CN113436006A - Loan risk prediction method and device based on block chain - Google Patents
Loan risk prediction method and device based on block chain Download PDFInfo
- Publication number
- CN113436006A CN113436006A CN202110768957.0A CN202110768957A CN113436006A CN 113436006 A CN113436006 A CN 113436006A CN 202110768957 A CN202110768957 A CN 202110768957A CN 113436006 A CN113436006 A CN 113436006A
- Authority
- CN
- China
- Prior art keywords
- loan
- risk
- risk prediction
- client
- customer
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/067—Enterprise or organisation modelling
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Technology Law (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a loan risk prediction method and a loan risk prediction device based on a block chain, which relate to the field of the block chain, and the method comprises the following steps: receiving a loan application request of a loan client; obtaining key loan element information submitted by a loan client according to the loan application request; comparing the key loan element information with the client information of clients with known loan risks, and determining a key loan element evaluation result corresponding to the key loan element information according to the comparison result; determining a loan risk type set of a loan customer according to the key loan element evaluation result; according to the loan risk type set of the loan client, searching a risk prediction model corresponding to the loan risk type from the risk prediction model set; and performing risk prediction on the loan clients based on the one or more searched risk prediction models to obtain the risk prediction results of the loan clients. The method not only can shorten the time consumption of the model training process, but also can improve the accuracy of the whole model prediction.
Description
Technical Field
The invention relates to the field of block chains, in particular to a loan risk prediction method and device based on a block chain.
Background
This section is intended to provide a background or context to the embodiments of the invention that are recited in the claims. The description herein is not admitted to be prior art by inclusion in this section.
When a client applies for loan from a banking institution, the banking institution performs loan risk prediction on the client so as to determine whether to issue corresponding loan to the client according to the risk prediction result. By means of artificial intelligence technology, a risk prediction model can be trained through machine learning to carry out risk prediction on loan clients.
Due to the diversification of client information and loan services, a model capable of accurately predicting the risk of loan clients is trained, and the technical problems of long time consumption and low model accuracy in the training process exist.
Disclosure of Invention
The embodiment of the invention provides a loan risk prediction method based on a block chain, which is used for solving the technical problems of long time consumption and low model accuracy in the training process of the conventional loan risk prediction method by means of an artificial intelligence technology, and comprises the following steps: receiving a loan application request of a loan client; obtaining key loan element information submitted by a loan client according to the loan application request; comparing the key loan element information with the client information of the client with the known loan risk, and determining the key loan element evaluation result corresponding to the key loan element information according to the comparison result, wherein the client information of the client with the known loan risk comprises: knowing key loan element information and key loan element evaluation results of loan risk customers; determining a loan risk type set of the loan customer according to the key loan element evaluation result, wherein the loan risk type set comprises one or more loan risk types of the loan customer; according to a loan risk type set of a loan customer of the loan customer, searching a risk prediction model corresponding to the loan risk type from the risk prediction model set, wherein the risk prediction model set comprises: the loan institutions upload a plurality of risk prediction models through a block chain network; and performing risk prediction on the loan clients based on the one or more searched risk prediction models to obtain the risk prediction results of the loan clients.
The embodiment of the invention also provides a loan risk prediction device based on the block chain, which is used for solving the technical problems of long time consumption and low model accuracy rate in the training process of the traditional loan risk prediction method by means of the artificial intelligence technology, and comprises the following steps: the loan application module is used for receiving a loan application request of a loan client; the key loan element information determining module is used for acquiring key loan element information submitted by a loan client according to the loan application request; the key loan element evaluation result acquisition module is used for comparing the key loan element information with the client information of the client with the known loan risk, and determining the key loan element evaluation result corresponding to the key loan element information according to the comparison result, wherein the client information of the client with the known loan risk comprises: knowing key loan element information and key loan element evaluation results of loan risk customers; the client loan risk type determining module is used for determining a loan risk type set of a loan client according to the key loan element evaluation result, wherein the loan risk type set comprises one or more loan risk types of the loan client; the risk prediction model selection module is used for searching a risk prediction model corresponding to the loan risk type from the risk prediction model set according to the loan risk type set of the loan customer, wherein the risk prediction model set comprises: the loan institutions upload a plurality of risk prediction models through a block chain network; and the risk prediction module is used for performing risk prediction on the loan clients based on the searched one or more risk prediction models to obtain the risk prediction results of the loan clients.
The embodiment of the invention also provides computer equipment for solving the technical problems of long time consumption and low model accuracy in the training process of the conventional loan risk prediction method by means of the artificial intelligence technology.
The embodiment of the invention also provides a computer readable storage medium for solving the technical problems of long time consumption and low model accuracy in the training process of the conventional loan risk prediction method by means of the artificial intelligence technology, wherein the computer readable storage medium stores a computer program for executing the loan risk prediction method based on the block chain.
