CN113256404A - Data processing method and device - Google Patents
Data processing method and device Download PDFInfo
- Publication number
- CN113256404A CN113256404A CN202110666848.8A CN202110666848A CN113256404A CN 113256404 A CN113256404 A CN 113256404A CN 202110666848 A CN202110666848 A CN 202110666848A CN 113256404 A CN113256404 A CN 113256404A
- Authority
- CN
- China
- Prior art keywords
- user
- auditing
- model
- resource
- audit
- 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.)
- Pending
Links
Images
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
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/10—Office automation; Time management
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Educational Administration (AREA)
- Accounting & Taxation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the specification provides a data processing method and a data processing device, wherein the data processing method comprises the steps of receiving a target resource acquisition request of a first user, and determining an asset index set of the first user based on the target resource acquisition request; determining an auditing model set comprising at least one target auditing model based on the asset index set of the first user and attribute information of the auditing models; inputting the asset index set of the first user into the auditing model set to obtain the auditing result of the first user output by each target auditing model in the auditing model set; and determining the target resource of the first user based on the auditing result of the first user.
Description
Technical Field
The embodiment of the specification relates to the technical field of computers, in particular to a data processing method. One or more embodiments of the present specification also relate to a data processing apparatus, a computing device, and a computer-readable storage medium.
Background
In the prior art, there is a data processing method: under the condition that a first user requests a third-party resource processing server to acquire resources, the third-party resource processing server firstly acquires historical acquisition of the first user and behavior data of resources used from a third-party database, processes the behavior data to form a resource acquisition index set of the first user, and initiates an auditing instruction to a second user, and the second user needs to audit the resources which are acquired by the first user from the third-party resource processing server based on the resource acquisition index set of the first user; the third-party resource processing server can send the requested resource to the first user after receiving the instruction of passing the audit sent by the second user.
In this process, for the third-party resource processing server, each time the first user sends a resource acquisition request to the third-party resource processing server, the third-party resource processing server needs to acquire historical acquisition of the first user and behavior data of resources used to form a resource acquisition index set, and needs to send an audit instruction to the second user, and can process the next resource acquisition request after waiting for receiving an audit pass instruction of the second user for the first user sending the resource acquisition request. Then, when there are a large number of first users in the network, a large number of resource acquisition requests may occur, and the third-party resource processing server may, according to the data processing method, have extremely low data processing efficiency, which may cause accumulation of relatively serious resource acquisition requests, and user experience is very poor.
For example, in the existing network credit process, when a lending user obtains a credit limit from a bank, the bank first needs to collect data of the lending user from each channel, including capital stream data, asset liability data, profit and loss data and other behavior data, process the collected behavior data according to experience, find out formation indexes affecting the credit limit height in a branch industry, form an index set through a plurality of indexes, then initiate an audit instruction to a creditor, send the index set to the creditor for viewing as a credit assessment, and borrow the lending user when the creditor receives a condition that the creditor views a corresponding index set of the industry where the client is located to pass the credit assessment. Therefore, when the number of lending users is large, the amount of data to be processed by the bank is large, the processing efficiency is low, and the accumulation of resource acquisition requests is serious, so that the user experience is poor.
Disclosure of Invention
In view of this, the embodiments of the present disclosure provide the field of computer technologies, and in particular, relate to a data processing method. One or more embodiments of the present specification also relate to a data processing apparatus, a computing device, and a computer-readable storage medium to address technical deficiencies in the prior art.
According to a first aspect of embodiments herein, there is provided a data processing method including:
receiving a target resource acquisition request of a first user, and determining an asset index set of the first user based on the target resource acquisition request;
determining an auditing model set comprising at least one target auditing model based on the asset index set of the first user and attribute information of the auditing models;
inputting the asset index set of the first user into the auditing model set to obtain the auditing result of the first user output by each target auditing model in the auditing model set;
and determining the target resource of the first user based on the auditing result of the first user.
According to a second aspect of embodiments herein, there is provided a data processing apparatus comprising:
the system comprises a request receiving module, a resource acquisition module and a resource management module, wherein the request receiving module is configured to receive a target resource acquisition request of a first user and determine an asset index set of the first user based on the target resource acquisition request;
a set determination module configured to determine an audit model set including at least one target audit model based on the asset metric set of the first user and attribute information of the audit model;
a result output module configured to input the asset index set of the first user into the review model set, and obtain a review result of the first user output by each target review model in the review model set;
a resource determination module configured to determine a target resource of the first user based on the audit result of the first user.
According to a third aspect of embodiments herein, there is provided a computing device comprising:
a memory and a processor;
the memory is used for storing computer-executable instructions, and the processor is used for executing the computer-executable instructions, and the computer-executable instructions realize the steps of the data processing method when being executed by the processor.
According to a fourth aspect of embodiments herein, there is provided a computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the data processing method described above.
One embodiment of the present specification implements a data processing method and apparatus, where the data processing method includes receiving a target resource acquisition request of a first user, and determining an asset index set of the first user based on the target resource acquisition request; determining an auditing model set comprising at least one target auditing model based on the asset index set of the first user and attribute information of the auditing models; inputting the asset index set of the first user into the auditing model set to obtain the auditing result of the first user output by each target auditing model in the auditing model set; and determining the target resource of the first user based on the auditing result of the first user.
Specifically, after receiving a target resource acquisition request of a first user, the data processing method can efficiently and accurately audit the first user based on an audit model set matched with the first user, so as to allocate a reasonable target resource to the first user based on an audit result, and even if a large number of target resource acquisition requests are faced, the data processing method provided by the embodiment of the specification can rapidly process the target resource acquisition requests, thereby greatly improving the processing efficiency and improving the user experience.
