WO2020077888A1

WO2020077888A1 - Method and apparatus for calculating credit score of loan user, and computer device

Info

Publication number: WO2020077888A1
Application number: PCT/CN2019/070361
Authority: WO
Inventors: 龙撷宇; 张敏; 徐志成
Original assignee: 深圳壹账通智能科技有限公司
Priority date: 2018-10-16
Filing date: 2019-01-04
Publication date: 2020-04-23
Also published as: CN109584037A

Abstract

Provided are a method and apparatus for calculating a credit score of a loan user, and a computer device. The method comprises: obtaining loan information filled by the loan user, credit data of the loan user, transaction data of each payment card owned by the loan user, utilities and services payments data, and insurance policy data (S110); generating a feature vector of the loan user according to the loan information, the credit data, the transaction data, the utilities and services payments data, and the insurance policy data (S120); and inputting the feature vector of the loan user to a pre-constructed scoring model, so as to obtain a credit score of the loan user (S130). The method reduces the probability of calculation errors of credit scores of a loan user.

Description

Calculation method, device and computer equipment for loan user credit score

This application requires the priority of the Chinese patent application filed on October 16, 2018 in the Chinese Patent Office with the application number 201811204578.3 and the invention titled "Calculation Method, Device and Computer Equipment for Credit Scores of Loan Users". Incorporated in this application.

Technical field

This application relates to the field of computer technology. Specifically, this application relates to a method, apparatus, and computer equipment for calculating credit scores of loan users.

Background technique

The score card technology is a large-scale automated processing method that is centered on computer technology and characterized by replacing manpower. It is a revolutionary measure currently adopted by commercial banks that can effectively control risks, reduce the number of business personnel, and greatly improve the efficiency of approval. One. There are many occasions for the use of scorecards, including marketing scoring, application scoring, behavioral scoring, and collection and recovery scoring, etc. Loan company scoring cards are generally used for customer identification and loan loan amount assessment.

The inventor realizes that the current loan company basically uses the user to fill in the information when scoring with the scorecard technology, and pulls the credit information of the PBC for evaluation, and the result is obtained after one evaluation, but the probability of error in this way is relatively high.

Summary of the invention

In view of the shortcomings of the existing methods, this application proposes a method, device and computer equipment for calculating the credit score of a loan user, so as to reduce the probability of error in calculating the credit score of the loan user.

According to the first aspect, the embodiments of the present application provide a method for calculating the credit score of a loan user, including:

Obtain the loan information filled in by the loan user, the credit information of the loan user, the transaction data of each payment card held by the loan user, life payment data and policy data;

Generate a feature vector of the loan user according to the loan information, the credit information data, the transaction data, the living payment data and the policy data;

The feature vector of the loan user is input into a pre-built scoring model to obtain the credit score result of the loan user.

According to the second aspect, the embodiments of the present application also provide a credit score calculation device for loan users, including:

A data acquisition module for acquiring loan information filled in by the loan user, credit information of the loan user, transaction data of various payment cards held by the loan user, living payment data and policy data;

A feature vector generating module, configured to generate a feature vector of the loan user based on the loan information, the credit data, the transaction data, the living payment data and the policy data;

The evaluation module is used to input the feature vector of the loan user into a pre-built scoring model to obtain the credit score result of the loan user.

According to a third aspect, an embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, which when executed by a processor implements the calculation of any of the above-mentioned loan user credit scores method.

According to a fourth aspect, an embodiment of the present application further provides a computer device, the computer device includes:

One or more processors;

Storage device for storing one or more programs,

When the one or more programs are executed by the one or more processors, the one or more processors implement any one of the calculation methods for credit scores of loan users described above.

The above method, device and computer equipment for calculating the credit score of a loan user obtains the loan information and credit data of the loan user filled in by the loan user, as well as the transaction data, life payment data and policy data of each payment card held by the loan user In combination with the scoring model, the user ’s pre-loan scoring card score can be updated in real time, reducing the probability of scoring errors once. In addition, user transactions can be tracked in real time to prevent malicious transactions caused by users' malicious transactions before the end of the approval process, and they can also discover potential customers based on real-time score card scores.