According to the loan risk prediction method based on the block chain, the device, the computer equipment and the computer readable storage medium provided by the embodiment of the invention, risk prediction models uploaded by various loan institutions are received through the block chain network to form a risk prediction model set, after a loan application request of a loan customer is received, the loan risk type set of the loan customer is determined according to the loan application request of the loan customer, then, according to various loan risk types of the loan customer in the loan risk type set, a risk prediction model corresponding to the loan risk type is searched in the risk prediction model set, and finally, based on one or more searched risk prediction models, the loan customer is subjected to risk prediction to obtain a risk prediction result of the loan customer.
Compared with the technical scheme that a model is directly trained to carry out risk prediction on loan clients in the prior art, in the embodiment of the invention, each loan institution respectively trains a plurality of risk prediction models, selects the risk prediction model corresponding to the loan risk type of the current loan application request of the loan client from the plurality of risk prediction models, and carries out loan risk prediction on the loan clients, thereby not only shortening the time consumption of the model training process, but also improving the accuracy of the whole model prediction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts. In the drawings:
fig. 1 is a flowchart of a loan risk prediction method based on a block chain according to an embodiment of the present invention;
FIG. 2 is a flow chart of loan risk prediction provided in an embodiment of the invention;
FIG. 3 is a flow chart of an alternative loan risk prediction scheme provided in embodiments of the invention;
FIG. 4 is a flowchart of a risk prediction result chaining process according to an embodiment of the present invention;
FIG. 5 is a block diagram of a loan transaction uplink process according to an embodiment of the invention;
fig. 6 is a flow chart of loan application based on a blockchain and 5G message provided in an embodiment of the present invention;
FIG. 7 is a flow chart of a process for generating a set of risk types for a customer loan, provided in an embodiment of the invention;
FIG. 8 is a flow chart of machine learning provided in an embodiment of the present invention;
FIG. 9 is a schematic diagram of a block chain-based loan risk prediction apparatus according to an embodiment of the invention;
FIG. 10 is a schematic view of an alternative loan risk prediction arrangement provided in an embodiment of the invention;
fig. 11 is a schematic diagram of a computer device provided in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention are further described in detail below with reference to the accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
The embodiment of the invention provides a loan risk prediction method based on a block chain, and fig. 1 is a flow chart of the loan risk prediction method based on the block chain provided in the embodiment of the invention, as shown in fig. 1, the method includes the following steps:
and S101, receiving a loan application request of a loan client.
It should be noted that the loan application request in the embodiment of the present invention may be a loan application request initiated by a loan client to any banking institution. Optionally, the loan application request includes at least: the customer information of the loan customer and the product information of the currently applied loan product.
S102, obtaining key loan element information submitted by a loan customer according to a loan application request;
the key loan factor information acquired in S102 includes, but is not limited to: loan type, property information of the client, business conditions of the public client, industry information of the industry where the client is located, loan application, credit information, historical repayment conditions and the like.
S103, comparing the key loan element information with the client information of the client with the known loan risk, and determining the key loan element evaluation result corresponding to the key loan element information according to the comparison result, wherein the client information of the client with the known loan risk comprises: knowing key loan element information and key loan element evaluation results of loan risk customers;
it should be noted that the client information of the clients with known loan risks may be stored in the blockchain network to ensure the authenticity and non-tamper of the data. The known loan risk clients can be clients with known loan risk prediction results pre-stored in a bank system, and the key loan element information and the key loan element evaluation results of the clients are stored in a correlation manner, so that after a loan application request of a new loan client is received, the key loan element information submitted by the loan client is obtained according to the loan application request, the key loan element information submitted by the loan client is matched with the key loan element information of the client with the known loan risk, and the key loan element evaluation result of the client successfully matched with the key loan element evaluation result is determined as the key loan element evaluation result of the loan client.
And S104, determining a loan risk type set of the loan customer according to the key loan element evaluation result, wherein the loan risk type set comprises one or more loan risk types of the loan customer.
In the embodiment of the invention, after a loan application request of a loan client is received, one or more loan risk types evaluated by the loan client can be determined according to the client information of the loan client and the product information of the currently applied loan product contained in the loan application request, and a loan risk type set of the loan client is formed according to the determined loan risk types. The loan risk types included in the loan risk type set in the embodiment of the present invention include, but are not limited to, the following: fraud risk, material counterfeiting risk, bankruptcy risk, illegal funds transfer risk, breach risk, etc.
In one embodiment, after searching the risk prediction model corresponding to the loan risk type from the risk prediction model set according to the loan risk type set of the loan customer, the loan risk prediction method based on the block chain provided in the embodiment of the present invention may further include the following steps: determining similar customers of the loan customers based on a pre-constructed customer relationship knowledge graph; adding the loan risk types of similar clients into the loan risk type set of the loan clients.
In the embodiment of the invention, the loan risk types of similar customers are added into the loan risk type set of the loan customer, so that more loan risk types can be predicted for the loan customer, and the finally generated risk prediction result is more accurate.
S105, according to a loan risk type set of a loan customer of the loan customer, searching a risk prediction model corresponding to the loan risk type from the risk prediction model set, wherein the risk prediction model set comprises: and each loan institution uploads a plurality of risk prediction models through the block chain network.
In the embodiment of the invention, historical loan risk data of each loan institution are fully utilized to train various machine learning models such as a support vector machine model, a Bayesian model and a neural network model, so that a plurality of risk prediction models of each loan institution can be obtained.
