prédiction de défauts de paiement entre entreprises, destiné principalement à des entités de type petites ou moyennes entreprises (PME) afin de leur permettre une meilleure gestion des risques financiers inhérents aux défauts de paiement, tels que les retards de paiement et impayés, de la part de leurs clients, mais également une aide décisionnelle dans le choix de leurs prospects. Cet exemple, non limitatif, est donné pour une meilleure compréhension de l’invention et n’exclut pas l’utilisation de la plateforme collaborative dans d’autres contextes industriels ou économiques pour la prédiction d’évènements à risque. In the embodiments described below, reference is made to a computer system, in the form of a collaborative electronic platform, for the prediction of payment defaults between companies, intended mainly for entities of the small or medium-sized enterprises (SMEs) type in order to to allow them better management of the financial risks inherent in payment defaults, such as late payments and unpaid bills, on the part of their customers, but also decision support in the choice of their prospects. This non-limiting example is given for a better understanding of the invention and does not exclude the use of the collaborative platform in other industrial or economic contexts for the prediction of risk events.
Rappelons que dans toute chaîne économique, les défauts de paiement constituent un risque majeur et entraînent un effet cascade pour les entreprises. Ce risque se révèle être critique pour les entreprises les plus fragiles, dont l’activité peut être mise en péril à cause des délais de paiement pratiqués par leurs clients, ou tout au moins, négligeable pour les entreprises de plus importante envergure, mais impactant leur trésorerie voire limitant leur croissance. Remember that in any economic chain, payment defaults constitute a major risk and lead to a cascade effect for companies. This risk turns out to be critical for the most fragile companies, whose activity can be endangered because of the payment delays practiced by their customers, or at least, negligible for larger companies, but impacting their cash flow or even limiting their growth.
Dans la suite de la description, on se place dans le contexte particulier de la réglementation française et/ou européenne et on désigne par le sigle PME les petites ou moyennes entreprises. Néanmoins, il faut souligner que les limites, en termes d’effectif ou de chiffre d’affaire, définissant la taille des entreprises varient d’un pays à l’autre. « PME » désignera donc par extension toute catégorie d’entreprises équivalente. In the remainder of the description, we place ourselves in the particular context of French and / or European regulations and the acronym PME denotes small or medium-sized enterprises. However, it should be noted that the limits, in terms of staff or turnover, defining the size of companies vary from country to country. "SME" will therefore designate by extension any equivalent category of business.
La figure 1 représente de façon simplifiée le principe de fonctionnement d’une plateforme collaborative 10 selon un premier aspect de l’invention. La plateforme collaborative 10 permet de réunir une pluralité d’entreprises 20 dans une communauté de partage d’informations, lesdites entreprises portant les références E1 , E2 et E3 pour être distinguées les unes des autres dans le cas d’espèce. Ainsi, chaque entreprise peut partager en temps réel avec les autres entreprises de la communauté ses expériences de paiement client, autrement dit l’état de paiement ou le statut comptable de ses factures, de sorte à permettre à la plateforme collaborative d’établir des profils de comportement des clients de chaque entreprise de la communauté, C1 à C6 sur la figure 1 . La plateforme collaborative 100 permet en effet de compiler les différentes données issues d’historiques de paiement fournis par les entreprises 20 de la communauté et d’adresser des recommandations préventives auxdites entreprises sur la base d’analyses statistiques et/ou de modèles d’apprentissage automatique décrits plus loin. FIG. 1 shows in a simplified manner the operating principle of a collaborative platform 10 according to a first aspect of the invention. The collaborative platform 10 makes it possible to bring together a plurality of companies 20 in an information-sharing community, said companies bearing the references E1, E2 and E3 to be distinguished from each other in this case. Thus, each company can share in real time with other companies in the community its customer payment experiences, in other words the payment status or the accounting status of its invoices, so as to allow the collaborative platform to establish profiles. behavior of the customers of each company in the community, C1 to C6 in Figure 1. The collaborative platform 100 makes it possible to compile the various data from payment histories provided by companies 20 in the community and to send preventive recommendations to said companies on the basis of statistical analyzes and / or learning models. automatic described below.
Par exemple, lorsqu’une entreprise E1 membre de la communauté, autrement dit utilisant la plateforme collaborative 10, fait l’objet d’un défaut de paiement N11 de la part de son client C1 , ce défaut de paiement est automatiquement partagé sur la plateforme collaborative 10, laquelle en tient compte dans l’attribution d’un score S1 actualisé au client C1 . Selon un aspect de l’invention détaillé plus loin, la plateforme collaborative 10 attribue un score suivant une notation précise à chaque client des entreprises de la communauté et à tout autre entité susceptible d’être sollicitée par un membre actuel ou futur de ladite plateforme, ces scores reflétant les comportements de paiement. De toute évidence, les défauts de paiement constatés ont un impact négatif sur les score attribués par la plateforme 10 aux entreprises en défaut. De la même façon, le bon comportement P25 du client C5 dans sa relation commerciale, surtout ses transactions financières, avec l’entreprise E2 est partagé sur la plateforme collaborative et impacte positivement le score S5 dudit client. Ensuite, l’entreprise E3, également membre de la communauté, en cherchant un prospect, est informée en temps réel des scores des prospects qu’elle cible, notamment des scores de C1 et C5. Le score négatif S1 de C1 permet à la plateforme collaborative 10 de déconseiller à E3 une transaction T31 avec C1 . Au contraire, le bon score S5 du prospect C5, client de E2, permet d’encourager l’entreprise E3 à engager une transaction T35 avec ledit prospect. For example, when a company E1 member of the community, in other words using the collaborative platform 10, is the subject of a payment default N11 on the part of its customer C1, this payment default is automatically shared on the platform. collaborative 10, which takes it into account when assigning an updated S1 score to customer C1. According to an aspect of the invention detailed below, the collaborative platform 10 assigns a score according to a precise rating to each client of businesses in the community and to any other entity likely to be solicited by a current or future member of said platform, these scores reflect payment behavior. Obviously, the payment defaults observed have a negative impact on the scores assigned by the platform 10 to defaulting companies. Likewise, the good behavior P25 of the client C5 in his relationship business, especially its financial transactions, with the company E2 is shared on the collaborative platform and positively impacts the S5 score of said customer. Then, the E3 company, also a member of the community, by looking for a prospect, is informed in real time of the scores of the prospects it targets, in particular the scores of C1 and C5. The negative S1 score of C1 allows the collaborative platform 10 to advise E3 against a T31 transaction with C1. On the contrary, the good S5 score of prospect C5, a customer of E2, makes it possible to encourage company E3 to initiate a T35 transaction with said prospect.
L’exemple simplifié ci-dessus, outre les fonctions sommaires de la plateforme collaborative, expose les principaux objectifs de celle-ci et met l’accent sur l’importance d’une analyse comportementale des clients dans la prédiction des défauts de paiement. En effet, les causes d’un défaut de paiement ne se limitent pas forcément à une défaillance d'entreprise au sens habituel (impliquant un dépôt de bilan), auquel cas le défaut de paiement serait prévisible car corrélé à un évènement prévisible à court terme. Souvent, les défauts de paiement correspondent tout simplement à des échéances volontairement non honorées, et sont donc difficilement prévisibles dans le cas de prospects inconnus. D’où l’intérêt d’une connaissance préalable du comportement des prospects, connaissance rendue possible grâce au partage d’information sur la plateforme collaborative et aux ressources disponibles. The simplified example above, in addition to the basic functions of the collaborative platform, outlines the main objectives of the platform and emphasizes the importance of customer behavioral analysis in the prediction of payment defaults. Indeed, the causes of a payment default are not necessarily limited to a business failure in the usual sense (involving a bankruptcy), in which case the payment default would be predictable because it is correlated with a foreseeable short-term event. . Often, payment defaults simply correspond to deadlines intentionally not honored, and are therefore difficult to predict in the case of unknown prospects. Hence the benefit of prior knowledge of prospect behavior, knowledge made possible through the sharing of information on the collaborative platform and the available resources.