BRIEF DESCRIPTION

The above-mentioned and / or additional aspects and advantages of this application will become apparent and easy to understand from the following description of the embodiments in conjunction with the accompanying drawings, in which:

1 is a schematic flowchart of a method for calculating a credit score of a loan user according to an embodiment of the application;

2 is a schematic structural diagram of a loan user credit score calculation device according to an embodiment of the application;

FIG. 3 is a schematic structural diagram of a computer device according to an embodiment of the present application.

detailed description

The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the drawings, in which the same or similar reference numerals indicate the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary, and are only used to explain the present application, and cannot be construed as limiting the present application.

Those skilled in the art can understand that unless specifically stated, the singular forms "a", "an", "said" and "the" used herein may also include the plural forms. It should be further understood that the word "comprising" used in the specification of this application refers to the presence of the described features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components, and / or their groups.

Those skilled in the art can understand that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those of ordinary skill in the art to which this application belongs. It should also be understood that terms such as those defined in a general dictionary should be understood to have a meaning consistent with the meaning in the context of the prior art, and unless specifically defined as here, it would not be idealized or overly The formal meaning is explained.

As shown in FIG. 1, in one embodiment, a method for calculating the credit score of a loan user includes:

S110. Obtain the loan information filled in by the loan user, the credit information of the loan user, the transaction data of each payment card held by the loan user, life payment data and policy data.

The loan information filled out by the loan user and the credit information of the loan user can be used as fixed input parameters, and the transaction data, life consumption data, and policy data of each payment card can be used as input parameters for real-time changes. If the loan user is a user who has submitted a loan application, the information filled in by the loan user refers to the information filled in when the user submits the loan application. If the loan user is a user who has not yet submitted a loan application, the information filled in by the loan user can be replaced with 0 or other specified characters. Optionally, payment cards include physical cards such as bank cards and credit cards, and may also include virtual cards such as WeChat and Alipay. Taking bank cards and credit cards as an example, you can use the online banking to extract bank card income and expenditure flow, credit card bills and flow, credit card bills and flow refer to the payment, repayment time, repayment records, etc. in addition to the PBOC credit record . Living consumption data refers to living bills, such as the location and amount of water, electricity and coal payment in the living bill. Policy data refers to the sum insured, premiums, insured period, insured items, time of insured, etc. in the policy. The insurance policy is the insurance policy, which refers to the written certificate of the insurance contract signed between the insurer and the insured.

The loan information filled out by the loan user and the credit information of the loan user can be obtained from the PBOC credit information system. The transaction data of the physical card in each payment card held by the loan user can be obtained from the business system of each bank, and the transaction data of the virtual card in each payment card held by the loan user can be obtained from the commonly used payment APP (Application, application) Obtained from the back-end system, payment apps include WeChat, Alipay, Apple Pay (Apple Pay) and so on. Life payment data can be obtained from the business system of each bank and the commonly used payment APP back-end system that can make life payment. The policy data can be obtained from various insurance systems, for example, from the Ping An Insurance system.

S120. Generate a feature vector of the loan user according to the loan information, the credit reference data, the transaction data, the living payment data, and the policy data.

In order to realize the credit evaluation of the loan user, it is necessary to process the acquired data and generate a feature vector of the loan user. The feature vectors of loan users are used to characterize the unique attributes of loan users. There are many ways to generate the feature vector of the loan user. For example, in one embodiment, the generation based on the loan information, the credit data, the transaction data, the living payment data and the policy data The feature vector of the loan user includes:

S121. Classify the loan information, the credit information data, the transaction data, the living payment data, and the policy data to obtain character type data and numeric type data.

Character type data refers to text data type data without computing power, which includes Chinese characters, English characters, numeric characters and other ASC Ⅱ (American Standard Code for Information Interchange) characters. Numerical data (metric data) is an observation value measured on a digital scale, and the result is expressed as a specific numerical value.

In one embodiment, the loan information, the credit information data, the transaction data, the living payment data and the policy data are classified to obtain character type data and numeric type data. The method includes: deleting duplicate data in the transaction data, the living payment data and the order data. After obtaining transaction data, life payment data and the order data, it is also necessary to preprocess the above data to remove duplicate data. For example, if the user pays for life through a bank card, the transaction data of the bank card includes this information, life The consumption data also includes this item of information, and only one item of information may be retained.

S122. Generate a first feature vector of the character type data.

There are many ways to generate the first feature vector, which will be described below in conjunction with two embodiments. It should be understood that the present application is not limited to the following manner of generating the first feature vector.