And searching a risk prediction model corresponding to the loan risk type from the risk prediction model set according to the loan risk type set of the loan client, wherein each loan risk prediction model can be uploaded to a block chain network by each loan institution, and the loan institution corresponding to each node of the block chain is shared for use. For example, some loan institutions use Bayesian models to warn default risks and deep learning models to warn default risks, and thus the loan institutions can upload models with higher prediction performance to block chains.
And S106, performing risk prediction on the loan client based on the one or more searched risk prediction models to obtain a risk prediction result of the loan client.
It should be noted that, if the loan risk type set of the loan customer includes a loan risk type, one or more risk prediction models corresponding to the loan risk type are searched from the risk prediction model set; the loan risk type set of the loan customer comprises a plurality of loan risk types, and one or more risk prediction models corresponding to each loan risk type are found out from the risk prediction model set; by utilizing each risk prediction model, the risk prediction can be carried out on the loan client to obtain a plurality of risk prediction sub-results, and then the risk prediction results of the loan client can be obtained by integrating the risk prediction sub-results.
Common integrated algorithm models are: the embodiment of the invention can adopt any one of the three integration algorithms to realize the integration of a plurality of risk prediction sub-results. In general, to build an integration with good generalization performance, individual learning algorithms should be good and different. For example, when predicting a certain type of risk (e.g., a default risk), one or more risk prediction models found in the above description may be classified (e.g., support vector machine, bayesian network, deep learning algorithm of different network structures) according to the type of the individual risk prediction model, and then, in each type of model, the model with the best performance is selected, and then, the model is integrated based on the selected model to obtain the prediction result of the risk.
In the embodiment of the invention, the loan requests of customers can be respectively predicted based on each model, then the prediction results of each model are integrated based on various integration algorithms of machine learning configured by intelligent contracts, and a final conclusion is finally obtained: i.e., whether the customer's transaction has a corresponding risk (e.g., bankruptcy risk, default risk) and the probability of the risk occurring.
In one embodiment, as shown in fig. 2, the method for predicting loan risk based on a block chain provided in the embodiment of the present invention may be implemented by the following steps when performing risk prediction on a loan client based on one or more found risk prediction models:
s201, obtaining the customer information of the loan customer;
s202, inputting the customer information of the loan customer into each searched risk prediction model to obtain a risk prediction result of each risk prediction model;
and S203, generating a risk prediction result of the loan customer according to the risk prediction result of each risk prediction model.
The customer information of the loan customer acquired in S201 includes, but is not limited to: the system comprises the assets information of the client, the business data of the public client, the industry data of the public client, the historical predicted client behavior data and the historical risk prediction result.
When the above S203 is implemented specifically, it can be implemented by the following steps: selecting a target integrated algorithm model to be adopted by each loan structure from a plurality of integrated algorithm models prestored on the blockchain network by using an intelligent contract prestored on the blockchain network; integrating the risk prediction results of the risk prediction models by using the selected target integration algorithm model to obtain the risk prediction result of the loan customer; and pushing the risk prediction result of the loan client to each loan structure.
Optionally, the target integrated algorithm model to be adopted selected by each loan institution may be a model with relatively good performance, and further, each loan institution may upload the selected integrated algorithm model and determine the performance of the integrated algorithm model uploaded by each loan institution based on historical loan service data through a block chain network.
In an embodiment, as shown in fig. 3, the loan risk prediction method based on a block chain provided in the embodiment of the present invention may specifically include the following steps when generating a risk prediction result of a loan customer according to the risk prediction result of each risk prediction model:
s301, obtaining the performance evaluation result of each risk prediction model;
s302, determining the weight coefficient of each risk prediction model according to the performance evaluation result of each risk prediction model;
and S303, generating a risk prediction result of the loan customer according to the weight coefficient and the risk prediction result of each risk prediction model.
In an embodiment, as shown in fig. 4, after performing risk prediction on the loan client based on the one or more found risk prediction models to obtain a risk prediction result of the loan client, the method for predicting loan risk based on a block chain provided in an embodiment of the present invention may further include the following steps:
s401, uploading the risk prediction result of the loan client to a block chain network;
and S402, executing loan application business of the loan customer based on the risk prediction result of the loan customer stored on the block chain network, wherein the loan application business of the loan customer is refused to be executed under the condition that the risk prediction result corresponding to any risk type of the loan customer exceeds a preset risk condition.
Through the embodiment, the risk prediction result is uploaded to the block chain network, so that other businesses, such as but not limited to loan application businesses, can be conveniently executed based on the risk prediction result stored in the block chain network.
When the loan risk prediction method based on the block chain provided by the embodiment of the invention is applied to the prediction of the loan risk of a bank to a public or private customer, the method specifically comprises the following steps:
1) and receiving a loan application request of the loan client, and uploading the loan application request data to the block chain. According to the loan application request, key loan elements submitted by a client, such as the type of loan submitted by the client, the property information of the client, the company management condition of the client, the industry information of the client, the loan application, the credit information of the loan client, other loans of the client, and the repayment condition of the previous loan, are obtained.