Drawings
FIG. 1 is a schematic diagram illustrating a credit evaluation performed by a creditor based on a set of metrics of a client according to an embodiment of the present disclosure;
FIG. 2 is a flow chart of a data processing method provided by an embodiment of the present specification;
FIG. 3 is a flowchart illustrating a data processing method according to an embodiment of the present disclosure;
FIG. 4 is a diagram illustrating training of an audit model in a data processing method according to an embodiment of the present disclosure;
FIG. 5 is a schematic diagram illustrating optimization of a review model and a set of review models in a data processing method according to an embodiment of the present disclosure;
fig. 6 is a schematic structural diagram of a data processing apparatus according to an embodiment of the present specification;
fig. 7 is a block diagram of a computing device according to an embodiment of the present disclosure.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. This description may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, as those skilled in the art will be able to make and use the present disclosure without departing from the spirit and scope of the present disclosure.
The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can also be referred to as a second and, similarly, a second can also be referred to as a first without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
First, the noun terms to which one or more embodiments of the present specification relate are explained.
Credit wind control: refers to rating and classifying credit risks through procedures such as risk identification, metering, monitoring and control. The credit risk in the embodiment of the specification is mainly focused on the credit limit risk control of the client.
Index set: can reflect a set of client factual characteristics, such as the age, assets, liabilities, whether or not there is history and other indexes.
And (3) decision inference tree: a tree data structure comprising a root node, a leaf node and a non-leaf node; the child node deducts its parent node, layer by layer, up to the root node.
Fuzzy logic: part of the Boolean operation extension of the real concept is processed. Classical logic insights that everything (statements) can be expressed in terms of binary terms (0 or 1, black or white, yes or no), while fuzzy logic substitutes probability values for boolean truth. These statements represent questions and semantic statements that are close in nature to everyday people, because "true" and the results are in most cases inaccurate (inaccurate, unclear, fuzzy). A fuzzy logic framework is provided mathematically, and the fuzzy logic framework is composed of three steps of fuzzification, derivation and defuzzification.
The credit wind control can be divided into small-amount wind control, medium-amount wind control and large-amount wind control according to the height of the limit. The small-amount wind control is represented by small-amount loan products, the credit line is generated through mass data modeling, and the line range is thousands of thousands, even millions. The large amount wind control is represented by a traditional bank, and mortgage output credit lines of assets are transferred through lines, and the amount is measured in tens of millions. The limit interval of the medium and large wind control is in ten thousand level, and the credit is generally generated by combining expert experience and sample data.
Taking the credit check of a certain bank as an example, a credit check person (a person who audits credit qualification and credit limit of a client applying for loan) will make different credit check frames for clients in different industries. The core idea of the framework is as follows: 1) customer data is collected from various channels, including capital flow data, asset liability data, profit data, and other behavioral data. 2) The data is processed mainly by experience, the forming indexes influencing the credit line height are found out in different industries, and a plurality of indexes form an index set. 3) After the client submits the loan application request form, the system automatically presents the index set of the client for the credit examiner to view and make credit evaluation.
Referring to fig. 1, fig. 1 is a schematic diagram illustrating a credit evaluation implemented by a creditor based on a client index set according to an embodiment of the present disclosure.
The credit and audit personnel, the client and the index set of the client are included in fig. 1. Specifically, credit and audit personnel firstly collect data of clients from various channels, wherein the data comprises fund flow data, asset liability data, profit and loss data and other behavior data; processing the acquired data according to experience, finding out data influencing the credit line height according to the industry to which the client belongs to form indexes, and forming an industry index set by a plurality of indexes; after the client submits the loan application request form, the system automatically presents the index set of the client, and the credit auditor can check the corresponding index set of the industry where the client is located to evaluate the credit of the client and judge whether the client can be credited or not, the loan amount, and the like.
The method needs to continuously optimize the index set during use, strives to find better indexes, needs to acquire more data, continuously iterates an approval tool, and improves the efficiency of crediting and auditing personnel. But the credit and audit effectiveness is ceiling, the daily approval amount has an upper limit, and the marginal cost exists by people; in addition, the credible and auditor may influence the auditing result if the decision of the credible and auditor is in a self-contradictory place; in addition, the letter and audit framework of the letter and audit personnel cannot be inherited after leaving the office. Therefore, when a large number of clients' loan requests are encountered, the bank system performs loan processing based on the auditing results of the creditors, which is extremely slow, and causes a plurality of loan requests to accumulate on the server, thereby causing a great burden to the bank server.
In this specification, a data processing method is provided. One or more embodiments of the present specification also relate to a data processing apparatus and a computing device, which are described in detail in the following embodiments one by one.
Referring to fig. 2, fig. 2 is a flowchart illustrating a data processing method according to an embodiment of the present disclosure, which specifically includes the following steps.
Step 202: receiving a target resource acquisition request of a first user, and determining an asset index set of the first user based on the target resource acquisition request.
In particular, in a credit scenario, the data processing method may be applied to a credit system of a bank.
Then, in a credit scenario, the first user may be understood as a customer that debits the bank and the resource may be understood as the amount of the debit.
In practical applications, the target resource obtaining request of the first user is received, and the credit system of the bank receives the obtaining request of the loan fund of the loan client.
