CN114549178A

CN114549178A - Credit evaluation method, credit evaluation device, electronic device and medium

Info

Publication number: CN114549178A
Application number: CN202210168809.XA
Authority: CN
Inventors: 姜力新; 徐敏; 朱佳宁; 黄文卿
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2022-02-23
Filing date: 2022-02-23
Publication date: 2022-05-27

Abstract

The disclosure provides a credit rating method, which can be applied to the financial field or other fields. The credit evaluation method comprises the following steps: acquiring original indexes of a target to be evaluated and data of the original indexes, wherein the data of the original indexes comprise the weight and the score of each original index; carrying out dimensionality reduction processing on the original indexes and the data of the original indexes to obtain total evaluation indexes and data of the total evaluation indexes; and determining an evaluation score for evaluating the credit of the target to be evaluated based on the total evaluation index and the data of the total evaluation index. The disclosure also provides a credit rating device, apparatus, storage medium and program product.

Description

Credit evaluation method, credit evaluation device, electronic device and medium

Technical Field

The present disclosure relates to the field of finance, in particular to the field of risk management, and more particularly to a method, apparatus, device, medium, and program product for credit rating.

Background

Risk management is a main task for ensuring fund safety of a bank, and personal credit risk assessment is a key process for carrying out loan approval by the bank.

In the process of realizing the concept disclosed by the invention, the inventor finds that the number of client data indexes extracted in the current client evaluation process is large, the indexes are mutually related, the problems of index information redundancy, complex calculation process and low accuracy exist, and the objective reflection of the scoring condition of the client is not facilitated.

Disclosure of Invention

In view of the foregoing, the present disclosure provides a method, apparatus, device, medium, and program product for credit rating.

According to a first aspect of the present disclosure, there is provided a method for evaluating credit, including: acquiring original indexes of a target to be evaluated and data of the original indexes, wherein the data of the original indexes comprise the weight and the score of each original index; performing dimensionality reduction processing on the original indexes and the data of the original indexes to obtain total evaluation indexes and data of the total evaluation indexes; and determining an evaluation score for evaluating the credit of the target to be evaluated based on the total evaluation index and the data of the total evaluation index.

According to an embodiment of the present disclosure, the step of performing dimension reduction processing on the original index and the data of the original index includes: dividing the original index into N non-associated evaluation indexes and M candidate associated evaluation indexes, wherein M is more than or equal to 1, and N is more than or equal to 1; determining data of M candidate related evaluation indexes corresponding to the M candidate related evaluation indexes and determining data of N non-related evaluation indexes corresponding to the N non-related evaluation indexes in the data of the original indexes; performing principal component analysis on the M candidate relevance evaluation indexes and the data of the M candidate relevance evaluation indexes to obtain K relevance evaluation indexes and data of K relevance evaluation indexes, wherein K is less than M; obtaining a total evaluation index based on the K associated evaluation indexes and the N non-associated evaluation indexes; and obtaining data of a total evaluation index based on the data of the K related evaluation indexes and the data of the N non-related evaluation indexes.

According to an embodiment of the present disclosure, before the step of dividing the original index into N non-relevance-class evaluation indexes and M candidate relevance-class evaluation indexes, the method further includes: calculating the correlation information coefficient among all indexes of the original indexes; the step of dividing the original index into N non-associated evaluation indexes and M candidate associated evaluation indexes includes: and dividing the original indexes into N non-associated evaluation indexes and M candidate associated evaluation indexes based on the associated information coefficient.

According to an embodiment of the present disclosure, the determining an evaluation score for evaluating the credit of the target to be evaluated based on the total evaluation index and the data of the total evaluation index includes:

multiplying the weight and the score of each evaluation index in the data of the total evaluation index and the total evaluation index to obtain the contribution score of each evaluation index; and adding the contribution scores of all the evaluation indexes to determine an evaluation score for evaluating the credit of the target to be evaluated.

According to an embodiment of the present disclosure, before the step of calculating the correlation information coefficient between the indexes of the original indexes, the method further includes: preprocessing the original index, wherein the preprocessing comprises converting the attribute of the original index into a numerical type by using Laplace smoothing.

According to the embodiment of the disclosure, the step of acquiring the original index of the target to be evaluated and the data of the original index comprises the following steps: and obtaining external evaluation indexes and data of the external evaluation indexes by utilizing a longitudinal federal learning method, wherein the external evaluation indexes comprise at least one of credit investigation type evaluation indexes, social contact type evaluation indexes and internet type evaluation indexes.