2) The method comprises the steps of obtaining customer information stored in a block chain by each loan institution, wherein the customer information comprises customer data collected by each branch of a bank, behavior prediction result data of the customer, analysis data of the industry where the customer is located and a risk prediction result of the customer in the bank by a customer behavior prediction model of the bank, and comparing and analyzing the information and loan key elements to obtain a loan key element evaluation result.
3) Determining a loan risk type set of the loan clients according to the evaluation result of the key loan elements, wherein the loan risk type set has fraud risk, material counterfeiting risk, bankruptcy risk, money laundering risk, default risk and the like;
4) and searching a risk prediction model corresponding to the loan risk type from the risk prediction model set according to the loan risk type set of the loan client, wherein each loan risk prediction model can be uploaded to a block chain network by each loan institution, and the loan institution corresponding to each node of the block chain is shared for use. For example, some loan institutions use Bayesian models to warn default risks and deep learning models to warn default risks, and thus the loan institutions can upload models with higher prediction performance to block chains.
5) And performing loan risk prediction on the loan clients based on one or more loan risk prediction models searched from the block chain to obtain the risk prediction result of the loan clients. For example, the loan requests of customers can be predicted respectively based on each model, then the prediction results of each model are integrated based on various integration algorithms of machine learning configured by intelligent contracts, and finally a final conclusion is obtained: i.e., whether the customer's transaction has a corresponding risk, such as a bankruptcy risk, a default risk, and a probability of occurrence of a risk.
6) And determining whether to release a loan to the client and the suggested quota of the loan based on the obtained risk prediction result, and uploading the data to the block chain. For example, information data with a default risk of 0.1 probability, a maximum loan amount of 10 thousands and the like are uploaded to the block chain.
7) And uploading the loan application information, the risk prediction result and the later loan execution wind result of each loan application to a block chain, and then evaluating the performance of the risk prediction model and adjusting parameters based on the data. The previous model evaluation may be due to the insufficiency of sample data, the precision of the evaluation is not accurate, and the newly appeared sample data can just make up the previous insufficiency.
Further, as shown in fig. 5, after performing a loan application service of a loan customer based on the risk prediction result of the loan customer stored on the blockchain network, the method for predicting a loan risk based on a blockchain provided in an embodiment of the present invention may further include the following steps:
s501, obtaining service data of loan application service;
and S502, uploading the service data of the loan application service to a block chain network.
The service data is stored in the block chain network, so that the traceability of the service data can be facilitated.
In one embodiment, as shown in fig. 6, before obtaining the key loan element information submitted by the loan client according to the loan application request, the block chain-based loan risk prediction method provided in the embodiment of the present invention further includes the following steps:
s601, receiving a loan application request sent by a loan client through a 5G message.
In the embodiment of the invention, the loan application request is sent through the 5G message, so that a client can transact loan application business through the 5G message, the trouble of downloading a client can be avoided, and the real-time performance of business transaction can be greatly improved by utilizing the advantage of high data transmission rate of the 5G message.
In order to enable a loan client to quickly know the risk prediction result, in an embodiment, as shown in fig. 6, after performing risk prediction on the loan client based on one or more found risk prediction models to obtain the risk prediction result of the loan client, the loan risk prediction method based on the block chain provided in the embodiment of the present invention further includes the following steps:
s602, determining loan amount information of the loan client according to the risk prediction result of the loan client;
and S603, sending the loan amount information of the loan client to the loan client through a 5G message.
In one embodiment, as shown in fig. 7, the block chain-based loan risk prediction method provided in the embodiment of the present invention may further include the following steps:
s701, obtaining loan risk data corresponding to each type of loan stored on a block chain network;
s702, counting loan risk type probability corresponding to each type of loan type by using an intelligent contract pre-stored on a block chain network;
s703, storing the loan risk types with the probability higher than the preset threshold value and the corresponding loan types in a block chain network in an associated manner;
and S704, inquiring the corresponding loan risk type from the block chain network according to the loan type of the loan customer, and adding the corresponding loan risk type into the loan risk type set of the loan customer.
It should be noted that the loan types in the embodiment of the present invention include, but are not limited to: personal petty loan, study-aid loan, house loan, automobile loan, company operation loan; with the above embodiment, the loan risk type with higher probability can be added to the loan risk type set of the loan customer.
In one embodiment, as shown in fig. 8, the block chain-based loan risk prediction method provided in the embodiment of the present invention may further include the following steps:
s801, acquiring historical loan risk data of each loan institution;
and S802, training different machine learning models according to the historical loan risk data of each loan institution to obtain a plurality of risk prediction models corresponding to each loan institution.
In the embodiment of the invention, the risk prediction model is trained by utilizing the historical loan risk data of each loan institution, so that the time consumption of the model training process can be shortened, different machine learning models are trained, and more risk prediction models can be obtained.
Since the risk prediction models of the loan institutions are shared, in order to prevent the model parameters from being tampered, further, in an embodiment, as shown in fig. 8, the method for predicting the loan risk based on the block chain provided in the embodiment of the present invention may further include the following steps:
and S803, uploading the plurality of risk prediction models corresponding to each loan institution to a block chain network.