La figure 2 représente schématiquement la plateforme collaborative 10 interagissant avec les principaux acteurs, à savoir les entreprises 20 membres de la communauté et les prospects/clients C, dans le but d’apporter auxdites entreprises une aide à la décision, sous forme de recommandations et d’informations, leur permettant de mieux gérer les risques de défauts de paiement, de choisir des prospects fiables et/ou de prolonger ou rompre un contrat avec un client. FIG. 2 schematically represents the collaborative platform 10 interacting with the main actors, namely companies 20 members of the community and prospects / customers C, with the aim of providing said companies with decision support, in the form of recommendations and information, allowing them to better manage the risk of payment defaults, to choose reliable prospects and / or to extend or terminate a contract with a customer.
À cet effet, la plateforme collaborative 10 comprend principalement un système de stockage de données 11 , un ou plusieurs serveurs informatiques 12, des moyens de traitement et de calcul 13 implémentant des algorithmes d’intelligence artificielle, et une interface de programmation applicative API ( Application Programming Interface) permettant de faire le lien entre un programme local et des programmes consommateurs exécutés chez les entreprises 20. La plateforme collaborative 10 peut être physique ou, de préférence, virtuelle, auquel cas elle présente une couche de virtualisation regroupant tout ou partie des éléments précités, notamment le système de stockage 11 et les serveurs 12, de sorte à obtenir une architecture en nuage, communément appelée « cloud » ( cloud computing ), offrant à ladite plateforme une agilité et une capacité de calcul avantageuses. To this end, the collaborative platform 10 mainly comprises a data storage system 11, one or more computer servers 12, processing and calculation means 13 implementing artificial intelligence algorithms, and an application programming interface API (Application Programming Interface) making it possible to make the link between a local program and consumer programs executed in companies 20. The collaborative platform 10 can be physical or, preferably, virtual, in which case it has a virtualization layer grouping together all or part of the aforementioned elements, in particular the storage system 11 and the servers 12, so as to obtain a cloud architecture, commonly called "cloud (Cloud computing), offering the platform advantageous agility and computing capacity.
Ainsi, la plateforme collaborative 10 est accessible par l’intermédiaire d’un réseau de type internet et peut être sous forme de logiciel en tant que service SaaS (Software as a Service), ou de programme fournisseur accessible via l’API par des programmes consommateurs. De préférence, la plateforme collaborative 10 est un SaaS basé web. Thus, the collaborative platform 10 is accessible via an Internet-type network and can be in the form of software as a SaaS (Software as a Service) service, or of a supplier program accessible via the API by programs. consumers. Preferably, the collaborative platform 10 is a web-based SaaS.
Le système de stockage 11 , selon un mode de réalisation de l’invention, est une base de données cloud à laquelle se connecte, de façon sécurisée, chaque entreprise 20 de la communauté au moyen d’un logiciel interne de gestion 21 tel qu’un progiciel de gestion intégrée ERP ( Entreprise Resource Planning ), pour partager des informations sur la plateforme collaborative 10. Le partage d’information avec la plateforme peut être réalisé différemment. La base de données 11 permet ainsi à chaque entreprise 20 membre de la communauté de contribuer par des données 22 clients/prospects, telles que des portefeuilles clients et des relevés de facturation, nécessaires à l’entrainement de modèles d’apprentissage automatique mis en œuvre par les moyens de calcul 13. La connexion entre les logiciels de gestion 21 et la base de données 11 peut nécessiter un programme spécifique d’interfaçage (passerelle) qui serait par exemple installé chez l’ utilisateur, à savoir l’entreprise membre, préalablement à l’utilisation de la plateforme collaborative 10. The storage system 11, according to one embodiment of the invention, is a cloud database to which is connected, in a secure manner, each company 20 of the community by means of internal management software 21 such as an ERP (Enterprise Resource Planning) integrated management software package, to share information on the collaborative platform 10. Information sharing with the platform can be done differently. The database 11 thus allows each company 20 member of the community to contribute data 22 customers / prospects, such as customer portfolios and billing statements, necessary for the training of the machine learning models implemented. by the calculation means 13. The connection between the management software 21 and the database 11 may require a specific interfacing program (gateway) which would for example be installed at the user, namely the member company, beforehand. the use of the collaborative platform 10.
La base de données 11 , selon un mode de réalisation, est distribuée sur une blockchain pour sécuriser les données internes fournies par les entreprises 20 de la communauté à la plateforme collaborative 10. De plus, cette blockchain est avantageusement utilisée pour sécuriser des transactions de/entre membres de la communauté, assurées par la plateforme collaborative comme expliqué plus loin, en recourant à des signatures électroniques et à des contrats intelligents ( smart contracts ). The database 11, according to one embodiment, is distributed on a blockchain to secure the internal data provided by the companies 20 of the community to the collaborative platform 10. In addition, this blockchain is advantageously used to secure transactions from / between members of the community, provided by the collaborative platform as explained below, by using electronic signatures and smart contracts.
Les moyens de calcul 13, selon un mode de réalisation, correspondent à des unités de traitement et de calcul, de type ordinateur, sur lesquelles des programmes spécifiques sont installés pour traiter des données et exécuter des modèles d’apprentissage automatique par un ou plusieurs processeurs. Les traitements de données opérés concernent notamment des mégadonnées (big data) arrivant sur la plateforme collaborative 10 en provenance d’une multitude de sources. The calculation means 13, according to one embodiment, correspond to processing and calculation units, of the computer type, on which programs Specifics are installed to process data and run machine learning models by one or more processors. The data processing operations carried out relate in particular to big data arriving on the collaborative platform 10 from a multitude of sources.
La plateforme collaborative 10 est disponible sur le réseau et accessible aux entreprises 20 membres de la communauté, sous certaines conditions de souscription, par différents terminaux 25 et moyens personnels de communication et d’assistance, représentés en figure 3, tels qu’un ordinateur 25a, via une interface web, une tablette numérique 25b et un smartphone 25c, via des applications mobiles dédiées. L’accès à la plateforme collaborative 10 est donc facilité pour s’adapter à une gestion à distance et à une connexion quasi-permanente, selon un mode de travail de plus en plus adopté par les dirigeants d’entreprises de type startups. The collaborative platform 10 is available on the network and accessible to companies 20 members of the community, under certain subscription conditions, by various terminals 25 and personal means of communication and assistance, shown in FIG. 3, such as a computer 25a. , via a web interface, a digital tablet 25b and a smartphone 25c, via dedicated mobile applications. Access to the collaborative platform 10 is therefore facilitated to adapt to remote management and an almost permanent connection, according to a way of working more and more adopted by the leaders of companies such as startups.
Ainsi, entre la plateforme collaborative 10 et chaque entreprise 20 membre de la communauté, s’instaure une relation d’échange de données, relation R1 dans le cas de l’entreprise E1 sur la figure 2, au travers de laquelle ladite plateforme collecte des données variées issues de la communauté et des clients et prospects C de la communauté. Ce dernier cas correspond à des données externes à la communauté, qu’on appellera données externes 30, et dont les sources seront listées plus loin. Parmi les données externes 30, des données contextuelles peuvent être collectées par l’intermédiaire de sources et d’organismes spécialisés et participeront à l’élaboration des prédictions de défauts de paiement subis par les entreprises 20 et au calcul des scores des clients/prospects desdites entreprises. Thus, between the collaborative platform 10 and each company 20 that is a member of the community, a data exchange relationship is established, relationship R1 in the case of the company E1 in FIG. 2, through which said platform collects data. various data from the community and C customers and prospects in the community. The latter case corresponds to data external to the community, which will be called external data 30, and whose sources will be listed below. Among the external data 30, contextual data can be collected through sources and specialized organizations and will participate in the development of predictions of payment defaults suffered by companies 20 and in the calculation of the scores of customers / prospects of said companies.
La figure 3 représente l’architecture système globale de la plateforme collaborative 10 qui s’organisme en trois paradigmes : la collecte de données, l’exploitation de données et la présentation d’informations. On comprend aisément que les entreprises 20 membres de la communauté, par leur utilisation de la plateforme collaborative 10, sont à la fois une source de données et une cible (destinataires) d’information transformée sur le cloud. Ce constat sera explicité à la lecture de la figure 4. Figure 3 shows the overall system architecture of the collaborative platform 10, which is organized into three paradigms: data collection, data exploitation and information presentation. It is easy to understand that the companies 20 members of the community, by their use of the collaborative platform 10, are both a source of data and a target (recipients) of information transformed on the cloud. This observation will be explained on reading Figure 4.