In specific implementation, the determining, based on the target resource acquisition request, the asset index set of the first user includes at least two ways, one of which may be that the credit system sends a resource application table to the client of the first user after receiving the target resource acquisition request of the first user, and the first user actively provides the resource application table based on the content in the resource application table, where the specific implementation manner is as follows:
the receiving a target resource acquisition request of a first user and determining an asset index set of the first user based on the target resource acquisition request includes:
receiving a target resource acquisition request of a first user, generating a resource application table for the first user based on the target resource acquisition request, and returning the resource application table to the first user;
and receiving user attribute information and resource information submitted by the first user based on the resource application form, and generating an asset index set of the first user based on the user attribute information and the resource information.
Specifically, after receiving a target resource acquisition request of a first user, the credit system generates a corresponding resource application table for the first user based on the target resource acquisition request. In practical application, the target resource acquisition request carries the personal identity information of the first user, namely the personal identity information filled by the user during credit system registration; and resource value information carrying the target resource of the first user, namely the loan amount. The credit system generates a corresponding resource application form for the first user based on the personal identity information and the loan amount of the first user. For example, if it is determined that the industry to which the first user belongs is a planting industry and the loan amount is 100 ten thousand through the personal identity information of the first user, a corresponding resource application form may be generated for the first user, and the resource application form may be directed to the industry of the first user, so that the first user fills some specific industry information, such as what is planted, a planting area, a specific location of a planting area, and the like.
Different resource application forms are generated for each first user in the personalized mode, so that the efficiency of a subsequent credit system for generating the asset index set of the first user based on the user attribute information and the resource information submitted by the first user based on the resource application forms is improved. The credit system does not need to perform industry judgment on the resource application form, and can reduce identification of useless information and the like.
After the resource application table is returned to the corresponding first user, the user attribute information and the resource information submitted by the first user based on the resource application table are received, and the asset index set of the first user is generated based on the user attribute information and the resource information. The user attribute information includes but is not limited to occupation, certificate information, working age, insurance information, family member condition and the like of the user; resource information includes, but is not limited to, user's capital expenditure, assets, liability conditions, and fixed asset profiles, among others.
In particular implementation, after receiving user attribute information and resource information submitted by the first user based on the resource application form, the credit system may aggregate the information submitted by the user to generate an asset index set of the first user.
In this embodiment, after the credit system obtains the asset index set of the first user, the credit system may subsequently perform more accurate and faster review on the first user based on the asset index set in combination with the review model set.
In another case, after receiving a target resource obtaining request of a first user, the credit system actively obtains user attribute information of the first user and obtains resource information of the user from a third-party resource platform authorized by the user, and the specific implementation manner is as follows:
the receiving a target resource acquisition request of a first user and determining an asset index set of the first user based on the target resource acquisition request includes:
receiving a target resource acquisition request of a first user, acquiring user attribute information of the first user based on the target resource acquisition request, and acquiring resource information of the first user from a third-party resource platform corresponding to the resource information under the condition of receiving an authorization instruction of the first user for the resource information;
generating an asset metric set for the first user based on the user attribute information and the resource information.
Specifically, after receiving the target resource acquisition request of the first user, the credit system may acquire user attribute information registered by the first user in advance based on login information of the first user in the credit system, and the user attribute information may be displayed to the user without being provided by the user again, and the user may perform operations such as modifying the user attribute information. And the credit system may also obtain its resource information directly from a third party resource platform authorized by the first user.
The third-party resource platform may be understood as any resource obtaining platform, such as a fixed asset certification obtaining platform, an asset certification obtaining platform, and the like.
Specifically, in order to ensure the authenticity of the resource information of the first user, and thus ensure the quota of the target resource determined for the first user, the credit system may actively acquire all resource information of the first user from a third-party resource platform authorized by the first user. Subsequently, more reasonable target resources can be determined for the first user based on more accurate resource information. Meanwhile, in order to further improve the information acquisition efficiency, the user attribute information which is registered by the user in advance can be directly acquired, displayed to the first user, and the modification operation of the first user is received, so that the overall information acquisition efficiency is improved, and the accuracy and the integrity of the information are ensured.
Step 204: and determining an auditing model set comprising at least one target auditing model based on the asset index set of the first user and the attribute information of the auditing models.
In practical application, an audit model set is stored in an audit model database of a credit system, a plurality of audit models are stored in the audit model database, and each audit model set comprises a plurality of target audit models; and each set of audit models corresponds to a different first user.
Specifically, the determining an audit model set including at least one target audit model based on the asset index set of the first user and the attribute information of the audit model includes:
determining attribute information of each audit model in an audit model database;
matching the asset index set of the first user with the attribute information of each auditing model, and determining at least one target auditing model corresponding to the first user based on the matching result;
and constructing a review model set based on the at least one target review model.
The attribute information of the audit model includes, but is not limited to, industry information and processing resource information corresponding to the audit model. In practical application, each audit model can be regarded as a decision inference tree, and each decision inference tree corresponds to customers in different industries and different credit products.
In specific implementation, after the asset index set of the first user is determined, a preset number of auditing models are matched for the first user from the auditing model database based on the asset index set of the first user, so as to form an auditing model set for subsequent auditing of the first user, where the preset number may be set according to actual application, and the preset number is not limited in this specification, for example, set to 5, 6, and so on.
Specifically, the audit model is obtained by training through the following steps:
establishing an initial auditing model according to an asset index set of a sample user and attribute information of resources to be acquired by the sample user;
and training the initial auditing model based on the asset index set of the sample user and the auditing result of the second user on the sample user according to the asset index set to obtain the auditing model.
Wherein, the initial auditing model can be understood as a decision inference tree instance.
In practical application, the credit and audit staff can construct different decision inference tree examples according to different credit products of customers in different industries, for example, providing purchasing products for catering merchants in local life, so that the credit and audit staff can construct a credit and audit decision inference tree (i.e., an initial audit model) of purchasing credits for the customers in the industry.