Based on the same inventive concept, the embodiment of the present invention further provides a loan risk prediction device based on a block chain, as described in the following embodiments. Because the principle of solving the problems of the device is similar to the block chain-based loan risk prediction method, the implementation of the device can refer to the implementation of the block chain-based loan risk prediction method, and repeated details are omitted.
Fig. 9 is a schematic diagram of a block chain-based loan risk prediction apparatus according to an embodiment of the present invention, as shown in fig. 9, the apparatus includes: the system comprises a loan application module 901, a key loan element information determination module 902, a key loan element evaluation result acquisition module 903, a client loan risk type determination module 904, a risk prediction model selection module 905 and a risk prediction module 906.
The loan application module 901 is used for receiving a loan application request of a loan client;
a key loan element information determining module 902, configured to obtain, according to the loan application request, key loan element information submitted by the loan customer;
a key loan element evaluation result obtaining module 903, configured to compare the key loan element information with client information of a client with a known loan risk, and determine, according to a comparison result, a key loan element evaluation result corresponding to the key loan element information, where the client information of the client with the known loan risk includes: knowing key loan element information and key loan element evaluation results of loan risk customers;
a client loan risk type determination module 904, configured to determine a loan risk type set of the loan client according to the key loan element evaluation result, where the loan risk type set includes one or more loan risk types of the loan client;
a risk prediction model selection module 905, configured to search, according to a loan risk type set of a loan customer of the loan customer, a risk prediction model corresponding to the loan risk type from a risk prediction model set, where the risk prediction model set includes: the loan institutions upload a plurality of risk prediction models through a block chain network;
and the risk prediction module 906 is used for performing risk prediction on the loan client based on the searched one or more risk prediction models to obtain a risk prediction result of the loan client.
In one embodiment, as shown in fig. 10, in the device for predicting loan risk based on a block chain provided in the embodiment of the present invention, the risk prediction module 906 includes: a client information acquisition unit 9061, a risk prediction unit 9062, and a risk prediction result integration unit 9063.
The client information acquiring unit 9061 is configured to acquire client information of a loan client; the risk prediction unit 9062 is used for inputting the customer information of the loan customers into the searched risk prediction models to obtain risk prediction results of the risk prediction models; and the risk prediction result integration unit 9063 is used for generating a risk prediction result of the loan customer according to the risk prediction result of each risk prediction model.
In this embodiment, the risk prediction result integration unit 9063 is further configured to: acquiring performance evaluation results of each risk prediction model; determining the weight coefficient of each risk prediction model according to the performance evaluation result of each risk prediction model; and generating a risk prediction result of the loan customer according to the weight coefficient and the risk prediction result of each risk prediction model.
Optionally, the risk prediction result integration unit 9063 is further configured to: selecting a target integrated algorithm model to be adopted by each loan structure from a plurality of integrated algorithm models prestored on the blockchain network by using an intelligent contract prestored on the blockchain network; integrating the risk prediction results of the risk prediction models by using the selected target integration algorithm model to obtain the risk prediction result of the loan customer; and pushing the risk prediction result of the loan client to each loan structure.
In one embodiment, as shown in fig. 10, the device for predicting loan risk based on a block chain provided in an embodiment of the present invention further includes: a risk prediction result uplink module 907 for uploading the risk prediction result of the loan client to the block chain network; and the loan application service handling module 908 is used for executing the loan application service of the loan customer based on the risk prediction result of the loan customer stored on the block chain network, wherein the loan application service of the loan customer is refused to be executed under the condition that the risk prediction result corresponding to any risk type of the loan customer exceeds a preset risk condition.
In one embodiment, as shown in fig. 10, the device for predicting loan risk based on a block chain provided in an embodiment of the present invention further includes: a business data uplink module 909, configured to obtain business data of the loan application business; and uploading the service data of the loan application service to the block chain network.
In one embodiment, as shown in fig. 10, the device for predicting loan risk based on a block chain provided in an embodiment of the present invention further includes: the 5G message communication module 910 is configured to receive a loan application request sent by a loan client through a 5G message; and determining the loan amount information of the loan client according to the risk prediction result of the loan client, and sending the loan amount information of the loan client to the loan client through a 5G message.
In one embodiment, as shown in fig. 10, the device for predicting loan risk based on a block chain provided in an embodiment of the present invention further includes: a similar customer determination module 911, configured to determine similar customers of the loan customer based on a pre-constructed customer relationship knowledge graph; in this embodiment, the client loan risk type determination module 904 is further configured to add a loan risk type of a similar client to the loan risk type set of the loan client.
In one embodiment, the customer loan risk type determination module 904 is further configured to: obtaining loan risk data corresponding to each type of loan stored on a block chain network; calculating the loan risk type probability corresponding to each type of loan type by using an intelligent contract pre-stored on a block chain network; storing the loan risk types with the probability higher than a preset threshold value and the corresponding loan types in a block chain network in an associated manner; and according to the loan type of the loan customer, inquiring the corresponding loan risk type from the block chain network, and adding the loan risk type into the loan risk type set of the loan customer.