A second aspect of the present disclosure provides an apparatus for evaluating credit, including: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring original indexes of a target to be evaluated and data of the original indexes, and the data of the original indexes comprise the weight and the score of each original index; the dimensionality reduction module is used for carrying out dimensionality reduction processing on the original indexes and the data of the original indexes to obtain total evaluation indexes and data of the total evaluation indexes; and the evaluation module is used for determining an evaluation score for evaluating the credit of the target to be evaluated based on the total evaluation index and the data of the total evaluation index.

A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the above-described method.

A fourth aspect of the present disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above-described method.

A fifth aspect of the disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the above method.

One or more of the embodiments described above have the following advantages or benefits: by dividing the total evaluation index into the relevance evaluation index and the non-relevance evaluation index, the redundancy of the evaluation index can be greatly reduced, the complexity of the calculation process is reduced, the accuracy of the credit evaluation is improved, and the objective reflection of the scoring condition of the credit of the client is facilitated.

Drawings

The foregoing and other objects, features and advantages of the disclosure will be apparent from the following description of embodiments of the disclosure, which proceeds with reference to the accompanying drawings, in which:

fig. 1 schematically illustrates an application scenario diagram of a method, apparatus, device, medium, and program product for credit rating according to an embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow chart of a method of credit rating according to an embodiment of the present disclosure;

FIG. 3 schematically shows a flow diagram of a dimension reduction process according to an embodiment of the disclosure;

fig. 4 schematically shows a block diagram of the structure of a credit rating apparatus according to an embodiment of the present disclosure; and

fig. 5 schematically shows a block diagram of an electronic device adapted to implement the method of credit rating according to an embodiment of the present disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is illustrative only and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. Moreover, in the following description, descriptions of well-known structures and techniques are omitted so as to not unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It is noted that the terms used herein should be interpreted as having a meaning that is consistent with the context of this specification and should not be interpreted in an idealized or overly formal sense.

Where a convention analogous to "at least one of A, B and C, etc." is used, in general such a construction is intended in the sense one having skill in the art would understand the convention (e.g., "a system having at least one of A, B and C" would include but not be limited to systems that have a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

Risk management is the main task of ensuring fund safety of banks, and personal credit risk assessment is the key process of loan approval of banks. At present, the bank evaluation method for customers mainly comprises the following steps: data are collected through a client service application form, the data are collected, various model indexes are extracted and calculated, weighting is carried out on the indexes to calculate client scores, and judgment is carried out on client grades according to the scores.

At present, data collected in a client evaluation process are mainly application form information and financial data generated in business transaction in a bank, the limitation is large, a complete client portrait cannot be constructed in multiple dimensions, and the accuracy of final client evaluation is low. The number of indexes extracted from the client data is large, the indexes are correlated, information use redundancy can be caused by simple weighted calculation, accuracy is low, and the scoring condition of the client can not be objectively reflected.

In view of the above problem, an embodiment of the present disclosure provides a method for evaluating a credit degree, including: acquiring original indexes of a target to be evaluated and data of the original indexes, wherein the data of the original indexes comprise the weight and the score of each original index; performing dimensionality reduction processing on the original indexes and the data of the original indexes to obtain total evaluation indexes and data of the total evaluation indexes; and determining an evaluation score for evaluating the credit of the target to be evaluated based on the total evaluation index and the data of the total evaluation index.

Correspondingly, an embodiment of the present disclosure further provides a method for performing dimension reduction processing on the original index and data of the original index, including: dividing the original index into N non-associated evaluation indexes and M candidate associated evaluation indexes, wherein M is more than or equal to 1, and N is more than or equal to 1; determining data of M candidate related evaluation indexes corresponding to the M candidate related evaluation indexes and determining data of N non-related evaluation indexes corresponding to the N non-related evaluation indexes in the data of the original indexes; performing principal component analysis on the M candidate relevance evaluation indexes and the data of the M candidate relevance evaluation indexes to obtain K relevance evaluation indexes and data of K relevance evaluation indexes, wherein K is less than M; obtaining a total evaluation index based on the K associated evaluation indexes and the N non-associated evaluation indexes; and obtaining data of a total evaluation index based on the data of the K related evaluation indexes and the data of the N non-related evaluation indexes.