In order to prevent overfitting, fuzzy logic can be added into the constructed decision reasoning tree, and the generalization capability of the decision reasoning tree is improved. And then training the constructed decision inference tree. And finding out historical approval records of local living catering merchants processed by the creditor along the above example, constructing a training sample, selecting two types of training data which pass crediting and fail crediting from the training sample, and deciding by using a decision inference tree respectively, wherein if an abnormal condition is found (namely the approval result in the training sample is inconsistent with the approval result of the decision inference tree), the decision inference tree is readjusted until all the training data of the historical samples can be evaluated correctly. And obtaining the trained decision inference tree (namely an audit model).
In specific implementation, a plurality of initial auditing models (namely decision inference tree instances) are constructed according to an asset index set of a sample user (the industry of the sample user can be determined through the asset index set) and attribute information of resources to be acquired by the sample user (credit products can be determined through the attribute information of the resources to be acquired).
And then training the initial auditing model based on the asset index set of each sample user and the auditing result (historical approval record) of the second user (i.e. credit personnel) to the sample user according to the asset index set to obtain the auditing model.
In the embodiment of the specification, a plurality of auditing models can be trained according to different credit products of different passenger groups, and subsequently, when the system is used, a reasonable target auditing model can be allocated to the first user based on the industry of the first user and the attribute information of the resource to be acquired, so that the first user can be quickly and accurately audited.
In addition, the audit model comprises an identity audit model and a resource audit model, wherein the identity audit model is obtained by training the following steps:
training the identity auditing model based on the user attribute information in the asset index set of the sample user and the auditing result of the second user on the sample user based on the user attribute information to obtain the identity auditing model;
correspondingly, the resource auditing model is obtained by training the following steps:
and training the resource auditing model based on the resource information in the asset index set of the sample user and the auditing result of the second user on the sample user based on the resource information to obtain the resource auditing model.
In practical application, each audit model comprises an identity audit model and a resource audit model. Specifically, for the specific training of the identity audit model and the resource audit model, reference may be made to the above embodiments, which are not described herein again.
In the embodiment of the specification, each audit model comprises an identity audit model and a resource audit model, and when the identity audit model is applied subsequently, the identity of the first user can be audited based on the identity audit model, and if the identity information of the first user is not audited, the resource audit can be omitted, so that the processing resources of the crediting and auditing system are saved, and the processing efficiency of the crediting and auditing system is improved.
Step 206: and inputting the asset index set of the first user into the auditing model set to obtain the auditing result of the first user output by each target auditing model in the auditing model set.
Specifically, the inputting the asset index set of the first user into the audit model set to obtain the audit result of the first user output by each target audit model in the audit model set includes:
inputting the user attribute information in the asset index set of the first user into each identity auditing model in the auditing model set, and obtaining a first auditing result of the first user output by each identity auditing model;
and under the condition that the first auditing result meets the preset auditing condition, inputting the resource information in the asset index set of the first user into each resource auditing model in the auditing model set, and obtaining a second auditing result of the first user output by each resource auditing model.
The preset auditing condition may be set according to actual application, and this is not limited in this specification, for example, the preset auditing condition is that the first auditing result is passed. That is, the resource information of the first user is checked only when the first checking result of the first user is passed.
Specifically, the first review result may be understood as pass or fail, and the second review result may be understood as a specific resource.
Taking an example that the audit model set comprises three target audit models, firstly, respectively inputting the user attribute information in the asset index set of a first user into the identity audit model of a first target audit model, and obtaining a first audit result of the first user output by the identity audit model of the first target audit model; and under the condition that the first auditing result is passed, inputting the asset information in the asset index set of the first user into the resource auditing model of the first target auditing model, obtaining a first second auditing result of the first user output by the resource auditing model of the first target auditing model, and if the first auditing result is not passed, ending the auditing process.
Similarly, the user attribute information in the asset index set of the first user is respectively input into the identity auditing model of the second target auditing model, and a second first auditing result of the first user output by the identity auditing model of the second target auditing model is obtained; and under the condition that the first auditing result is passed, inputting the asset information in the asset index set of the first user into a resource auditing model of a second target auditing model, obtaining a second auditing result of the first user output by the resource auditing model of the second target auditing model, and if the first auditing result is not passed, ending the auditing process.
Respectively inputting the user attribute information in the asset index set of the first user into an identity auditing model of a third target auditing model, and obtaining a third first auditing result of the first user output by the identity auditing model of the third target auditing model; and under the condition that the first auditing result is passed, inputting the asset information in the asset index set of the first user into a resource auditing model of a third target auditing model, obtaining a third second auditing result of the first user output by the resource auditing model of the third target auditing model, and if the first auditing result is not passed, ending the auditing process.
The second result of the review can be understood as resource information, such as a loan amount.
In the embodiment of the description, in order to improve the processing efficiency of the credit system and save the processing resources of the credit system, when the identity information audit of the first user fails, the resource audit process is not performed on the first user, so that the resource occupation of the resource audit process is avoided.
Step 208: and determining the target resource of the first user based on the auditing result of the first user.
Specifically, the determining the target resource of the first user based on the audit result of the first user includes:
processing the first audit result and the second audit result of the first user according to a preset audit rule to obtain a target audit result of the first user;
and determining the target resource of the first user based on the target auditing result of the first user.
The preset audit rule may be set according to actual application, for example, the preset audit rule is a rule that a few audit rules comply with a majority, or a rule that an audit result obtained by a model with the highest score is a target audit result.
In specific implementation, after the first and second auditing results are obtained, a preset auditing rule is run on a result set formed by the first and second auditing results to determine a final evaluation result for the first user.