In one embodiment, as shown in fig. 10, the device for predicting loan risk based on a block chain provided in an embodiment of the present invention further includes: a machine learning module 912 for obtaining historical loan risk data for each loan institution; and training different machine learning models according to the historical loan risk data of each loan institution to obtain a plurality of risk prediction models corresponding to each loan institution.
In one embodiment, as shown in fig. 10, the device for predicting loan risk based on a block chain provided in an embodiment of the present invention further includes: the risk prediction model linking module 913 is configured to upload the multiple risk prediction models corresponding to each loan institution to the block link network.
Based on the same inventive concept, the embodiment of the present invention further provides a computer device, so as to solve the technical problems of long time consumption in the training process and low model accuracy of the existing loan risk prediction method by using the artificial intelligence technology, as shown in fig. 11, fig. 11 is a schematic diagram of the computer device provided in the embodiment of the present invention, as shown in fig. 11, the computer device 11 includes a memory 111, a processor 112, and a computer program stored in the memory 111 and operable on the processor 112, and when the processor 112 executes the computer program, the loan risk prediction method based on the block chain is implemented.
Based on the same inventive concept, the embodiment of the invention also provides a computer readable storage medium, which is used for solving the technical problems of long time consumption in the training process and low model accuracy rate of the conventional loan risk prediction method by means of an artificial intelligence technology.
In summary, according to the loan risk prediction method based on the block chain, the device, the computer equipment, and the computer-readable storage medium provided in the embodiments of the present invention, the risk prediction models uploaded by the loan institutions are received through the block chain network to form a risk prediction model set, after receiving a loan application request from a loan customer, a loan risk type set of the loan customer is determined according to the loan application request from the loan customer, and then a risk prediction model corresponding to the loan risk type is searched from the risk prediction model set according to each loan risk type of the loan customer in the loan risk type set, and finally, based on one or more found risk prediction models, a risk prediction result of the loan customer is obtained.
Compared with the technical scheme that a model is directly trained to carry out risk prediction on loan clients in the prior art, in the embodiment of the invention, each loan institution respectively trains a plurality of risk prediction models, selects the risk prediction model corresponding to the loan risk type of the current loan application request of the loan client from the plurality of risk prediction models, and carries out loan risk prediction on the loan clients, thereby not only shortening the time consumption of the model training process, but also improving the accuracy of the whole model prediction.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above-mentioned embodiments are intended to illustrate the objects, technical solutions and advantages of the present invention in further detail, and it should be understood that the above-mentioned embodiments are only exemplary embodiments of the present invention, and are not intended to limit the scope of the present invention, and any modifications, equivalent substitutions, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (22)
1. A loan risk prediction method based on a block chain is characterized by comprising the following steps:
receiving a loan application request of a loan client;
obtaining key loan element information submitted by the loan client according to the loan application request;
comparing the key loan element information with client information of clients with known loan risks, and determining a key loan element evaluation result corresponding to the key loan element information according to the comparison result, wherein the client information of the clients with known loan risks comprises: knowing key loan element information and key loan element evaluation results of loan risk customers;
determining a loan risk type set of the loan customer according to the key loan element evaluation result, wherein the loan risk type set comprises one or more loan risk types of the loan customer;
according to the loan risk type set of the loan client, searching a risk prediction model corresponding to the loan risk type from a risk prediction model set, wherein the risk prediction model set comprises: the loan institutions upload a plurality of risk prediction models through a block chain network;
and performing risk prediction on the loan client based on the one or more searched risk prediction models to obtain a risk prediction result of the loan client.
2. The method of claim 1, wherein performing risk prediction for the loan customer based on the one or more risk prediction models found to obtain a risk prediction result for the loan customer comprises:
acquiring customer information of the loan customer;
inputting the customer information of the loan customer into each searched risk prediction model to obtain a risk prediction result of each risk prediction model;
and generating a risk prediction result of the loan client according to the risk prediction result of each risk prediction model.
3. The method of claim 2, wherein generating the loan client's risk prediction based on the risk prediction results of each risk prediction model comprises:
acquiring performance evaluation results of each risk prediction model;
determining the weight coefficient of each risk prediction model according to the performance evaluation result of each risk prediction model;
and generating a risk prediction result of the loan client according to the weight coefficient and the risk prediction result of each risk prediction model.
4. The method of claim 2, wherein generating the loan client's risk prediction based on the risk prediction results of each risk prediction model comprises:
selecting a target integrated algorithm model to be adopted by each loan structure from a plurality of integrated algorithm models prestored on the blockchain network by using an intelligent contract prestored on the blockchain network;
integrating the risk prediction results of the risk prediction models by using the selected target integration algorithm model to obtain the risk prediction result of the loan client;
and pushing the risk prediction result of the loan customer to each loan structure.
5. The method of claim 1, wherein after performing a risk prediction for the loan customer based on the one or more risk prediction models found, resulting in a risk prediction result for the loan customer, the method further comprises:
uploading the risk prediction result of the loan client to a block chain network;
and executing the loan application business of the loan customer based on the risk prediction result of the loan customer stored on the block chain network, wherein the loan application business of the loan customer is refused to be executed under the condition that the risk prediction result corresponding to any risk type of the loan customer exceeds a preset risk condition.