Correspondingly, the embodiment of the disclosure also provides a credit rating device, equipment, a storage medium and a program product.

The method and the device for evaluating the credit degree determined by the disclosure can be used in the financial field, and can also be used for evaluating the credit degree in any field except the financial field.

In the technical scheme of the disclosure, the collection, storage, use, processing, transmission, provision, disclosure, application and other processing of the personal information of the related user are all in accordance with the regulations of related laws and regulations, necessary confidentiality measures are taken, and the customs of the public order is not violated.

In the technical scheme of the disclosure, before the personal information of the user is acquired or collected, the authorization or the consent of the user is acquired.

Fig. 1 schematically shows an application scenario diagram of a method, an apparatus, a device, a medium, and a program product for credit rating according to an embodiment of the present disclosure.

As shown in fig. 1, the application scenario 100 according to this embodiment may include

terminal devices

101, 102, 103, a network 104 and a server 105. The network 104 serves as a medium for providing communication links between the

terminal devices

101, 102, 103 and the server 105. Network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, to name a few.

The user may use the

terminal devices

101, 102, 103 to interact with the server 105 via the network 104 to receive or send messages or the like. The

terminal devices

101, 102, 103 may have installed thereon various communication client applications, such as shopping-like applications, web browser applications, search-like applications, instant messaging tools, mailbox clients, social platform software, etc. (by way of example only).

The

terminal devices

101, 102, 103 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop portable computers, desktop computers, and the like.

The server 105 may be a server providing various services, such as a background management server (for example only) providing support for websites browsed by users using the

terminal devices

101, 102, 103. The background management server may analyze and perform other processing on the received data such as the user request, and feed back a processing result (e.g., a webpage, information, or data obtained or generated according to the user request) to the terminal device.

It should be noted that the method for evaluating the credit provided by the embodiment of the present disclosure may be generally executed by the server 105. Accordingly, the credit rating device provided by the embodiment of the present disclosure may be generally disposed in the server 105. The method for evaluating the credit provided by the embodiment of the present disclosure may also be performed by a server or a server cluster that is different from the server 105 and is capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105. Accordingly, the credit rating device provided by the embodiment of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the

terminal devices

101, 102, 103 and/or the server 105.

It should be understood that the number of terminal devices, networks, and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

The method for evaluating the credit of the disclosed embodiment will be described in detail below with reference to fig. 2 based on the scenario described in fig. 1.

Fig. 2 schematically shows a flow chart of a method of credit rating according to an embodiment of the present disclosure.

As shown in fig. 2, the method for evaluating the credit degree of the embodiment includes operations S201 to S203.

In operation S201, an original index of a target to be evaluated and data of the original index are obtained, where the data of the original index includes a weight and a score of each original index.

In one embodiment, the original indexes of the target to be evaluated include an internal index set of a bank, specifically including financial indexes. The obtained financial information indexes of the user mainly comprise the following 4 types of financial indexes under the condition that the user agrees or authorizes to obtain the user information:

1. the basic information of the client: name, gender, credential type, credential number, job type, unit nature, academic calendar, age, etc.;

2. customer property information: the system comprises a fixed-term deposit balance, a current deposit balance, a financing hold quantity, a fund hold quantity, national debt information, insurance configuration, a real object precious metal purchasing condition, third party deposit and management information, an account foreign exchange condition, an annual income level and the like;

3. transfer transaction information: transfer amount, transfer object, transfer frequency, transfer channel and the like;

4. credit and debit card information: card number, credit card limit, credit card usage limit, guarantee type total limit, customer total limit, longest account age, etc.

In operation S202, the original indexes and the data of the original indexes are subjected to dimensionality reduction processing to obtain total evaluation indexes and data of the total evaluation indexes.

In order to further reduce the number of redundant indexes, facilitate subsequent calculation, and improve the accuracy of calculation, so as to objectively reflect the credit rating condition of a client, the indexes with high correlation degree can be extracted through dimension reduction processing, and some indexes (such as age, gender, marital status, and the like) with low correlation degree and basic information of the client are reserved, so as to completely reserve the characteristic data of the client as much as possible, wherein the dimension reduction processing may be a principal component analysis method, and other dimension reduction methods may be used, which is not limited in the embodiment of the disclosure.