Along the above example, if the first audit result of the first user is pass, the second first audit result is not pass, and the third first audit result is pass, then based on the rule that the minority obeys the majority, the first audit result of the first user can be determined to be pass. At this time, the first second review result of the first user is 50 thousands, the third second review result is 60 thousands, and the score of the resource review model corresponding to the third second review result is the highest, so that based on the rule that the review result obtained by the model with the highest score is the target review result, it can be determined that the second review result of the first user is 60 thousands. It can thus be determined that the final evaluation result (target resource) of the first user is 60 ten thousand.
After receiving a target resource acquisition request of a first user, the data processing method can efficiently and accurately audit the first user based on an audit model set matched with the first user, so that reasonable target resources can be distributed to the first user based on an audit result, and even if a large number of target resource acquisition requests are met, the data processing method provided by the embodiment of the specification can rapidly process the target resources, thereby greatly improving the processing efficiency and improving the user experience.
In addition, in order to ensure the stability and accuracy of the audit model, the credit system retrains the audit model based on a new training sample in a fixed period or under the condition that the processed resource acquisition request meets a certain condition, and the specific implementation manner is as follows:
acquiring an asset index set of the first user based on a preset time interval;
and retraining the auditing model according to the asset index set of the first user and the auditing result of the second user on the first user according to the asset index set to obtain a new auditing model.
The preset time interval may be set according to practical applications, which is not limited in this specification, for example, the preset time interval is 2 months, 3 months, and the like.
In addition, training of the audit model may also be triggered according to the number of resource acquisition requests processed, for example, in the case that the audit model has processed 5000 resource acquisition requests, it may be retrained based on the history of 5000 resource acquisition requests it processes.
Meanwhile, in order to perform combined optimization on the target audit models in the audit model sets, the target audit models in each audit model set can be scored, and then the target audit models with the highest scores in a plurality of audit model sets aiming at the same credit product in the same industry are recombined to form a more optimized audit model set. The specific implementation mode is as follows:
and scoring each target auditing model in the auditing model set based on a preset scoring rule, and adjusting the target auditing models in the auditing model set based on a scoring result.
The preset scoring rule can be set according to actual application, for example, the preset scoring rule is scored according to the processing efficiency, the processing amount, the user audit passing rate and the like of each target audit model. Specifically, the scoring basis of each target audit model is the contribution degree of the credit evaluation result.
The following description will further explain the data processing method by taking the application of the data processing method provided in this specification in the field of crediting and auditing as an example, with reference to fig. 3. Fig. 3 shows a flowchart of a processing procedure of a data processing method according to an embodiment of the present specification, which specifically includes the following steps.
Step 302: a loan application request is received from a client.
Specifically, before receiving a loan application request of a customer, a plurality of decision inference trees aiming at different credit products of different customer groups are trained.
Referring to fig. 4, fig. 4 is a schematic diagram illustrating training of an audit model in a data processing method according to an embodiment of the present disclosure.
Fig. 4 includes the credit reviewer, the decision inference tree, and sample data, where the decision inference tree may be understood as the auditing model of the above embodiment, and the sample data includes positive sample data and negative sample data, that is, the historical credit review passed data and the credit review non-passed data processed by the credit reviewer.
Firstly, the credit auditor generates different decision reasoning trees based on different credit products of different passenger groups, and fuzzy logic is added into each decision reasoning tree to prevent overfitting, so that the generalization capability of the decision reasoning trees is improved. Then, the decision inference tree is trained by using the acquired positive sample data and negative sample data, and the trained decision inference tree, that is, the machine assistant in fig. 4 is obtained.
In addition, in the subsequent use process, under the condition that new approval data are precipitated in one period, the decision inference tree can be retrained continuously according to the steps so as to improve the efficiency and the accuracy of the decision inference tree.
Step 304: and evaluating the client through a review group based on the loan application request of the client to obtain a plurality of evaluation results.
The review groups in fig. 3 can be understood as the review model sets of the above embodiments, and each review group includes a plurality of machine assistants (review models), and each machine assistant corresponds to different industry clients and different industry index sets.
In practical application, a plurality of machine assistants form a review group, each machine assistant in the group carries out joint examination and approval on loan application requests of clients, and finally credit evaluation results and loan amounts of the clients are determined according to preset voting rules of the review group.
Step 306: voting is carried out on the plurality of evaluation results based on a preset voting rule, and an evaluation result of the loan application request of the client is obtained.
The preset voting rule can be set according to actual conditions, and is not limited herein.
In practical application, the data processing method comprises the following specific implementation steps:
the method comprises the following steps: setting the members of the review group, the range of the clients to be reviewed and the voting rules of the review, wherein the voting can have a plurality of playing methods according to different evaluation results, and can be winning when the total number of the votes is the highest or winning when the total score of the votes is the highest, and setting different voting rules according to actual conditions.
Step two: and (4) deciding a specific review group according to the loan application request of the client, and performing credit evaluation on the request by the machine assistant of the member in the review group.
Step three: and (4) forming a result set by credit evaluation results produced by all the machine assistants in the panel, and operating a preset voting rule on the result set to produce a final evaluation result.
Step four: after a preset period, scoring is carried out on the machine assistants in all the review groups, and a plurality of machine assistants with high scores are selected to recombine new review groups according to the scoring basis, namely the contribution degree of the credit evaluation result.
Referring to fig. 5, fig. 5 is a schematic diagram illustrating optimization of an audit model and an audit model set in a data processing method according to an embodiment of the present disclosure.
FIG. 5 includes the optimization engine, machine assistant and panel of the credit system.