In one embodiment, the generating the first feature vector of the character type data includes: performing one-hot encoding on the character type data to generate the first feature vector of the character type data. One hot encoding is a process of converting categorical variables into a form that is easy to use by machine learning algorithms. The specific encoding method can be implemented according to the existing methods in the prior art.

In another embodiment, the generating the first feature vector of the character type data includes: performing hash calculation on the character type data to generate the first feature vector of the character type data. Hash refers to transforming an input of any length into a fixed-length output through a hash algorithm, and the output is a hash value. By performing hash calculation on the character type data, the first feature vector of the character type data can be obtained.

S123. Generate a second feature vector of the numeric data.

There are many ways to generate the second feature vector. For example, in one embodiment, the generating the second feature vector of the numeric type data includes: creating an initial feature vector; and sequentially placing the numeric type data in a preset order Fill in the initial feature vector to obtain the second feature vector of the numeric type data. The initial feature vector is an empty vector, and the size can be determined according to the number of acquired numeric type data. The preset order can be set according to the actual needs of the user, for example, in accordance with the order of loan information, credit data, transaction data, living payment data and policy data, the extracted corresponding numerical type data are sequentially filled into the initial feature vector, then The second feature vector of numeric data can be obtained.

S124: Combine the first feature vector and the second feature vector to generate a feature vector of the loan user.

The first feature vector and the second feature vector are combined to generate the loan user's feature vector, which is the input feature of the scoring model. The merging method may be that the first feature vector is in front, the second feature vector is in the back, or the second feature vector is in front, and the first feature vector is in the back, or other merging methods may be used.

S130. Input the feature vector of the loan user into a pre-built scoring model to obtain the credit score result of the loan user.

The training model is used to train the scoring model to obtain a trained scoring model. The training sample includes loan information and credit data filled in by each sample user, as well as transaction data, life consumption data, and policy data of each payment card held by the sample user.

In one embodiment, the scoring model is:

Wherein, Y is a credit score result, a1, a2 ..., an are coefficients, and X1, X2 ... Xn are various parameters in the feature vector of the loan user.

Optionally, the scoring model may also be a logistic regression model, a neural network model, a decision tree model, and so on.

Enter the loan user's feature vector into the trained scoring model to get the user's credit score result.

In one embodiment, the obtaining a credit score result of the loan user, and then, further includes: according to the credit score result, issuing a payment corresponding to the credit score result to the loan user. For a user who submits a loan application, the loan company can determine whether to issue a loan to the user and the amount of the loan based on the credit score result.

In addition, for users who have not submitted a loan application, the loan company intelligently recommends the corresponding amount of loan products based on the credit score result, so as to tap potential customers.

S1. Obtain transaction data, life payment data and policy data of each payment card held by the user.

Since the user has not yet submitted the loan application, the loan information and credit information of the user can be replaced by 0 or other specified characters. The transaction data of the physical card in each payment card held by the user can be obtained from the business system of each bank, and the transaction data of the virtual card in each payment card held by the user can be obtained from the commonly used payment APP background system. Life payment data can be obtained from the business system of each bank and the commonly used payment APP back-end system that can make life payment. Policy data can be obtained from various insurance systems.

S2. Generate a user's feature vector based on loan information, credit information data, the transaction data, the living payment data, and the policy data.

The specific implementation of step S2 is the same as step S120, except that the loan information and credit data in S2 are all replaced with 0 or other designated characters. If the loan information and credit data in this step are all replaced with 0 or other numbers, the loan information and credit data are classified into numeric type data. If the loan information and credit information in this step are all replaced with a or other characters, the loan information and credit information are classified into character type data.

S3. Input the user's feature vector into the pre-built scoring model to obtain the user's credit score result.

The scoring model in step S3 adopts the same scoring model as in step S130. The user's feature vector is input into a pre-built scoring model, and the user's feature vector is calculated by the scoring model to output the user's credit score result.

S4. According to the user's credit score result, recommend a loan product with a corresponding amount.

The loan amount corresponding to each loan product is generally different. Take the loan products of Ping An Pratt & Whitney as an example. The small loan products include i-loan, the maximum loan amount is 30,000, and the large loan products include the home loan. , Zhai e business loan line is 150,000 to 5 million. The correspondence between the range of credit score results and loan products can be set in advance. The lower the general credit score result, the lower the loan amount corresponding to the loan product. After obtaining the user's credit score result, determine the range of the credit score result, and then find the loan product to be recommended.