In operation S203, an evaluation score for evaluating the credit of the target to be evaluated is determined based on the total evaluation index and the data of the total evaluation index.

FIG. 3 schematically shows a flow diagram of a dimension reduction process according to an embodiment of the disclosure.

As shown in fig. 3, the dimension reduction processing of this embodiment includes operations S301 to S305.

In operation S301, the original index is divided into N non-associated evaluation indexes and M candidate associated evaluation indexes, where M is greater than or equal to 1 and N is greater than or equal to 1.

In operation S302, of the data of the original indexes, data of M candidate related evaluation indexes corresponding to the M candidate related evaluation indexes and data of N non-related evaluation indexes corresponding to the N non-related evaluation indexes are determined.

In operation S303, principal component analysis is performed on the data of the M candidate relevance-class evaluation indexes and the data of the M candidate relevance-class evaluation indexes to obtain data of K relevance-class evaluation indexes and K relevance-class evaluation indexes, where K is less than M.

In operation S304, a total evaluation index is obtained based on the K associated evaluation indexes and the N non-associated evaluation indexes.

In operation S305, data of a total evaluation index is obtained based on the data of the K related evaluation indexes and the data of the N non-related evaluation indexes.

Since K is less than M, the number of the total evaluation indexes is less than that of the original indexes, and correspondingly, the number of the data of the total evaluation indexes is less than that of the data of the original indexes, so that the number of redundant indexes can be reduced, the subsequent calculation is facilitated, and the calculation accuracy is improved.

And calculating the correlation information coefficient among the indexes by applying an information entropy theory, and compared with a K-MEANS clustering algorithm, the method has the characteristics of no need of giving the number of clusters to be generated in advance and insensitivity to initial values. And extracting an index with high association degree as a principal component analysis initial index through an information entropy theory, and simultaneously keeping an index with low association degree and being client basic information.

According to the embodiment of the disclosure, the specific implementation steps of calculating the associated information coefficient among the indexes by applying the information entropy theory are as follows:

1. obtaining the value range and the corresponding probability distribution of the variable X to be selected, wherein the value range of the variable X to be selected is { X }₁，x₂，...，x_nIs given by { p (x) }, corresponding to a probability distribution₁)，p(x₂)，...，p(x_n) Based on the value range and the corresponding probability distribution of the variable X to be selected, the information entropy h (X) is calculated as:

in the formula: p (x) is not less than 0_i) Less than or equal to 1 and

2. calculating between the candidate variable X and the target variable Y when the event Y is Y_jWhen present, is represented by y_jObtained about x_jInformation amount of (I) (x)_i：y_j) Comprises the following steps:

3. based on y_jWith respect to x_jInformation amount of (I) (x)_i：y_j) To obtain average mutual information I between X and Y (X: y) is:

in the formula, p (x)_i|y_j) Represents the conditional probability, p (x)_i，y_j) Representing the joint probability.

4. Since the average mutual information represents the information amount shared by two random variables, based on the average mutual information I (X: Y) between X and Y, the correlation information coefficient between the candidate variable X and the target variable Y is obtained as:

according to the definition of the related information coefficient, the following steps are carried out: i is more than or equal to 0_R1 or less, and the greater the degree of association of X with Y, I_RThe larger.

Setting the threshold value of the coefficient of the associated information as I_tIf the calculated correlation information coefficient I between the candidate variable X and the target variable Y_R≥I_tThen the candidate variable is used as the principal component analysis initial variable.

The method can simplify and analyze the correlated complex relationship among the variables by applying a principal component analysis method, and reduces the dimension of a high-dimensional variable space under the principle of striving for the least loss of data information, so that the formed comprehensive index retains the information on the original index variation as much as possible.

And performing principal component analysis on the index with high correlation degree extracted based on the correlation information coefficient, extracting the principal component index, and calculating the corresponding weight, wherein the principal component analysis specifically comprises the following steps:

1. subtracting the column mean value from each column of the original matrix to generate a standardized matrix Z_b；

2. Calculating a normalized matrix Z_bOf the covariance matrix Z_c；

3. Calculating the covariance matrix Z_cAnd corresponding eigenvectors, where i is 1, 2, …, n, n is the matrix Z_cThe number of eigenvalues;

4. arranging the characteristic values in a descending order, and calculating the cumulative contribution rate of the first m principal elements according to the following formula:

wherein m is 1, 2, …, n-1.