And the optimization engine is responsible for the machine assistant and the iterative upgrading of the review group joint examination and approval. After the system runs for a period, the optimization engine can initiate a training task, and a creditor retrains the machine assistant according to the approval result data in the period and the prior knowledge of the creditor, so that the approval accuracy rate is improved; meanwhile, the optimization engine initiates a review group recombination instruction, recombination is carried out according to scoring results of machine assistants in the existing review group, and a new review group is constructed.
In the embodiment of the specification, the credit system can break through the technical problems of credit audit effectiveness ceiling and instability of credit audit through the combination of the machine assistant, the joint approval and the optimization engine, and meanwhile, the decision inference tree has the characteristic of inheritability and iteration, so that the result of credit evaluation can be more accurate. The problem that in the prior art, the credit requests of a credit system are accumulated, and the processing efficiency is extremely low is solved.
Corresponding to the above method embodiment, the present specification further provides an embodiment of a data processing apparatus, and fig. 6 shows a schematic structural diagram of a data processing apparatus provided in an embodiment of the present specification. As shown in fig. 6, the apparatus includes:
a request receiving module 602 configured to receive a target resource acquisition request of a first user and determine an asset index set of the first user based on the target resource acquisition request;
a set determination module 604 configured to determine a set of audit models including at least one target audit model based on the asset metric set of the first user and attribute information of the audit models;
a result output module 606, configured to input the asset index set of the first user into the review model set, and obtain the review result of the first user output by each target review model in the review model set;
a resource determination module 608 configured to determine a target resource of the first user based on the review result of the first user.
Optionally, the request receiving module 602 is further configured to:
receiving a target resource acquisition request of a first user, generating a resource application table for the first user based on the target resource acquisition request, and returning the resource application table to the first user;
and receiving user attribute information and resource information submitted by the first user based on the resource application form, and generating an asset index set of the first user based on the user attribute information and the resource information.
Optionally, the request receiving module 602 is further configured to:
receiving a target resource acquisition request of a first user, acquiring user attribute information of the first user based on the target resource acquisition request, and acquiring resource information of the first user from a third-party resource platform corresponding to the resource information under the condition of receiving an authorization instruction of the first user for the resource information;
generating an asset metric set for the first user based on the user attribute information and the resource information.
Optionally, the audit model is obtained by training as follows:
establishing an initial auditing model according to an asset index set of a sample user and attribute information of resources to be acquired by the sample user;
and training the initial auditing model based on the asset index set of the sample user and the auditing result of the second user on the sample user according to the asset index set to obtain the auditing model.
Optionally, the audit model includes an identity audit model and a resource audit model, where the identity audit model is obtained by training through the following steps:
training the identity auditing model based on the user attribute information in the asset index set of the sample user and the auditing result of the second user on the sample user based on the user attribute information to obtain the identity auditing model;
correspondingly, the resource auditing model is obtained by training the following steps:
and training the resource auditing model based on the resource information in the asset index set of the sample user and the auditing result of the second user on the sample user based on the resource information to obtain the resource auditing model.
Optionally, the result output module 606 is further configured to:
inputting the user attribute information in the asset index set of the first user into each identity auditing model in the auditing model set, and obtaining a first auditing result of the first user output by each identity auditing model;
and under the condition that the first auditing result meets the preset auditing condition, inputting the resource information in the asset index set of the first user into each resource auditing model in the auditing model set, and obtaining a second auditing result of the first user output by each resource auditing model.
Optionally, the resource determination module 608 is further configured to:
processing the first audit result and the second audit result of the first user according to a preset audit rule to obtain a target audit result of the first user;
and determining the target resource of the first user based on the target auditing result of the first user.
Optionally, the apparatus further comprises:
a training module configured to:
acquiring an asset index set of the first user based on a preset time interval;
and retraining the auditing model according to the asset index set of the first user and the auditing result of the second user on the first user according to the asset index set to obtain a new auditing model.
Optionally, the apparatus further comprises:
a scoring module configured to:
and scoring each target auditing model in the auditing model set based on a preset scoring rule, and adjusting the target auditing models in the auditing model set based on a scoring result.
The data processing device provided by the embodiment of the present specification can efficiently and accurately audit the first user based on the audit model set matched with the first user after receiving the target resource acquisition request of the first user, so as to allocate a reasonable target resource to the first user based on the audit result, and even in the face of a large number of target resource acquisition requests, the data processing method provided by the embodiment of the present specification can rapidly process the target resource acquisition requests, thereby greatly improving the processing efficiency and improving the user experience.
The above is a schematic configuration of a data processing apparatus of the present embodiment. It should be noted that the technical solution of the data processing apparatus and the technical solution of the data processing method belong to the same concept, and details that are not described in detail in the technical solution of the data processing apparatus can be referred to the description of the technical solution of the data processing method.
FIG. 7 illustrates a block diagram of a computing device 700 provided in accordance with one embodiment of the present description. The components of the computing device 700 include, but are not limited to, memory 710 and a processor 720. Processor 720 is coupled to memory 710 via bus 730, and database 750 is used to store data.
Computing device 700 also includes access device 740, access device 740 enabling computing device 700 to communicate via one or more networks 760. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. Access device 740 may include one or more of any type of network interface, e.g., a Network Interface Card (NIC), wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.
In one embodiment of the present description, the above-described components of computing device 700, as well as other components not shown in FIG. 7, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 7 is for purposes of example only and is not limiting as to the scope of the present description. Those skilled in the art may add or replace other components as desired.
Computing device 700 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), mobile phone (e.g., smartphone), wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 700 may also be a mobile or stationary server.