Toujours en référence à la figure 3, les données collectées par la plateforme collaborative 10 comprennent des données des entreprises 20 de la communauté et des données des clients C et autres entreprises ne faisant pas partie de la communauté. Dans une autre acceptation, on peut considérer que la communauté au sens large comprend des membres actifs : les entreprises 20 utilisant la plateforme collaborative, et les membres passifs : les clients et prospects C. Il faut également noter qu’une entreprise 20 membre de la communauté peut aussi être un client C d’une autre entreprise 20 membre de la communauté. Still with reference to FIG. 3, the data collected by the collaborative platform 10 comprises data from companies 20 of the community and data from customers C and other companies not forming part of the community. In another acceptance, we can consider that the community in the broad sense includes active members: companies 20 using the collaborative platform, and passive members: customers and prospects C. It should also be noted that a company 20 member of the community can also be a client C of another company 20 that is a member of the community.
Les données des membres 20 sont essentiellement transactionnelles et comprennent par exemple : les portefeuilles clients, les relevés de facturation, les factures, les devis, etc. The data of the members 20 is essentially transactional and includes for example: customer portfolios, billing statements, invoices, quotes, etc.
Les données externes, des clients/prospects C, sont essentiellement financières, fournies par des partenaires de type fournisseurs de données ( data providers), et permettent d’estimer la santé financière des clients et donc leur prédisposition à honorer un engagement contractuel tel qu’une facture parvenue à échéance. External data, from customers / prospects C, are essentially financial, provided by partners such as data providers, and make it possible to estimate the financial health of customers and therefore their predisposition to honor a contractual commitment such as an invoice that is due.
La plateforme collaborative 10 permet ensuite d’exploiter les données brutes reçues en exécutant des opérations d’extraction, de traitement et de prédiction à l’aide des moyens de calcul de la plateforme, avant de stocker les différents informations qui seront communiquées sur les terminaux utilisateurs 25 via les différentes interfaces. La présentation des informations s’effectue ensuite sur les interfaces disponibles pour chaque entreprise utilisant la plateforme, à savoir les interfaces web, les applications mobiles APP, mais aussi par courrier électronique (email). Pour ce faire, l’API de la plateforme collaborative permet de faire le lien entre les interfaces utilisateur (programmes consommateur comme les applications mobiles et les extensions web) et les programmes fournisseur installés dans ladite plateforme. Les opérations précitées seront expliquées plus en détail lors de la description du procédé de prévention mis en œuvre par la plateforme collaborative. Toutefois, il convient d’identifier au préalable les principales données échangées entre la plateforme collaborative et les entreprises de la communauté. The collaborative platform 10 then makes it possible to use the raw data received by performing extraction, processing and prediction operations using the platform's calculation means, before storing the various information that will be communicated on the terminals. 25 users via the different interfaces. The information is then presented on the interfaces available to each company using the platform, namely web interfaces, mobile APP applications, but also by electronic mail (email). To do this, the API of the collaborative platform makes it possible to make the link between the user interfaces (consumer programs such as mobile applications and web extensions) and the supplier programs installed in said platform. The aforementioned operations will be explained in more detail when describing the prevention process implemented by the collaborative platform. However, it is necessary to identify beforehand the main data exchanged between the collaborative platform and the companies of the community.
La figure 4 représente schématiquement un utilisateur 20 (entreprise membre) dans sa relation d’échange de données avec la plateforme collaborative 10. L’entreprise 20 transmet principalement, de façon automatique via l’ERP ou manuelle, des historiques 210 de paiement des clients et des défauts de paiement 220, retards de paiement ou impayés, constatés. En contrepartie, la plateforme collaborative 10 est apte à retourner à l’entreprise 20 des informations de prévention 110 relatives aux clients et prospects de ladite entreprise. Les informations de prévention 110 regroupent par exemple : des alertes de risque 111, des scores de risque de crédit 112 et des rapports d’informations 113. FIG. 4 schematically represents a user 20 (member company) in its data exchange relationship with the collaborative platform 10. The company 20 mainly transmits, automatically via the ERP or manually, customer payment histories 210. and payment defaults 220, late payments or unpaid bills, noted. In return, the collaborative platform 10 is able to return to the company 20 prevention information 110 relating to the customers and prospects of said company. The prevention information 110 includes, for example: risk alerts 111, credit risk scores 112 and information reports 113.
Une alerte de risque 111 survient lorsqu’un risque analysé devient critique et informe par exemple d’un défaut de paiement imminent de la part d’un client, de l’approche de la date d’échéance d’une facture donnée, d’une situation générale problématique d’un client, d’une détérioration inquiétante du score d’un client, etc. En tout état de cause, l’alerte de risque 111 correspond à une situation d’urgence et requiert un traitement en priorité. A risk alert 111 occurs when an analyzed risk becomes critical and informs, for example, of an imminent payment default on the part of a customer, of the approach of the due date of a given invoice, of a general problematic situation of a customer, a worrying deterioration in a customer's score, etc. In any case, the risk alert 111 corresponds to an emergency situation and requires priority treatment.
Un score de risque de crédit 112 correspond tout simplement au score attribué par la plateforme collaborative à un client ou à un prospect donné. Dans un mode de réalisation, les scores sont calculés selon des méthodes connues telles que le système de notation décrit dans « Yoshino, Naoyuki & Taghizadeh-Hesary, Farhad. (2015). Analysis of Crédit Ratings for Small and Medium-Sized Enterprises: Evidence from Asia. Asian Development Review. 32. 18-37. 10.1162/ADEV_a_00050. » . A credit risk score 112 simply corresponds to the score assigned by the collaborative platform to a given customer or prospect. In one embodiment, the scores are calculated according to known methods such as the scoring system described in "Yoshino, Naoyuki & Taghizadeh-Hesary, Farhad. (2015). Analysis of Credit Ratings for Small and Medium-Sized Enterprises: Evidence from Asia. Asian Development Review. 32. 18-37. 10.1162 / ADEV_a_00050. ".
Ce système de notation permet de calculer pour chaque entreprise un score X allant de 0 à 10, correspondant à une note financière qualitative (système d’étoiles sur les interfaces graphiques par exemple) et à une note de crédit encadrant davantage les décisions à prendre. Le tableau ci-dessous donne un exemple d’une telle notation : This scoring system makes it possible to calculate for each company an X score ranging from 0 to 10, corresponding to a qualitative financial score (star system on graphical interfaces for example) and to a credit score further framing the decisions to be made. The table below gives an example of such a notation:
Un rapport d’information 113 peut, quant à lui, contenir différentes informations, classées selon leur pertinence dans la prise de décision ou simplement présentées de façon thématique, et permet de dresser un profil de risque pour chaque client ou prospect. An information report 113 can, for its part, contain different information, classified according to its relevance in the decision-making or simply presented in a thematic way, and makes it possible to draw up a risk profile for each client or prospect.
Il est important de noter que les données fournies par toutes les entreprises de la communauté sont centralisées dans la plateforme collaborative et servent indifféremment selon les modèles exécutés à établir les informations destinées à chacune desdites entreprises. Par exemple, un client donné peut se retrouver dans plusieurs historiques de paiement fournis par des entreprises différentes, ce qui permet à la plateforme collaborative de reconstituer un historique de paiement propre audit client, qui impactera les prédictions obtenues vis-à-vis de ce même client, et qui reste accessible pour les entreprises de la communauté afin de leur permettre de prendre des décisions transactionnelles impliquant ce client en toute connaissance de cause. It is important to note that the data provided by all companies in the community is centralized in the collaborative platform and is used indifferently according to the models carried out to establish the information intended for each of the aforesaid companies. For example, a given customer can be found in several payment histories provided by different companies, which allows the collaborative platform to reconstruct a payment history specific to the customer audit, which will impact the predictions obtained with respect to the same. client, and which remains accessible to businesses in the community in order to enable them to make informed transactional decisions involving this client.