5. And (3) constructing a transformation matrix T by taking eigenvectors corresponding to the first k larger eigenvalues, wherein eta (k) > 85%, wherein k < ═ m, and T ═ u1, u2, … and uk.

6. Through Z_kCalculating to obtain the first k main components to reduce the number of indexes, Z_kFor extracted principal component of variable to be selected, then Z_kThe corresponding weights are:

ω_kj＝ω_j*T

according to an embodiment of the present disclosure, the determining an evaluation score for evaluating the credit of the target to be evaluated based on the total evaluation index and the data of the total evaluation index includes: multiplying the weight and the score of each evaluation index in the data of the total evaluation index and the total evaluation index to obtain the contribution score of each evaluation index; and adding the contribution scores of all the evaluation indexes to determine an evaluation score for evaluating the credit of the target to be evaluated.

According to an embodiment of the present disclosure, before the step of calculating the correlation information coefficient between the indexes of the original indexes, the method further includes: preprocessing the original index, wherein the preprocessing comprises converting the attribute of the original index into a numerical type by using Laplace smoothing. Namely, the classification type variable processing, and further, the preprocessing includes: missing value processing, abnormal value elimination and digital variable processing.

Exemplary, specific pretreatment steps are as follows:

1. first, the missing values of the data of the original index are processed, for example, the positions of the missing values are filled with "-999".

2. And then, removing abnormal values of the data filled with the missing values, wherein the step of removing the data with the overlarge end and the undersize end after sorting each characteristic numerical value is included.

3. Secondly, carrying out logarithmic font variable processing on the data with the abnormal values removed: and data scaling and data discretization are used for conversion. The data scaling can eliminate unit and scale differences of different fields, and is suitable for the amount fields of deposit, loan, financing, fund and the like; the data discretization can solve the problems of data loss and distortion, and common discretization modes comprise equal-width, equal-frequency, equal-distance and clustering characteristics.

4. Finally, performing type-based variable processing, namely processing the original index: since the attribute of the original index is a character type attribute, the laplacian smoothing technique can be used to convert the original index data into a magnitude attribute, such as a gender, a property of the unit in which the original index is located, and other fields.

According to the embodiment of the disclosure, in the step of acquiring the original index of the target to be evaluated and the data of the original index, the original index includes an internal evaluation index, and the internal evaluation index includes a financial evaluation index. Correspondingly, the data of the original indexes comprise internal data of the target to be evaluated, and the internal data comprise financial data.

According to the embodiment of the disclosure, the original index of the target to be evaluated further comprises an external evaluation index, and the external evaluation index comprises at least one of a credit investigation type evaluation index, a social contact type evaluation index and an internet type evaluation index. Correspondingly, the data of the original indexes further include external data of the target to be evaluated, and the external data includes at least one of credit investigation type data, social contact type data and internet type data. By introducing external data, the problem of the unicity of the evaluation data is solved, the client evaluation can be carried out in a multi-dimensional manner, and the evaluation accuracy is improved

According to the embodiment of the disclosure, the step of acquiring the original index of the target to be evaluated and the data of the original index comprises the following steps: and obtaining external evaluation indexes and data of the external evaluation indexes by utilizing a longitudinal federal learning method, wherein the external evaluation indexes comprise at least one of credit investigation type evaluation indexes, social contact type evaluation indexes and internet type evaluation indexes. Based on the longitudinal federal learning law, the external evaluation index information can be acquired under the condition of meeting data safety.

Illustratively, the method can be used for performing longitudinal federal learning in combination with a people bank credit investigation system, social media, an e-commerce platform and an internet financial enterprise, and under the condition that a user agrees or authorizes to obtain user information, credit investigation type evaluation indexes, social type evaluation indexes and internet type evaluation indexes of a client and corresponding credit investigation type, social type, consumption type and other data are obtained. The specific steps of the longitudinal federal learning law are as follows:

1. the encrypted samples are aligned.

And finding out a common sample of the two parties on the premise of data encryption by adopting an RSA encryption algorithm. And each participant performs hash processing on the own sample ID to obtain a hash value of the sample ID, and sends the hash value to the other participants through an RSA encryption algorithm, and the participants can determine the intersection of the sample IDs according to the hash value to determine the common sample ID.