6. The method of claim 5, wherein after performing the loan application service for the loan customer based on the risk prediction result for the loan customer stored on the blockchain network, the method further comprises:
acquiring service data of the loan application service;
and uploading the service data of the loan application service to a block chain network.
7. The method of claim 1, wherein receiving a loan application request from a loan customer comprises:
receiving a loan application request sent by a loan client through a 5G message;
after the loan client carries out risk prediction based on the one or more searched risk prediction models and obtains the risk prediction result of the loan client, the method further comprises the following steps:
determining loan amount information of the loan client according to the risk prediction result of the loan client;
and sending the loan amount information of the loan client to the loan client through a 5G message.
8. The method of claim 1, wherein after finding a risk prediction model corresponding to a loan risk type from a set of risk prediction models based on a set of loan risk types for a loan customer of the loan customer, the method further comprises:
determining similar customers of the loan customers based on a pre-constructed customer relationship knowledge graph;
adding the loan risk types of similar clients to the loan risk type set of the loan clients.
9. The method of claim 1, wherein after finding a risk prediction model corresponding to a loan risk type from a set of risk prediction models based on a set of loan risk types for a loan customer of the loan customer, the method further comprises:
obtaining loan risk data corresponding to each type of loan stored on a block chain network;
calculating the loan risk type probability corresponding to each type of loan type by using an intelligent contract pre-stored on a block chain network;
storing the loan risk types with the probability higher than a preset threshold value and the corresponding loan types in a block chain network in an associated manner;
and inquiring the corresponding loan risk type from the block chain network according to the loan type of the loan customer, and adding the corresponding loan risk type into the loan risk type set of the loan customer.
10. The method of any of claims 1 to 9, further comprising:
acquiring historical loan risk data of each loan institution;
training different machine learning models according to historical loan risk data of each loan institution to obtain a plurality of risk prediction models corresponding to each loan institution;
and uploading a plurality of risk prediction models corresponding to each loan institution to the block chain network.
11. A loan risk prediction apparatus based on a block chain, comprising:
the loan application module is used for receiving a loan application request of a loan client;
the key loan element information determining module is used for acquiring key loan element information submitted by the loan client according to the loan application request;
a key loan element evaluation result obtaining module, configured to compare the key loan element information with client information of a client with a known loan risk, and determine, according to a comparison result, a key loan element evaluation result corresponding to the key loan element information, where the client information of the client with the known loan risk includes: knowing key loan element information and key loan element evaluation results of loan risk customers;
the client loan risk type determining module is used for determining a loan risk type set of the loan client according to the key loan element evaluation result, wherein the loan risk type set comprises one or more loan risk types of the loan client;
the risk prediction model selection module is used for searching a risk prediction model corresponding to the loan risk type from a risk prediction model set according to the loan risk type set of the loan customer, wherein the risk prediction model set comprises: the loan institutions upload a plurality of risk prediction models through a block chain network;
and the risk prediction module is used for performing risk prediction on the loan client based on the searched one or more risk prediction models to obtain a risk prediction result of the loan client.
12. The apparatus of claim 11, wherein the risk prediction module comprises:
a client information acquisition unit for acquiring client information of the loan client;
the risk prediction unit is used for inputting the customer information of the loan customer into each searched risk prediction model to obtain a risk prediction result of each risk prediction model;
and the risk prediction result integration unit is used for generating the risk prediction result of the loan client according to the risk prediction result of each risk prediction model.
13. The apparatus of claim 12, wherein the risk prediction results integration unit is further to:
acquiring performance evaluation results of each risk prediction model;
determining the weight coefficient of each risk prediction model according to the performance evaluation result of each risk prediction model;
and generating a risk prediction result of the loan client according to the weight coefficient and the risk prediction result of each risk prediction model.
14. The apparatus of claim 12, wherein the risk prediction results integration unit is further to:
selecting a target integrated algorithm model to be adopted by each loan structure from a plurality of integrated algorithm models prestored on the blockchain network by using an intelligent contract prestored on the blockchain network;
integrating the risk prediction results of the risk prediction models by using the selected target integration algorithm model to obtain the risk prediction result of the loan client;
and pushing the risk prediction result of the loan customer to each loan structure.
15. The apparatus of claim 11, wherein the apparatus further comprises:
the risk prediction result uplink module is used for uploading the risk prediction result of the loan client to a block chain network;
and the loan application service handling module is used for executing the loan application service of the loan client based on the risk prediction result of the loan client stored on the block chain network, wherein the loan application service of the loan client is refused to be executed under the condition that the risk prediction result corresponding to any risk type of the loan client exceeds a preset risk condition.
16. The apparatus of claim 15, wherein after performing the loan application service of the loan customer based on the risk prediction result of the loan customer stored on the blockchain network, the apparatus further comprises:
acquiring service data of the loan application service;
and uploading the service data of the loan application service to a block chain network.