La plateforme collaborative 10, outre les informations de prévention 110, est apte à fournir aux entreprises 20 membres de la communauté des services supplémentaires, en fonction des contrats souscrits, tels qu’un remboursement 120 d’impayés, ou recouvrement de créances, grâce à une mutualisation des risques entre membres de la communauté ; et un financement mutualisé des factures clients entre membres de la communauté basé sur un modèle pair-à-pair, qui découle de l’aspect collaboratif de la plateforme. The collaborative platform 10, in addition to the prevention information 110, is able to provide companies 20 members of the community with additional services, depending on the contracts subscribed, such as reimbursement 120 of unpaid debts, or debt collection, thanks to pooling of risks between members of the community; and pooled financing of customer invoices between community members based on a peer-to-peer model, which stems from the collaborative aspect of the platform.
De plus, les échanges les plus sensibles entre la plateforme collaborative 10 et les entreprises 20 de la communauté sont sécurisés sur la blockchain. Cela concerne en premier lieu, les données financières et comptables, les contrats signés électroniquement ainsi que les ordres de virement et autres opérations monétaires. La figure 5 représente les principales étapes d’un procédé 500, mis en œuvre par la plateforme collaborative 10, pour la prévision des risques liés aux défauts de paiement dans une entreprise 20, ladite prévision se déclinant sur deux volets représentant chacun une utilisation possible de ladite plateforme : le volet prédiction des défauts de paiement des clients 520 et le volet choix des prospects 530. In addition, the most sensitive exchanges between the collaborative platform 10 and the 20 companies in the community are secured on the blockchain. This concerns in the first place, financial and accounting data, contracts signed electronically as well as transfer orders and other monetary operations. FIG. 5 represents the main steps of a method 500, implemented by the collaborative platform 10, for forecasting the risks associated with payment defaults in a company 20, said forecast being broken down into two parts each representing a possible use of said platform: the prediction component of customer defaults 520 and the selection of prospects component 530.
Avant de pouvoir utiliser la plateforme collaborative 10, chaque entreprise 20 doit effectuer une souscription 510 pour créer son compte utilisateur lui donnant accès à des services plus ou moins personnalisés, en fonction des besoins de l’entreprise, de son chiffre d’affaires, de son volume de portefeuille clients, etc. Before being able to use the collaborative platform 10, each company 20 must make a 510 subscription to create its user account giving it access to more or less personalized services, depending on the needs of the company, its turnover, its customer portfolio volume, etc.
La souscription 510 est donc une étape initiale du procédé 500 de prévision des risques, et peut être réalisée en suivant des étapes ordinaires d’enregistrement et de souscription en ligne. Par exemple, la souscription d’une entreprise 20 à la plateforme collaborative 10 s’accompagne des étapes suivantes, dont certaines sont optionnelles de toute évidence : The subscription 510 is therefore an initial step of the risk forecasting method 500, and can be carried out by following ordinary steps of registration and online subscription. For example, the subscription of a company 20 to the collaborative platform 10 involves the following steps, some of which are obviously optional:
- Démonstration de la plateforme collaborative et des services proposés ;- Demonstration of the collaborative platform and the services offered;
- Présentation de l’offre commerciale ; - Presentation of the commercial offer;
- Création du profil de l’entreprise, par remplissage de champs du type : secteur d’activité (liste de choix), immatriculation (identité de l’entreprise), nom de l’entreprise, chiffre d’affaire, nombre de clients approximatif, adresse de messagerie électronique (email), numéro de téléphone, logo de l’entreprise, etc. ; - Creation of the company profile, by filling in fields such as: sector of activity (choice list), registration (company identity), company name, turnover, approximate number of customers , electronic mail address (email), phone number, company logo, etc. ;
- Chiffrage de l’offre commerciale (abonnements forfaitaires) basé sur le profil enregistré de l’entreprise ; - Costing of the commercial offer (flat rate subscriptions) based on the registered profile of the company;
- Proposition de contrat suivie d’un agrément sur l’offre ; - Contract proposal followed by approval of the offer;
- Signature électronique du contrat ; - Electronic signature of the contract;
- Paiement des frais d’engagement annuel ou autre ; - Payment of annual or other commitment fees;
- Edition du contrat signé sous forme électronique (format PDF par exemple) ;- Edition of the signed contract in electronic form (PDF format for example);
- Communication des identifiants utilisateur (identifiant et mot de passe) pour l’accès à la plateforme et à l’espace utilisateur via la page web ou l’application mobile ; - Communication of user identifiers (username and password) for access to the platform and the user area via the web page or mobile application;
- Mise en place d’un outil informatique d’accès aux bases de données de l’entreprise soit directement par l’ERP de l’entreprise, soit par le biais d’un logiciel de gestion des données client CDMS (Customer Data Management Software) ; - Implementation of an IT tool for accessing the company's databases either directly through the company's ERP or through customer data management software CDMS (Customer Data Management Software );
- Premier export de données financières et comptables (portefeuilles clients, facturation, etc.) de façon manuelle ou automatisée via l’ERP entreprise.- First export of financial and accounting data (customer portfolios, invoicing, etc.) manually or automatically via the company ERP.
Les deux dernières étapes permettent à la plateforme collaborative de collecter les premières données des entreprises membres. À cet effet, la plateforme est compatible avec différents ERP existants, par le biais de passerelles spécifiques, et est apte à collecter des informations telles que le portefeuille clients, l’historique de facturation, les devis, etc. The last two steps allow the collaborative platform to collect the first data from member companies. To this end, the platform is compatible with various existing ERPs, through specific gateways, and is able to collect information such as customer portfolio, billing history, quotes, etc.
La plateforme collaborative est également apte à importer des informations compilés dans des tableurs ordinaires tels que des fichier Excel (Microsoft Excel). Selon un mode de réalisation, l’établissement de la connexion entre la plateforme collaborative 10 et l’ERP 21 d’une entreprise 20 membre, voir figure 2, peut se faire juste après la finalisation de la souscription 510. Le souscripteur, à savoir une personne de l’entreprise, reçoit un email l’invitant à télécharger un programme qu’il doit installer sur son système informatique. Ce programme CDMS permettra ensuite à l’entreprise d’établir un lien entre la plateforme collaborative et son ERP en choisissant la passerelle correspondant à son type d’ERP (parmi les marques déposées CIEL, ORACLE, SAP, Microsoft, etc.). Ainsi, ce programme constitue un pont entre le système de comptabilité de l’entreprise membre et la plateforme collaborative, et permet un transfert automatisé, en temps réel, d’informations extraites de façon ciblée de sorte à alimenter la plateforme avec toute donnée pertinente à l’évaluation du risque de défaut de paiement. The collaborative platform is also able to import information compiled into ordinary spreadsheets such as Excel files (Microsoft Excel). According to one embodiment, the establishment of the connection between the collaborative platform 10 and the ERP 21 of a member company 20, see FIG. 2, can be done just after the finalization of the subscription 510. The subscriber, namely a person from the company receives an email inviting him to download a program that he must install on his computer system. This CDMS program will then allow the company to establish a link between the collaborative platform and its ERP by choosing the gateway corresponding to its type of ERP (among the trademarks CIEL, ORACLE, SAP, Microsoft, etc.). Thus, this program constitutes a bridge between the accounting system of the member company and the collaborative platform, and allows an automated transfer, in real time, of information extracted in a targeted manner so as to feed the platform with any relevant data to assessment of the risk of default.
Dans le cas où la mise en place d’un pont entre l’ERP de l’entreprise et la plateforme collaborative est réticente voire impossible, ladite entreprise a la possibilité d’importer un fichier de type Excel dans la plateforme via l’interface web ou l’application mobile de sorte à partager les informations y contenues avec ladite plateforme. Les informations extraites sont ensuite immédiatement affichées et mises à jour sur les différents supports d’accès à la plateforme (interface web et applications mobiles). In the event that the establishment of a bridge between the company's ERP and the collaborative platform is reluctant or even impossible, said company has the possibility of importing an Excel-type file into the platform via the web interface or the mobile application so as to share the information contained therein with said platform. The information extracted is then immediately displayed and updated on the various platform access media (web interface and mobile applications).
Dans la suite, on suppose que l’entreprise 20, qui compte utiliser la plateforme collaborative 10 selon le procédé 500 de la figure 5, a achevé l’étape de souscription 510 et s’est enregistrée avec succès sur ladite plateforme. In the following, it is assumed that the company 20, which intends to use the collaborative platform 10 according to the method 500 of FIG. 5, has completed the subscription step 510 and has successfully registered on said platform.
Le procédé 500 de prévision des risques, suivant le volet prédiction des défauts de paiement 520, comprend principalement : The risk forecasting method 500, according to the payment defaults prediction component 520, mainly comprises:
- une étape 521 d’export de données de l’entreprise 20 vers la plateforme collaborative 10, de façon ponctuelle ou périodique ; - a step 521 of exporting data from the company 20 to the collaborative platform 10, on an ad hoc or periodic basis;
- une étape 522 de collecte de données parmi les données exportées ; a step 522 of collecting data from among the exported data;
- une étape 523 d’analyse et de prédiction par l’exécution d’algorithmes de traitement de données et d’intelligence artificielle ; - a step 523 of analysis and prediction by executing data processing and artificial intelligence algorithms;
- une étape 524 d’information et de recommandation basée sur les résultats de l’étape précédente ; et - a step 524 of information and recommendation based on the results of the previous step; and
- une étape finale 540 de décision quant à l’action à accomplir par l’entreprise 20. L’étape 521 d’export de données permet d’alimenter la plateforme collaborative 10 par des données financières et comptables des entreprises 20 de la communauté, de sorte que ladite plateforme soir en mesure d’identifier et de prédire d’éventuels défauts de paiements. L’export de données s’effectue au travers de la liaison sécurisée établie entre l’outil comptable de l’entreprise, tel que l’ERP, et la base de données de la plateforme selon les modalités présentées ci-avant (export automatique ou manuel, CDMS, etc.). - a final step 540 for deciding on the action to be performed by the company 20. The data export step 521 makes it possible to feed the collaborative platform 10 with financial and accounting data from the companies 20 in the community, so that said platform is able to identify and predict possible payment defaults. . Data export is carried out through the secure link established between the company's accounting tool, such as the ERP, and the platform's database as described above (automatic export or manual, CDMS, etc.).
Parmi les données exportées sur la plateforme collaborative, on peut citer : le portefeuille clients, exporté au début, avec la possibilité d’ajouter de nouveaux clients ultérieurement ; les factures, de façon périodique, de préférence de façon quotidienne ; l’historique des paiements clients, également de façon périodique, de préférence de façon hebdomadaire pour une meilleure prévision des défauts de paiement. Among the data exported to the collaborative platform, we can mention: the customer portfolio, exported at the start, with the possibility of adding new customers later; invoices, periodically, preferably daily; customer payment history, also periodically, preferably weekly for better forecasting of defaults.
Lorsqu’une entreprise membre oublie de charger des données de facturation ou d’historique de paiement, des rappels sont faits par la plateforme au moyen de notifications sur l’interface web ou sur les applications mobiles, ou par simples emails, invitant ladite entreprise à mettre à jour ses données pour le bon fonctionnement de la plateforme et des résultats fiables et à jour. When a member company forgets to load billing or payment history data, reminders are made by the platform by means of notifications on the web interface or on mobile applications, or by simple emails, inviting said company to update its data for the proper functioning of the platform and reliable and up-to-date results.
Accessoirement, les données exportées peuvent être horodatées 610 afin d’établir des preuves de dates sur lesdites données et éviter tout conflit avec une entreprise qui, par exemple, affirmerait ne pas avoir été alertée d’un impayé sur une facture exportée, lorsque celle-ci aurait été véritablement exportée après échéance. L’étape 522 de collecte de données par la plateforme collaborative 10 correspond à des opérations d’extraction, de normalisation et de classement des données utiles dans la base de données de ladite plateforme pour permettre l’exécution des algorithmes d’analyse et de prédiction. Les données collectées sont ensuite injectées dans algorithmes de la plateforme tels que des modèles d’apprentissage automatique mis en œuvre lors d’une étape 620 permanente d’apprentissage automatique. Incidentally, the exported data can be time-stamped 610 in order to establish proof of dates on said data and to avoid any conflict with a company which, for example, would claim not to have been alerted to an unpaid invoice on an exported invoice, when the latter this would have been truly exported after the deadline. The step 522 of data collection by the collaborative platform 10 corresponds to operations of extraction, standardization and classification of the useful data in the database of said platform to allow the execution of the analysis and prediction algorithms. . The collected data is then fed into platform algorithms such as machine learning models implemented in a permanent machine learning step 620.
L’étape 523 d’analyse et de prédiction permet à la fois d’analyser le statut de chaque facture importée en vue de détecter un défaut de paiement selon des règles calendaires bien établies, et de prédire l’occurrence d’un tel défaut par apprentissage automatique, en tenant compte du profil de risque des clients, d’attributs temporels, de données contextuelles (santé financière des clients, situation économique du pays du client, évènements, etc.). La prédiction des défauts de paiement repose ainsi sur la construction d’un modèle prédictif à partir de données contextuelles. The analysis and prediction step 523 makes it possible both to analyze the status of each imported invoice with a view to detecting a payment default according to well-established calendar rules, and to predict the occurrence of such a default by machine learning, taking into account the risk profile of clients, temporal attributes, contextual data (financial health of customers, economic situation in the customer's country, events, etc.). The prediction of payment defaults is thus based on the construction of a predictive model from contextual data.
Différents types de modèles d’apprentissage, supervisé ou non supervisé, peuvent être utilisés, tels qu'un modèle d'arbre de décision, un modèle de regroupement, un modèle de réseau bayésien, un modèle graphique probabiliste, un modèle basé sur des règles et/ou un modèle de machine à vecteurs de support. Les modèles d’apprentissage automatique précités peuvent être mis en œuvre seuls ou combinés selon une architecture en réseau de neurones artificiels, auquel cas des méthodes d’apprentissage profond ( Deep Learning) sont utilisées. Different types of learning models, supervised or unsupervised, can be used, such as decision tree model, clustering model, Bayesian network model, probabilistic graphical model, rule-based model and / or a support vector machine model. The aforementioned machine learning models can be implemented alone or in combination in an artificial neural network architecture, in which case Deep Learning methods are used.
En référence à la figure 8 et en prenant comme exemple un modèle 131 d'arbre de décision, le réseau de neurones comprend un certain nombre de nœuds, reliés par diverses branches et répartis en couches : entrée, couches cachées et sortie. Chaque nœud représente une demande concernant un ou plusieurs attributs associés à une facture 22, les attributs d’entrée étant par exemple la date d’émission de la facture, le nom du client, le montant hors taxe, etc. Le résultat d'une demande représentée par un nœud courant détermine la branche, émanant du nœud courant, à suivre pour atteindre un autre nœud du réseau de neurones. Le dernier nœud d'une branche particulière estime un défaut de paiement pour la facture tel qu’un retard de paiement par exemple. Referring to FIG. 8 and taking as an example a decision tree model 131, the neural network comprises a certain number of nodes, connected by various branches and divided into layers: input, hidden layers and output. Each node represents a request for one or more attributes associated with an invoice 22, the input attributes being for example the date of issue of the invoice, the name of the customer, the amount excluding tax, etc. The result of a request represented by a current node determines the branch, emanating from the current node, to follow in order to reach another node of the neural network. The last node of a particular branch estimates a default on the invoice such as late payment for example.
L’étape 523 d’analyse et de prédiction permet également de prédire la trésorerie de chaque entreprise 20 de la communauté en se basant sur les données importées dans la plateforme collaborative. Il s’agit d’une prédiction duale de la prédiction des défauts de paiement. Autrement dit, la prédiction des défauts de paiement pour une entreprise conditionne, à quelques paramètres près, la prédiction de la trésorerie de ladite entreprise. The analysis and prediction step 523 also makes it possible to predict the cash flow of each company 20 in the community based on the data imported into the collaborative platform. This is a dual prediction of the prediction of defaults. In other words, the prediction of payment defaults for a company conditions, with a few parameters, the prediction of the cash flow of said company.
La prédiction de la trésorerie grâce aux données big data et aux modèles d’apprentissage automatique procure un avantage considérable sur les solutions existantes, qui se contentent d’un calcul de moyenne pour déterminer des tendances statistiques. Predicting cash flow using big data and machine learning models provides a significant advantage over existing solutions, which simply averaging to determine statistical trends.
L’étape 524 d’information et de recommandation permet à la plateforme collaborative 10 de fournir les informations de prévention (alerte de risque, et rapport d’information), nécessaires à une prise de décision réfléchie de la part de l’entreprise 20, et de suggérer l’action la plus appropriée compte tenu du résultat de l’analyse et de la prédiction réalisées à l’étape précédente. The information and recommendation step 524 allows the collaborative platform 10 to provide prevention information (risk alert, and information report), necessary for a considered decision-making on the part of the company 20, and to suggest the most appropriate action taking into account the result of the analysis and the prediction carried out in the previous step.