If there is only one loan product to be recommended, the loan product can be directly pushed to the user via SMS or other instant messaging software. If there are multiple loan products to be recommended, you can push multiple loan products directly to users through SMS or other instant messaging software, or you can further screen multiple loan products and choose one from multiple loan products. User loan products. There are many ways to choose a loan product from multiple loan products. For example, two loan products have the same loan amount, but one loan product needs a mortgage to apply, and the other loan product can apply without a mortgage to obtain user data. It is found that the user does not have a mortgage and there is no real estate under his name, so he can only recommend loan products that can be applied without a mortgage to the user to improve the effectiveness of the recommendation.

Based on the same inventive concept, this application also provides a credit score calculation device for loan users. The specific implementation of the device of this application will be described in detail below with reference to the drawings.

As shown in FIG. 2, in one embodiment, a credit score calculation device for loan users includes:

The data obtaining module 210 is used to obtain loan information filled in by the loan user, credit information of the loan user, transaction data of each payment card held by the loan user, living payment data and policy data;

The feature vector generating module 220 is configured to generate a feature vector of the loan user based on the loan information, the credit information data, the transaction data, the living payment data and the policy data;

The evaluation module 230 is used to input the feature vector of the loan user into a pre-built scoring model to obtain the credit score result of the loan user.

In one embodiment, it further includes a payment issuance module connected to the evaluation module 230, and the payment issuance module is used to issue payment corresponding to the credit scoring result to the loan user according to the credit scoring result.

In one embodiment, the feature vector generation module 220 includes:

A classification unit for classifying the loan information, the credit information data, the transaction data, the living payment data and the policy data to obtain character type data and numeric type data;

A first feature vector generating unit, configured to generate a first feature vector of the character type data;

A second feature vector generating unit, configured to generate a second feature vector of the numeric type data;

The loan user feature vector generating unit is configured to combine the first feature vector and the second feature vector to generate the loan user feature vector.

In one embodiment, the classification unit classifies the loan information, the credit data, the transaction data, the living payment data, and the policy data to obtain character type data and numeric type data. , Is also used to delete duplicate data in the transaction data, the living payment data and the order data.

In one embodiment, the first feature vector generating unit performs one-hot encoding on the character type data to generate a first feature vector of the character type data.

In one embodiment, the first feature vector generating unit performs hash calculation on the character type data to generate a first feature vector of the character type data.

In one embodiment, the second feature vector generating unit creates an initial feature vector; the numeric type data is sequentially filled into the initial feature vector in a preset order to obtain a second feature vector of the numeric type data .

In one embodiment, the scoring model is:

An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, any method for calculating a credit score of a loan user described above is implemented. The storage medium includes, but is not limited to, any type of disk (including floppy disk, hard disk, optical disk, CD-ROM, and magneto-optical disk), ROM (Read-Only Memory, read-only memory), RAM (Random Access Memory, immediately Memory), EPROM (Erasable Programmable Read-Only Memory, erasable programmable read-only memory), EEPROM (Electrically Erasable Programmable Read-Only Memory, electrically erasable programmable read-only memory), flash memory, magnetic cards or light cards. That is, a storage medium includes any medium that stores or transmits information in a readable form by a device (eg, a computer). It can be read-only memory, magnetic disk or optical disk.

An embodiment of the present application also provides a computer device. The computer device includes:

One or more processors;

Storage device for storing one or more programs,

3 is a schematic structural diagram of a computer device of the present application, including a processor 320, a storage device 330, an input unit 340, a display unit 350, and other devices. Those skilled in the art may understand that the structural device shown in FIG. 3 does not constitute a limitation on all computer equipment, and may include more or less components than those illustrated, or combine certain components. The storage device 330 may be used to store the application program 310 and each functional module, and the processor 320 runs the application program 310 stored in the storage device 330 to execute various functional applications and data processing of the device. The storage device 330 may be an internal memory or an external memory, or include both internal and external memory. The internal memory may include read-only memory, programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), flash memory, or random access memory. The external storage can include hard disks, floppy disks, ZIP disks, U disks, magnetic tapes, etc. The storage devices disclosed in this application include but are not limited to these types of storage devices. The storage device 330 disclosed in this application is only an example and not a limitation.