17. The apparatus of claim 11, wherein the apparatus further comprises:
the 5G message communication module is used for receiving a loan application request sent by a loan client through a 5G message; and determining the loan amount information of the loan client according to the risk prediction result of the loan client, and sending the loan amount information of the loan client to the loan client through a 5G message.
18. The apparatus of claim 11, wherein the apparatus further comprises:
the similar client determining module is used for determining similar clients of the loan clients based on a client relationship knowledge graph which is constructed in advance;
the client loan risk type determination module is further used for adding loan risk types of similar clients to the loan risk type set of the loan clients.
19. The apparatus of claim 11, wherein the customer loan risk type determination module is further to:
obtaining loan risk data corresponding to each type of loan stored on a block chain network;
calculating the loan risk type probability corresponding to each type of loan type by using an intelligent contract pre-stored on a block chain network;
storing the loan risk types with the probability higher than a preset threshold value and the corresponding loan types in a block chain network in an associated manner;
and inquiring the corresponding loan risk type from the block chain network according to the loan type of the loan customer, and adding the corresponding loan risk type into the loan risk type set of the loan customer.
20. The apparatus of any of claims 11 to 19, further comprising:
the machine learning module is used for acquiring historical loan risk data of each loan institution; training different machine learning models according to historical loan risk data of each loan institution to obtain a plurality of risk prediction models corresponding to each loan institution;
and the risk prediction model chaining module is used for uploading the plurality of risk prediction models corresponding to each loan institution to the block chain network.
21. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the computer program implements the block chain based loan risk prediction method of any one of claims 1 to 10.
22. A computer-readable storage medium storing a computer program for executing the block chain-based loan risk prediction method according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110768957.0A CN113436006A (en) | 2021-07-07 | 2021-07-07 | Loan risk prediction method and device based on block chain |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110768957.0A CN113436006A (en) | 2021-07-07 | 2021-07-07 | Loan risk prediction method and device based on block chain |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113436006A true CN113436006A (en) | 2021-09-24 |
Family
ID=77759540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110768957.0A Pending CN113436006A (en) | 2021-07-07 | 2021-07-07 | Loan risk prediction method and device based on block chain |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113436006A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113992429A (en) * | 2021-12-22 | 2022-01-28 | 支付宝(杭州)信息技术有限公司 | Event processing method, device and equipment |
| CN115187393A (en) * | 2022-09-14 | 2022-10-14 | 深圳市明源云科技有限公司 | Loan risk detection method and device, electronic equipment and readable storage medium |
-
2021
- 2021-07-07 CN CN202110768957.0A patent/CN113436006A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113992429A (en) * | 2021-12-22 | 2022-01-28 | 支付宝(杭州)信息技术有限公司 | Event processing method, device and equipment |
| CN113992429B (en) * | 2021-12-22 | 2022-04-29 | 支付宝(杭州)信息技术有限公司 | Event processing method, device and equipment |
| CN115187393A (en) * | 2022-09-14 | 2022-10-14 | 深圳市明源云科技有限公司 | Loan risk detection method and device, electronic equipment and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109922032B (en) | Method, device, equipment and storage medium for determining risk of logging in account | |
| TWI634492B (en) | Assessment method of risk, device, computer device and storage medium | |
| CN111667267B (en) | Block chain transaction risk identification method and device | |
| CN113435770A (en) | Transaction risk assessment method and device based on block chain | |
| WO2018103456A1 (en) | Method and apparatus for grouping communities on the basis of feature matching network, and electronic device | |
| CN111476662A (en) | Anti-money laundering identification method and device | |
| CN112733995B (en) | Method for training neural network, behavior detection method and behavior detection device | |
| CN110348978A (en) | The recognition methods of risk clique, device, equipment and the storage medium calculated based on figure | |
| CN113436006A (en) | Loan risk prediction method and device based on block chain | |
| CN111008335B (en) | Information processing method, device, equipment and storage medium | |
| CN112070615A (en) | Financial product recommendation method and device based on knowledge graph | |
| CN110555148B (en) | User behavior evaluation method, computing device and storage medium | |
| CN112799708A (en) | Method and system for jointly updating business model | |
| US11714917B2 (en) | Systems and methods for anonymizing sensitive data and simulating accelerated schedule parameters using the anonymized data | |
| WO2018193085A1 (en) | System and method for managing fraud detection in a financial transaction system | |
| CN113689270B (en) | Method for determining black product device, electronic device, storage medium, and program product | |
| CN109165947B (en) | Account information determination method and device and server | |
| CN113450158A (en) | Bank activity information pushing method and device | |
| CN110060157B (en) | Reputation evaluation method and system | |
| CN113159926A (en) | Loan transaction repayment date determination method and device | |
| CN114092216A (en) | Enterprise credit rating method, apparatus, computer device and storage medium | |
| CN113469668A (en) | Block chain-based method and device for limiting public customer transaction | |
| CN115204888A (en) | Target account identification method and device, storage medium and electronic equipment | |
| CN112766935A (en) | Method, device, computing equipment and medium for processing bill service | |
| TWI657393B (en) | Marketing customer group prediction system and method |
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 |