Les informations obtenues sont affichées de façon interactive sur les différentes interfaces utilisateur (web et application mobile) pour permettre une lecture simplifiée et un accès immédiat à l’information. The information obtained is displayed interactively on the various user interfaces (web and mobile application) to allow easy reading and immediate access to the information.
Les figures 6, 7A et 7B illustrent des exemples d’interfaces graphiques 251 de présentation d’information sur un smartphone 25 via une application mobile. L’interface peut ainsi comporter différentes rubriques 252 montrant les informations sous forme de courbes et de graphiques 253 (secteurs, histogrammes et autres), ainsi que des listes de factures, devis, clients et autres, permettant un accès à leurs éléments 254. Figures 6, 7A and 7B illustrate examples of graphical interfaces 251 for presenting information on a smartphone 25 via a mobile application. The interface can thus include different sections 252 showing information in the form of curves and graphs 253 (sectors, histograms and others), as well as lists of invoices, quotes, customers and others, allowing access to their elements 254.
Toujours en référence à la figure 5, le procédé 500 de prévision des risques, suivant le volet choix des prospects 530, comprend principalement : Still with reference to FIG. 5, the risk forecasting method 500, according to the selection of prospects section 530, mainly comprises:
- une étape 531 de recherche de prospects par l’entreprise 20 ; - a step 531 of prospecting by the company 20;
- une étape 532 d’affichage du score des prospects trouvés ; - a step 532 of displaying the score of the prospects found;
- une étape conditionnelle 533 de choix de prospects ; a conditional step 533 of choosing prospects;
- une étape 534 d’ajout de prospects à une liste de prospects ; et - a step 534 of adding prospects to a list of prospects; and
- l’étape finale 540 de décision. - the final decision step 540.
L’étape 531 de recherche des prospects permet à l’entreprise 20 de rechercher des prospects par l’intermédiaire de la plateforme collaborative 10 afin d’accéder aux scores qui leur sont attribués par ladite plateforme. Cette recherche peut être simple ou avancée, avec la sélection de certains critères tels que le secteur industriel, le chiffre d’affaire, l’implantation géographique, etc. La plateforme est également apte à sauvegarder les préférences des entreprises ayant déjà effectué des recherches de prospects. The prospect search step 531 allows the company 20 to search for prospects through the collaborative platform 10 in order to access the scores assigned to them by said platform. This search can be simple or advanced, with the selection of certain criteria such as industrial sector, turnover, geographical location, etc. The platform is also able to save the preferences of companies that have already carried out prospect research.
L’étape 532 d’affichage du score permet de lister les différents prospects trouvés avec les scores qui leur sont attribués par la plateforme collaborative selon un système de notation tel que celui présenté ci-avant. La présentation du résultat de la recherche avec le score peut s’apparenter graphiquement à la présentation donnée en figure 7B pour le portefeuille clients d’une entreprise. The score display step 532 makes it possible to list the various prospects found with the scores assigned to them by the collaborative platform according to a scoring system such as that presented above. The presentation of the search result with the score can be graphically similar to the presentation given in Figure 7B for a company's customer portfolio.
L’étape 533 de choix consiste à sélectionner les prospects retenus par l’entreprise 20. Toutefois, il convient de noter que ce choix peut ne pas être motivé par le score affiché. Les scores sont de simples indicateurs et la décision finales revient de plein pouvoir à l’entreprise 20 malgré l’utilisation de la plateforme collaborative, qui est un outil d’aide à la décision uniquement. The choice step 533 consists in selecting the prospects retained by the company 20. However, it should be noted that this choice may not be motivated by the score. attach. The scores are simple indicators and the final decision rests in full power with the company 20 despite the use of the collaborative platform, which is a decision support tool only.
L’étape 534 d’ajout des prospects choisis par l’entreprise 20 permet in fine d’ajouter lesdits prospects à une liste consultable via le menu de l’interface web ou de l’application mobile. The step 534 of adding the prospects chosen by the company 20 ultimately makes it possible to add said prospects to a list that can be consulted via the menu of the web interface or of the mobile application.
La plateforme collaborative 10 permet également, selon un autre aspect de l’invention, de mutualiser les risques encourus par les entreprises membres de la communauté. Autrement dit, la plateforme collaborative permet de rembourser tout ou partie des impayés subis par les membres de la communauté ayant souscrits cette option d’assurance sur la plateforme. The collaborative platform 10 also makes it possible, according to another aspect of the invention, to pool the risks incurred by the companies that are members of the community. In other words, the collaborative platform makes it possible to reimburse all or part of the unpaid debts suffered by members of the community who have taken out this insurance option on the platform.
La figure 9 représente le déroulement d’un processus de compensation de la balance d’un membre de la communauté à la suite d’un impayé, ledit processus, pris indépendamment du reste du procédé de prévention supra, comprend : Figure 9 shows the course of a process for compensating the balance of a member of the community following an unpaid debt, said process, taken independently of the rest of the above prevention process, comprises:
- une étape 510 de souscription, pouvant correspondre à une première souscription à la plateforme collaborative avec l’option « assurance » ou à une souscription complémentaire au service « assurance » ; - a subscription step 510, which may correspond to a first subscription to the collaborative platform with the "insurance" option or to an additional subscription to the "insurance" service;
- une étape 523 d’analyse, permettant de détecter un impayé par des considérations calendaires ordinaires de dépassement des délais admis de paiement ; - a step 523 of analysis, making it possible to detect an unpaid amount by ordinary calendar considerations of exceeding the accepted payment deadlines;
- une étape 524 d’information, notifiant l’utilisateur de l’impayé constaté ;- an information step 524, notifying the user of the unpaid amount noted;
- une étape 540 de décision de la part de l’utilisateur, attestant de la validité de l’impayé ; - a decision step 540 on the part of the user, attesting to the validity of the unpaid;
- une étape 551 de génération d’une compensation de la balance enregistrée sur un portefeuille virtuel de l’utilisateur créé lors de la souscription ; - a step 551 of generating a compensation for the balance recorded on a virtual wallet of the user created during the subscription;
- une étape 552 de validation de la compensation par un administrateur de la plateforme collaborative ; a step 552 of validation of the compensation by an administrator of the collaborative platform;
- une étape 553 de transfert de la compensation de la balance sur le portefeuille de l’utilisateur ; et - a step 553 of transferring the compensation from the balance to the user's wallet; and
- une étape 554 d’actualisation dudit portefeuille après virement des fonds.- a step 554 of updating said portfolio after transfer of funds.
La plateforme collaborative ainsi décrite permet à une communauté d’entreprises de partager leurs expériences de paiement client afin que chacune d’entre elles puisse se renseigner sur l’historique des paiements d’un prospect donné en temps réel lorsque celui-ci leur demande un devis par exemple, et prenne la décision adéquate. De plus, la plateforme collaborative permet, grâce à des données collectées de différentes sources, de prédire des défauts de paiement par apprentissage automatique, facilitant ainsi la gestion des risques de part des entreprises les plus vulnérables telles que les PME. The collaborative platform thus described allows a community of companies to share their customer payment experiences so that each of them can learn about the payment history of a given prospect in time. real when the latter asks them for a quote, for example, and makes the appropriate decision. In addition, the collaborative platform allows, thanks to data collected from different sources, to predict payment defaults by machine learning, thus facilitating risk management for the most vulnerable companies such as SMEs.
Il ressort clairement de la présente description que la plateforme collaborative et les procédés associés peuvent être réalisés selon des variantes, avec par exemple l’ajout et/ou la modification de certaines caractéristiques techniques, sans pour autant sortir du cadre de l’invention. Par exemple, la plateforme peut proposer des fonctionnalités telles que l’édition de factures électroniques entre les membres de la communauté, l’envoi périodique d’une liste ciblée de prospects pouvant correspondre aux attentes d’un membre en fonction de données collectées dans des sources auxiliaires telles que les réseaux sociaux. It is clear from the present description that the collaborative platform and the associated processes can be implemented according to variants, for example with the addition and / or modification of certain technical characteristics, without departing from the scope of the invention. For example, the platform can offer functionalities such as the edition of electronic invoices between the members of the community, the periodic sending of a targeted list of prospects which can correspond to the expectations of a member according to data collected in auxiliary sources such as social networks.