2. And (5) training an encryption model.

After the common sample ID is determined, each participant conducts sub-model training locally based on own data, then homomorphic encryption is conducted on intermediate calculation results such as gradient values and loss values of the sub-models and transmitted to the cloud, and the cloud conducts aggregation calculation on the results to obtain intermediate parameters of the combined model. And returning the updated model parameters to the participants, repeating iteration until the model training is completed until convergence, taking the final intermediate result as the total score of the client evaluation, wherein the score contains the credit investigation, social contact, finance, consumption and other data of the client, and comprehensively evaluating the client according to the score.

According to an embodiment of the present disclosure, the weight of the evaluation index is calculated by using an entropy method. The entropy method can objectively give weight, avoids the subjectivity of the analytic hierarchy process, and does not need to prepare a reference data column in advance compared with a grey correlation degree analytic process.

Illustratively, the entropy method is implemented by the following steps:

supposing that m samples to be evaluated are provided, n evaluation indexes form an original index data matrix:

wherein X_ijAnd the j-th item of the ith sample represents the numerical value of the evaluation index.

In order to eliminate the influence on the evaluation result due to different dimensions, each index needs to be normalized.

If the larger the value of the index used, the better (forward index), then:

if the smaller the value of the index used, the better (negative index), then:

wherein X_jIs the j index value, X_maxIs the maximum value of the j-th index, X_minIs the minimum value of the j index.

Calculating the specific gravity of the marker value of the ith sample in the jth index:

in the formula, p is not less than 0_ij≤1。

Thus, a weight matrix of data can be established:

calculating the entropy value of the j index:

wherein the constant k is greater than 0,

ensure that e is more than or equal to 0_jLess than or equal to 1, i.e. e_jThe maximum is 1.

So the entropy of the jth index is:

the degree of difference of the jth index is d_j＝1-e_jSo as to obtain the corresponding weight of each index as:

according to the method for evaluating the credit rating of the embodiment of the disclosure, the total evaluation index is divided into the associated evaluation index and the non-associated evaluation index, so that the redundancy of the evaluation index can be greatly reduced, the complexity of the calculation process is reduced, the accuracy of the credit rating is improved, and the evaluation condition of the credit rating of a client can be objectively reflected.

The method for evaluating the degree of confidence of the present disclosure will be described in detail below with reference to examples.

Example 1

1. Under the condition that the user information can be obtained by the consent or authorization of the user, the original indexes of the target to be evaluated and the data of the original indexes are obtained, wherein the data of the original indexes comprise the weight and the score of each original index, and the weight and the score are shown in table 1.

TABLE 1

2. Calculating the correlation information coefficient among the index data in the table 1 by applying an information entropy theory to obtain the candidate correlation evaluation indexes, wherein the candidate correlation evaluation indexes comprise: z1, Z2, Z4, Z5, Z6, Z8, Z9, Z10, Z11, Z12, Z14, Z15; non-related evaluation indexes: z3, Z7.

Performing principal component analysis on the candidate relevance evaluation indexes and the data of the candidate relevance evaluation indexes to obtain a relevance evaluation index Z17, wherein the data of the corresponding relevance evaluation index Z17 is as follows: the weight is 0.176 and the index score is 80, as shown in table 2.

TABLE 2

3. Obtaining external evaluation indexes and data of the external evaluation indexes by utilizing a longitudinal federal learning method, wherein the external evaluation indexes comprise credit investigation type evaluation indexes, social type evaluation indexes and internet type evaluation indexes, and correspondingly, the external data comprise weights and scores of the credit investigation type data, the social type data and the internet type data, and the data are specifically shown in a table 3:

TABLE 3

4. Multiplying the weight and the score of each evaluation index in the table 3 to obtain the contribution score of each evaluation index; then adding the contribution scores of all the evaluation indexes, and determining the evaluation score for evaluating the credit of the target to be evaluated as follows:

Score＝0.02*80+0.04*60+0.176*80+0.22*75+0.18*25+0.05*30+0.13*45+0.06*55+0.03*10＝50.03

by the credit evaluation method, the redundancy of information is reduced, the accuracy of credit evaluation is improved, besides, data such as credit investigation type, social contact type and consumption type can be brought into a client evaluation model, the problem of singleness of credit evaluation data is solved, and the accuracy of credit evaluation is improved.

Based on the credit rating evaluation method, the disclosure also provides a credit rating evaluation device. The credit evaluation device will be described in detail below with reference to fig. 4.