Wherein the processor 720 is configured to execute computer-executable instructions that, when executed by the processor, implement the steps of the data processing method described above.
The above is an illustrative scheme of a computing device of the present embodiment. It should be noted that the technical solution of the computing device and the technical solution of the data processing method belong to the same concept, and details that are not described in detail in the technical solution of the computing device can be referred to the description of the technical solution of the data processing method.
An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which when executed by a processor implement the steps of the data processing method described above.
The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium belongs to the same concept as the technical solution of the data processing method, and details that are not described in detail in the technical solution of the storage medium can be referred to the description of the technical solution of the data processing method.
The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
The computer instructions comprise computer program code which may be in the form of source code, object code, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may contain content that is subject to appropriate increase or decrease as required by legislation and patent practice in jurisdictions, for example, in some jurisdictions, computer readable media does not include electrical carrier signals and telecommunications signals as is required by legislation and patent practice.
It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of acts, but those skilled in the art should understand that the present embodiment is not limited by the described acts, because some steps may be performed in other sequences or simultaneously according to the present embodiment. Further, those skilled in the art should also appreciate that the embodiments described in this specification are preferred embodiments and that acts and modules referred to are not necessarily required for an embodiment of the specification.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The preferred embodiments of the present specification disclosed above are intended only to aid in the description of the specification. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the embodiments and the practical application, to thereby enable others skilled in the art to best understand and utilize the embodiments. The specification is limited only by the claims and their full scope and equivalents.
Claims (12)
1. A method of data processing, comprising:
receiving a target resource acquisition request of a first user, and determining an asset index set of the first user based on the target resource acquisition request;
determining an auditing model set comprising at least one target auditing model based on the asset index set of the first user and attribute information of the auditing models, wherein each target auditing model comprises an identity auditing model and a resource auditing model;
inputting the asset index set of the first user into the auditing model set to obtain the auditing result of the first user output by each target auditing model in the auditing model set;
and determining the target resource of the first user based on the auditing result of the first user.
2. The data processing method of claim 1, wherein receiving a target resource acquisition request of a first user and determining an asset metric set of the first user based on the target resource acquisition request comprises:
receiving a target resource acquisition request of a first user, generating a resource application table for the first user based on the target resource acquisition request, and returning the resource application table to the first user;
and receiving user attribute information and resource information submitted by the first user based on the resource application form, and generating an asset index set of the first user based on the user attribute information and the resource information.
3. The data processing method of claim 1, wherein receiving a target resource acquisition request of a first user and determining an asset metric set of the first user based on the target resource acquisition request comprises:
receiving a target resource acquisition request of a first user, acquiring user attribute information of the first user based on the target resource acquisition request, and acquiring resource information of the first user from a third-party resource platform corresponding to the resource information under the condition of receiving an authorization instruction of the first user for the resource information;
generating an asset metric set for the first user based on the user attribute information and the resource information.
4. A data processing method as claimed in claim 2 or 3, wherein the audit model is obtained by training:
establishing an initial auditing model according to an asset index set of a sample user and attribute information of resources to be acquired by the sample user;
and training the initial auditing model based on the asset index set of the sample user and the auditing result of the second user on the sample user according to the asset index set to obtain the auditing model.
5. The data processing method of claim 4, the audit model comprising an identity audit model and a resource audit model, wherein the identity audit model is trained by:
training the identity auditing model based on the user attribute information in the asset index set of the sample user and the auditing result of the second user on the sample user based on the user attribute information to obtain the identity auditing model;
correspondingly, the resource auditing model is obtained by training the following steps:
and training the resource auditing model based on the resource information in the asset index set of the sample user and the auditing result of the second user on the sample user based on the resource information to obtain the resource auditing model.
6. The data processing method of claim 5, wherein the inputting the asset metric set of the first user into the set of audit models to obtain the audit result of the first user output by each target audit model in the set of audit models comprises:
inputting the user attribute information in the asset index set of the first user into each identity auditing model in the auditing model set, and obtaining a first auditing result of the first user output by each identity auditing model;
and under the condition that the first auditing result meets the preset auditing condition, inputting the resource information in the asset index set of the first user into each resource auditing model in the auditing model set, and obtaining a second auditing result of the first user output by each resource auditing model.
7. The data processing method of claim 6, the determining a target resource of the first user based on the review result of the first user, comprising:
processing the first audit result and the second audit result of the first user according to a preset audit rule to obtain a target audit result of the first user;
and determining the target resource of the first user based on the target auditing result of the first user.
8. The data processing method of claim 4, further comprising:
acquiring an asset index set of the first user based on a preset time interval;
and retraining the auditing model according to the asset index set of the first user and the auditing result of the second user on the first user according to the asset index set to obtain a new auditing model.
9. The data processing method of claim 1, further comprising:
and scoring each target auditing model in the auditing model set based on a preset scoring rule, and adjusting the target auditing models in the auditing model set based on a scoring result.
10. A data processing apparatus comprising:
the system comprises a request receiving module, a resource acquisition module and a resource management module, wherein the request receiving module is configured to receive a target resource acquisition request of a first user and determine an asset index set of the first user based on the target resource acquisition request;
a set determination module configured to determine an audit model set including at least one target audit model based on the asset metric set of the first user and attribute information of the audit model, wherein each target audit model includes an identity audit model and a resource audit model;
a result output module configured to input the asset index set of the first user into the review model set, and obtain a review result of the first user output by each target review model in the review model set;
a resource determination module configured to determine a target resource of the first user based on the audit result of the first user.