Claims

R E V E N D I C A T I O N S
1. Plateforme électronique collaborative (10) pour la prédiction d’évènements à risque tels que des défauts de paiement entre une entreprise (20) et des clients de ladite entreprise, comprenant un système de stockage de données (11), au moins un serveur informatique (12) et des moyens de traitement et de calcul (13) implémentant au moins un modèle d'apprentissage automatique, la plateforme étant apte à importer des données telles que des données financières de l’entreprise par le biais d’une liaison sécurisée entre le système de stockage de données et un outil de gestion interne (21) de ladite l’entreprise, ledit modèle estimant l’occurrence d’évènements à risque en se basant sur les données importées, ladite plateforme étant caractérisée en ce qu’elle est reliée à une pluralité d’entreprises (20) formant une communauté de partage d’informations en temps réel sur la plateforme, en ce qu’elle est apte à transmettre toute information partagée par une première entreprise à au moins une deuxième entreprise de la communauté pour laquelle ladite information présente un intérêt, et en ce qu’elle comprend une interface de programmation applicative API permettant d’exécuter un programme utilisateur de gestion des risques sur des terminaux (25) des entreprises de la communauté. 1. Collaborative electronic platform (10) for the prediction of risky events such as payment defaults between a company (20) and customers of said company, comprising a data storage system (11), at least one server IT (12) and processing and calculation means (13) implementing at least one machine learning model, the platform being able to import data such as financial data of the company by means of a secure link between the data storage system and an internal management tool (21) of said company, said model estimating the occurrence of risky events based on the imported data, said platform being characterized in that it is linked to a plurality of companies (20) forming a real-time information sharing community on the platform, in that it is able to transmit any information shared by a first company to at least one of ninth company in the community for which said information is of interest, and in that it comprises an application programming interface API for executing a risk management user program on terminals (25) of companies in the community.
2. Plateforme collaborative selon la revendication 1, caractérisée en ce qu’elle est reliée à des sources de données externes (30) et en ce que les moyens de traitement et de calcul (13) comportent des algorithmes de notation permettant de déterminer un score pour toute entreprise à partir d’informations sur ladite entreprise contenues dans les données externes importées par ladite plateforme. 2. Collaborative platform according to claim 1, characterized in that it is connected to external data sources (30) and in that the processing and calculation means (13) comprise scoring algorithms making it possible to determine a score. for any company from information on said company contained in external data imported by said platform.
3. Piateforme collaborative selon l’une des revendications 1 ou 2, caractérisée en ce qu’elle présente une architecture en nuage avec une couche de virtualisation comprenant au moins le système de stockage de données (11 ) et tout serveur (12), et en ce qu’elle est accessible via un réseau de type internet. 3. Collaborative platform according to one of claims 1 or 2, characterized in that it has a cloud architecture with a virtualization layer comprising at least the data storage system (11) and any server (12), and in that it is accessible via an Internet type network.
4. Plateforme collaborative selon l’une quelconque des revendications précédentes, dans laquelle le système de stockage de données (11) comprend une base de données et les moyens de traitement et de calcul (13) comprennent au moins un processeur, et dans laquelle ladite base de données est distribuée sur une chaîne de blocs. 4. Collaborative platform according to any one of the preceding claims, in which the data storage system (11) comprises a database and the processing and calculation means (13) comprise at least one processor, and in which said database is distributed over a blockchain.
5. Plateforme collaborative selon l’une quelconque des revendications précédentes, dans laquelle les informations partagées par les entreprises (20) membres de la communauté comprennent des historiques de paiement des clients de chaque entreprise, et dans laquelle les données financières importées comprennent des portefeuilles clients et des factures. 5. Collaborative platform according to any one of the preceding claims, in which the information shared by the companies (20) members of the community comprises payment histories of the customers of each company, and in which the imported financial data comprises customer portfolios. and invoices.
6. Plateforme collaborative selon l’une quelconque des revendications précédentes, dans laquelle au moins un modèle d'apprentissage automatique (131) construit une prédiction de défaut de paiement sur une facture (22) à partir d’attributs relatifs à ladite facture, de données financières importées sur la plateforme et de données contextuelles (31). 6. Collaborative platform according to any one of the preceding claims, in which at least one machine learning model (131) constructs a prediction of default on an invoice (22) from attributes relating to said invoice, of financial data imported to the platform and contextual data (31).
7. Procédé (500) de prévision des risques liés à des défauts de paiement entre une entreprise (20) et des clients de ladite entreprise, mis en œuvre par une plateforme collaborative (10) selon l’une des revendications 1 à 6, caractérisé en ce qu’il comprend : 7. A method (500) for forecasting the risks associated with payment defaults between a company (20) and customers of said company, implemented by a collaborative platform (10) according to one of claims 1 to 6, characterized in that it includes:
- une étape initiale (510) de souscription de l'entreprise à la plateforme ; - an initial step (510) of the company's subscription to the platform;
- une étape (521 ) d’export de données d’un outil de gestion interne (21 ) de l’entreprise vers le système de stockage de données (11 ) de la plateforme ; - a step (521) of exporting data from an internal management tool (21) of the company to the data storage system (11) of the platform;
- une étape (523) d’analyse et de prédiction mettant en œuvre au moins un modèle d’apprentissage automatique ; - une étape (524) de présentation, sur un terminal de l’entreprise, d’informations basées sur des résultats de l’étape précédente. - a step (523) of analysis and prediction implementing at least one machine learning model; - a step (524) of presentation, on a terminal of the company, of information based on the results of the previous step.
8. Procédé selon la revendication 7, dans lequel l’étape (523) d’analyse et de prédiction utilise des données fournies par plusieurs entreprises (20) de la communauté ainsi que des données externes (30) provenant de sources telles que des fournisseurs de données financières, et permet également de détecter des défauts de paiement en tenant compte des délais d’échéance des factures importées sur la plateforme. 8. The method of claim 7, wherein the step (523) of analysis and prediction uses data provided by several businesses (20) in the community as well as external data (30) from sources such as suppliers. of financial data, and also makes it possible to detect payment defaults by taking into account the due dates of invoices imported on the platform.
9. Procédé selon l’une des revendications 7 ou 8, dans lequel l’étape (524) de présentation d’informations produit des informations de prévention (110) comprenant au moins une information parmi une alerte de risque (111), un score de risque de crédit (112) et un rapport d’information (113) correspondant au profil de risque d’un client de l’entreprise (20). 9. Method according to one of claims 7 or 8, wherein the step (524) of presenting information produces prevention information (110) comprising at least one item of information from among a risk alert (111), a score. credit risk (112) and an information report (113) corresponding to the risk profile of a customer of the company (20).
10. Procédé selon l’une quelconque des revendications 7 à 9, comprenant en outre des opérations de remboursement d’impayés en faveur d’entreprises (20) de la communauté, suivant un système de mutualisation des risques centralisé dans la plateforme collaborative (10) et sécurisé par une chaîne de blocs. 10. Method according to any one of claims 7 to 9, further comprising repayment operations in favor of companies (20) of the community, according to a risk pooling system centralized in the collaborative platform (10). ) and secured by a blockchain.
11. Procédé selon l’une quelconque des revendications 7 à 10, comprenant en outre des opérations de financement mutualisé de factures de clients, entre des entreprises (20) membres de la communauté, selon un modèle de financement pair-à-pair géré par la plateforme collaborative (10). 11. Method according to any one of claims 7 to 10, further comprising operations of pooled financing of customer invoices, between companies (20) members of the community, according to a peer-to-peer financing model managed by the collaborative platform (10).
12. Procédé selon l’une quelconque des revendications 7 à 11, dans lequel l’étape (523) d’analyse et de prédiction comprend une étape de prédiction de la trésorerie d’une entreprise (20) de la communauté, basée sur les données importées dans la plateforme collaborative (10). 12. A method according to any one of claims 7 to 11, wherein the step (523) of analysis and prediction comprises a step of predicting the cash flow of a company (20) of the community, based on the results. data imported into the collaborative platform (10).
EP21722522.6A 2020-03-31 2021-03-31 Collaborative electronic platform for predicting non-payments for companies and associated method Withdrawn EP4128122A1 (en)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
FR2003218 2020-03-31
PCT/FR2021/050564 WO2021198615A1 (en) 2020-03-31 2021-03-31 Collaborative electronic platform for predicting non-payments for companies and associated method