The input unit 340 is used to receive input of a signal, and receive loan information filled in by a loan user, credit information of the loan user, transaction data of each payment card held by the loan user, life payment data, and policy data. The input unit 340 may include a touch panel and other input devices. The touch panel can collect the user's touch operations on or near it (such as the user's operation on the touch panel or near the touch panel using any suitable objects or accessories such as fingers, stylus, etc.), and according to the preset The program drives the corresponding connection device; other input devices may include but are not limited to one or more of a physical keyboard, function keys (such as playback control keys, switch keys, etc.), trackball, mouse, joystick, etc. The display unit 350 may be used to display information input by the user or information provided to the user and various menus of the computer device. The display unit 350 may take the form of a liquid crystal display, an organic light emitting diode, or the like. The processor 320 is the control center of the computer equipment, connects various parts of the entire computer with various interfaces and lines, runs or executes the software programs and / or modules stored in the storage device 330, and calls the data stored in the storage device , Perform various functions and process data.

In an embodiment, the computer device includes one or more processors 320, and one or more storage devices 330, and one or more application programs 310, wherein the one or more application programs 310 are stored in the storage device 330 It is configured to be executed by the one or more processors 320, and the one or more application programs 310 are configured to execute the method for calculating the credit score of the loan user described in the above embodiment.

The above credit user credit score calculation method, device and computer equipment, combined with various data and scoring models, can update the user ’s pre-loan score card score in real time, reduce the probability of an error in the score evaluation, and can track user transactions in real time to prevent users from ending the approval process Malicious transactions before lending cause bad debts, and you can also discover potential customers based on real-time score card scores.

It should be understood that although the steps in the flowchart of the drawings are displayed in order according to the arrows, the steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order limitation for the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the drawings may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but may be executed at different times, and the order of execution is also It is not necessarily carried out sequentially, but may be executed in turn or alternately with at least a part of other steps or sub-steps or stages of other steps.

It should be understood that the functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units may be integrated into one module. The above-mentioned integrated modules can be implemented in the form of hardware or software function modules.

The above is only part of the implementation of this application. It should be pointed out that for those of ordinary skill in the art, without departing from the principles of this application, a number of improvements and retouches can also be made. These improvements and retouches also It should be regarded as the scope of protection of this application.

Claims

A method for calculating the credit score of a loan user includes:

Obtain the loan information filled in by the loan user, the credit information of the loan user, the transaction data of each payment card held by the loan user, life payment data and policy data;

Generate a feature vector of the loan user according to the loan information, the credit information data, the transaction data, the living payment data and the policy data;

The feature vector of the loan user is input into a pre-built scoring model to obtain the credit score result of the loan user.
The method for calculating the credit score of a loan user according to claim 1, said obtaining the credit score result of the loan user, and thereafter, further comprising:

According to the credit scoring result, the loan user is issued a payment corresponding to the credit scoring result.
The method for calculating the credit score of a loan user according to claim 1, wherein the loan user is generated based on the loan information, the credit information data, the transaction data, the living payment data and the policy data Feature vectors, including:

Classify the loan information, the credit information data, the transaction data, the living payment data and the policy data to obtain character type data and numeric type data;

Generating a first feature vector of the character type data;

Generating a second feature vector of the numeric data;

The first feature vector and the second feature vector are combined to generate a feature vector of the loan user.
The method for calculating the credit score of a loan user according to claim 3, said classifying the loan information, the credit data, the transaction data, the living payment data and the policy data to obtain a character type Data and numeric data, before, also include:

Delete duplicate data in the transaction data, the living payment data and the order data.
The method for calculating the credit score of a loan user according to claim 3, the generating the first feature vector of the character type data includes:

Perform one-hot encoding on the character type data to generate a first feature vector of the character type data;

or,

Perform hash calculation on the character type data to generate a first feature vector of the character type data.
The method for calculating the credit score of a loan user according to claim 3, wherein the generating the second feature vector of the numerical data includes:

Create an initial feature vector;

The numeric type data is sequentially filled into the initial feature vector according to a preset order to obtain a second feature vector of the numeric type data.
The method for calculating the credit score of a loan user according to any one of claims 1 to 6, the scoring model is:

Wherein, Y is a credit score result, a1, a2 ..., an are coefficients, and X1, X2 ... Xn are various parameters in the feature vector of the loan user.
A loan user credit score calculation device, including:

A data acquisition module for acquiring loan information filled in by the loan user, credit information of the loan user, transaction data of various payment cards held by the loan user, living payment data and policy data;

A feature vector generating module, configured to generate a feature vector of the loan user based on the loan information, the credit data, the transaction data, the living payment data and the policy data;

The evaluation module is used to input the feature vector of the loan user into a pre-built scoring model to obtain the credit score result of the loan user.
A computer-readable non-volatile storage medium on which a computer program is stored. When the program is executed by a processor, a method for calculating a credit score of a loan user is implemented. The calculation method includes the following steps:

Obtain the loan information filled in by the loan user, the credit information of the loan user, the transaction data of each payment card held by the loan user, life payment data and policy data;

Generate a feature vector of the loan user according to the loan information, the credit information data, the transaction data, the living payment data and the policy data;

The feature vector of the loan user is input into a pre-built scoring model to obtain the credit score result of the loan user.
The computer-readable non-volatile storage medium according to claim 9, said obtaining the credit score result of the loan user, and thereafter, further comprising:

According to the credit scoring result, the loan user is issued a payment corresponding to the credit scoring result.
The computer-readable non-volatile storage medium according to claim 9, said to generate the said according to the loan information, the credit data, the transaction data, the living payment data and the policy data Feature vectors of loan users, including:

Classify the loan information, the credit information data, the transaction data, the living payment data and the policy data to obtain character type data and numeric type data;

Generating a first feature vector of the character type data;

Generating a second feature vector of the numeric data;

The first feature vector and the second feature vector are combined to generate a feature vector of the loan user.
The computer-readable non-volatile storage medium according to claim 11, the classification of the loan information, the credit data, the transaction data, the living payment data and the policy data is obtained Character type data and numeric type data, before, also include:

Delete duplicate data in the transaction data, the living payment data and the order data.
The computer-readable non-volatile storage medium of claim 11, the generating the first feature vector of the character type data includes:

Perform one-hot encoding on the character type data to generate a first feature vector of the character type data;

or,

Perform hash calculation on the character type data to generate a first feature vector of the character type data.
The computer-readable non-volatile storage medium of claim 11, the generating the second feature vector of the numeric type data includes:

Create an initial feature vector;

The numeric type data is sequentially filled into the initial feature vector according to a preset order to obtain a second feature vector of the numeric type data.
The computer-readable non-volatile storage medium according to claims 9-14, the scoring model is:

Wherein, Y is a credit score result, a1, a2 ..., an are coefficients, and X1, X2 ... Xn are various parameters in the feature vector of the loan user.
A computer device, the computer device includes:

One or more processors;

Storage device for storing one or more programs,

When the one or more programs are executed by the one or more processors, so that the one or more processors implement a method for calculating the credit score of a loan user, the calculation method includes the following steps:

Obtain the loan information filled in by the loan user, the credit information of the loan user, the transaction data of each payment card held by the loan user, living payment data and policy data

Generate a feature vector of the loan user according to the loan information, the credit information data, the transaction data, the living payment data and the policy data;

The feature vector of the loan user is input into a pre-built scoring model to obtain the credit score result of the loan user.
The computer device according to claim 16, said obtaining the credit score result of the loan user, and thereafter, further comprising:

According to the credit scoring result, the loan user is issued a payment corresponding to the credit scoring result.
The computer device according to claim 16, said generating a feature vector of the loan user based on the loan information, the credit data, the transaction data, the living payment data and the policy data, including :

Classify the loan information, the credit information data, the transaction data, the living payment data and the policy data to obtain character type data and numeric type data;

Generating a first feature vector of the character type data;

Generating a second feature vector of the numeric data;

The first feature vector and the second feature vector are combined to generate a feature vector of the loan user.
The computer device according to claim 18, said classifying the loan information, the credit data, the transaction data, the living payment data and the policy data to obtain character type data and numeric type data , Before, also included:

Delete duplicate data in the transaction data, the living payment data and the order data.
The computer device according to claim 18, the generating the first feature vector of the character type data comprises:

Perform one-hot encoding on the character type data to generate a first feature vector of the character type data;

or,

Perform hash calculation on the character type data to generate a first feature vector of the character type data.