11. A computing device, comprising:
a memory and a processor;
the memory is for storing computer-executable instructions, and the processor is for executing the computer-executable instructions, which when executed by the processor, implement the steps of the data processing method of any one of claims 1 to 9.
12. A computer-readable storage medium storing computer-executable instructions which, when executed by a processor, implement the steps of the data processing method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110666848.8A CN113256404A (en) | 2021-06-16 | 2021-06-16 | Data processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110666848.8A CN113256404A (en) | 2021-06-16 | 2021-06-16 | Data processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113256404A true CN113256404A (en) | 2021-08-13 |
Family
ID=77188435
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110666848.8A Pending CN113256404A (en) | 2021-06-16 | 2021-06-16 | Data processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113256404A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115907986A (en) * | 2022-11-15 | 2023-04-04 | 支付宝(杭州)信息技术有限公司 | Asset checking method and device, medium and computer equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876588A (en) * | 2018-04-28 | 2018-11-23 | 重庆小雨点小额贷款有限公司 | A kind of loan measures and procedures for the examination and approval, device, server and storage medium |
| CN110837963A (en) * | 2019-11-06 | 2020-02-25 | 浪潮卓数大数据产业发展有限公司 | Risk control platform construction method based on data, model and strategy |
| CN111523849A (en) * | 2019-12-31 | 2020-08-11 | 金瓜子科技发展（北京）有限公司 | Resource transaction auditing method and device and server |
| CN111709826A (en) * | 2020-06-11 | 2020-09-25 | 中国建设银行股份有限公司 | Target information determination method and device |
| US20200357060A1 (en) * | 2019-05-10 | 2020-11-12 | Fair Ip, Llc | Rules/model-based data processing system for intelligent default risk prediction |
| CN112150276A (en) * | 2020-09-30 | 2020-12-29 | 中国银行股份有限公司 | Training method, using method, device and equipment of machine learning model |
| CN112927069A (en) * | 2021-04-20 | 2021-06-08 | 顶象科技有限公司 | User credit risk assessment method and device and electronic equipment |
-
2021
- 2021-06-16 CN CN202110666848.8A patent/CN113256404A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108876588A (en) * | 2018-04-28 | 2018-11-23 | 重庆小雨点小额贷款有限公司 | A kind of loan measures and procedures for the examination and approval, device, server and storage medium |
| US20200357060A1 (en) * | 2019-05-10 | 2020-11-12 | Fair Ip, Llc | Rules/model-based data processing system for intelligent default risk prediction |
| CN110837963A (en) * | 2019-11-06 | 2020-02-25 | 浪潮卓数大数据产业发展有限公司 | Risk control platform construction method based on data, model and strategy |
| CN111523849A (en) * | 2019-12-31 | 2020-08-11 | 金瓜子科技发展（北京）有限公司 | Resource transaction auditing method and device and server |
| CN111709826A (en) * | 2020-06-11 | 2020-09-25 | 中国建设银行股份有限公司 | Target information determination method and device |
| CN112150276A (en) * | 2020-09-30 | 2020-12-29 | 中国银行股份有限公司 | Training method, using method, device and equipment of machine learning model |
| CN112927069A (en) * | 2021-04-20 | 2021-06-08 | 顶象科技有限公司 | User credit risk assessment method and device and electronic equipment |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115907986A (en) * | 2022-11-15 | 2023-04-04 | 支付宝(杭州)信息技术有限公司 | Asset checking method and device, medium and computer equipment |
| CN115907986B (en) * | 2022-11-15 | 2023-08-29 | 支付宝(杭州)信息技术有限公司 | Asset checking method and device, medium and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ma et al. | Financial credit risk prediction in internet finance driven by machine learning | |
| US20180260891A1 (en) | Systems and methods for generating and using optimized ensemble models | |
| Rao et al. | Design of comprehensive evaluation index system for P2P credit risk of “three rural” borrowers | |
| TW201944305A (en) | Method and apparatus for determining risk probability of service request event | |
| CN108475393A (en) | The system and method that decision tree is predicted are promoted by composite character and gradient | |
| Eddy et al. | Credit scoring models: Techniques and issues | |
| Yuping et al. | New methods of customer segmentation and individual credit evaluation based on machine learning | |
| CN113435713B (en) | Risk map compiling method and system based on GIS technology and two-model fusion | |
| CN111210332A (en) | Method and device for generating post-loan management strategy and electronic equipment | |
| CN113256404A (en) | Data processing method and device | |
| Zhou | Data mining for individual consumer credit default prediction under e-commence context: a comparative study | |
| TWI761695B (en) | Core body method and device and method and device for generating core body security model, computing device and computer readable storage medium | |
| CN116611911A (en) | Credit risk prediction method and device based on support vector machine | |
| CN115238588A (en) | Graph data processing method, risk prediction model training method and device | |
| CN115545088A (en) | Model construction method, classification method and device and electronic equipment | |
| Shaik et al. | Customer loan eligibility prediction using machine learning | |
| Preetham et al. | A Stacked Model for Approving Bank Loans | |
| Wu et al. | Research on internet financial risk control based on deep learning algorithm | |
| CN111160662A (en) | Risk prediction method, electronic equipment and storage medium | |
| Theuri et al. | The impact of Artficial Intelligence and how it is shaping banking | |
| Glasson | Censored regression techniques for credit scoring | |
| Kumar et al. | Data Mining in Credit Scoring and Future Application | |
| Fair et al. | Endogenous labour flow networks | |
| Pinochet et al. | Predicting the Intention to Use the Investment Aggregate Functionality in the Context of Open Banking Using the Artificial Neural Network Approach | |
| US20240184812A1 (en) | Distributed active learning in natural language processing for determining resource metrics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210813 |