Publications (1)

Publication Number Publication Date
EP4128122A1 true EP4128122A1 (en) 2023-02-08

Family

ID=72560661

Family Applications (1)

Application Number Title Priority Date Filing Date
EP21722522.6A Withdrawn EP4128122A1 (en) 2020-03-31 2021-03-31 Collaborative electronic platform for predicting non-payments for companies and associated method

Country Status (3)

Country Link
US (1) US20230128246A1 (en)
EP (1) EP4128122A1 (en)
WO (1) WO2021198615A1 (en)

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10872383B2 (en) 2017-02-14 2020-12-22 Oracle International Corporation Using a model to estimate a payment delinquency for an invoice
US20190287182A1 (en) 2018-03-14 2019-09-19 American Express Travel Related Services Company, Inc. Transaction Compliance Scoring System

Also Published As

Publication number Publication date
WO2021198615A1 (en) 2021-10-07
US20230128246A1 (en) 2023-04-27

Similar Documents

Publication Publication Date Title
De Villiers et al. A (new) role for business–Promoting the United Nations’ Sustainable Development Goals through the internet-of-things and blockchain technology
US20160086190A1 (en) Systems and methods for comprehensive consumer relationship management
EP1811448A1 (en) Method and system for deploying a business application
US20120254053A1 (en) On Demand Information Network
US20220083954A1 (en) Methods and systems for real-time inventory reallocation from supplier to retailer
US20210350488A1 (en) Methods and systems for notifying user of change to data sharing settings
US20210150604A1 (en) Systems and methods for customization of reviews
US20220148014A1 (en) Methods and systems for generating notifications from a computing system
US20220076308A1 (en) Systems and methods for selectively authorizing transactions in online commerce based on dynamically-determined sales regions
US20130325707A1 (en) Automated bill payment system
EP4149046A1 (en) Systems and methods for blockchain network congestion-adaptive digital asset event handling
JP6301326B2 (en) Service asset management system and method
CN110599082A (en) Method for providing a negotiable service by interfacing an initial supplier and a buyer via an intermediate negotiable provider
US20220020055A1 (en) Systems and methods for managing and controlling electronic messaging campaigns
US20210241315A1 (en) Systems and methods for dynamic messaging campaign
US20210150593A1 (en) Systems and methods for customization of reviews
CN116091242A (en) Recommended product combination generation method and device, electronic equipment and storage medium
EP3945484A1 (en) Systems and methods for obtaining information from a digital message
US20210279774A1 (en) Systems and methods for dynamic campaign engine
EP4128122A1 (en) Collaborative electronic platform for predicting non-payments for companies and associated method
US11270355B2 (en) Systems and methods for dynamic messaging campaign
US20200204514A1 (en) Prioritized messaging system
US11615424B2 (en) Systems and methods for dynamically conducting messaging campaigns responsive to customer events
US20230056015A1 (en) Systems and methods for modifying online stores through scheduling
US20230053818A1 (en) Systems and methods for modifying online stores

Legal Events

Date Code Title Description
STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: UNKNOWN

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE INTERNATIONAL PUBLICATION HAS BEEN MADE

PUAI Public reference made under article 153(3) epc to a published international application that has entered the european phase

Free format text: ORIGINAL CODE: 0009012

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: REQUEST FOR EXAMINATION WAS MADE

17P Request for examination filed

Effective date: 20221028

AK Designated contracting states

Kind code of ref document: A1

Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR

DAX Request for extension of the european patent (deleted)
RAV Requested validation state of the european patent: fee paid

Extension state: TN

Effective date: 20221028

Extension state: MA

Effective date: 20221028

STAA Information on the status of an ep patent application or granted ep patent

Free format text: STATUS: THE APPLICATION IS DEEMED TO BE WITHDRAWN

18D Application deemed to be withdrawn

Effective date: 20230523