Fig. 4 schematically shows a block diagram of the structure of the credit rating apparatus according to the embodiment of the present disclosure.

As shown in fig. 4, the evaluation apparatus 400 of this embodiment includes a first obtaining module 410, a dimension reduction module 420, and an evaluation module 430.

The first obtaining module 410 is configured to obtain an original index of a target to be evaluated and data of the original index, where the data of the original index includes a weight and a score of each original index, and the first obtaining module 410 may be configured to perform operation S201 described above, which is not described herein again.

And the dimension reduction module 420 is configured to perform dimension reduction processing on the original index and the data of the original index to obtain a total evaluation index and data of the total evaluation index. In an embodiment, the second obtaining module 420 may be configured to perform the operation S202 described above, which is not described herein again.

And the evaluation module 430 is configured to determine an evaluation score for evaluating the credit of the target to be evaluated based on the total evaluation index and the data of the total evaluation index. In an embodiment, the evaluation module 430 may be configured to perform the operation S203 described above, which is not described herein again.

According to the embodiment of the present disclosure, any multiple modules of the first obtaining module 410, the dimension reduction module 420, and the evaluation module 430 may be combined and implemented in one module, or any one of the modules may be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules may be combined with at least part of the functionality of the other modules and implemented in one module. According to an embodiment of the present disclosure, at least one of the first obtaining module 410, the dimension reduction module 420, and the evaluation module 430 may be implemented at least partially as a hardware circuit, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system on a chip, a system on a substrate, a system on a package, an Application Specific Integrated Circuit (ASIC), or may be implemented by hardware or firmware in any other reasonable manner of integrating or packaging a circuit, or may be implemented by any one of three implementations of software, hardware, and firmware, or any suitable combination of any of the three. Alternatively, at least one of the first obtaining module 410, the dimension reduction module 420, the evaluation module 430 may be at least partially implemented as a computer program module, which when executed, may perform a corresponding function.

As shown in fig. 5, an electronic device 500 according to an embodiment of the present disclosure includes a processor 501 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM)502 or a program loaded from a storage section 508 into a Random Access Memory (RAM) 503. The processor 501 may comprise, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or associated chipset, and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), among others. The processor 501 may also include onboard memory for caching purposes. Processor 501 may include a single processing unit or multiple processing units for performing different actions of a method flow according to embodiments of the disclosure.

In the RAM 503, various programs and data necessary for the operation of the electronic apparatus 500 are stored. The processor 501, the ROM 502, and the RAM 503 are connected to each other by a bus 504. The processor 501 performs various operations of the method flows according to embodiments of the present disclosure by executing programs in the ROM 502 and/or RAM 503. Note that the programs may also be stored in one or more memories other than the ROM 502 and the RAM 503. The processor 501 may also perform various operations of method flows according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, electronic device 500 may also include an input/output (I/O) interface 505, input/output (I/O) interface 505 also being connected to bus 504. The electronic device 500 may also include one or more of the following components connected to the I/O interface 505: an input portion 506 including a keyboard, a mouse, and the like; an output portion 507 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, and a speaker; a storage portion 508 including a hard disk and the like; and a communication section 509 including a network interface card such as a LAN card, a modem, or the like. The communication section 509 performs communication processing via a network such as the internet. The driver 510 is also connected to the I/O interface 505 as necessary. A removable medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 510 as necessary, so that a computer program read out therefrom is mounted into the storage section 508 as necessary.

The present disclosure also provides a computer-readable storage medium, which may be contained in the apparatus/device/system described in the above embodiments; or may exist separately and not be assembled into the device/apparatus/system. The computer-readable storage medium carries one or more programs which, when executed, implement the method according to an embodiment of the disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, a computer-readable storage medium may include ROM 502 and/or RAM 503 and/or one or more memories other than ROM 502 and RAM 503 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the method illustrated in the flow chart. The program code is for causing a computer system to perform the methods of the embodiments of the disclosure when the computer program product is run on the computer system.

The computer program performs the above-described functions defined in the system/apparatus of the embodiments of the present disclosure when executed by the processor 501. The systems, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

In one embodiment, the computer program may be hosted on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed in the form of a signal on a network medium, downloaded and installed through the communication section 509, and/or installed from the removable medium 511. The computer program containing program code may be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network through the communication section 509, and/or installed from the removable medium 511. The computer program, when executed by the processor 501, performs the above-described functions defined in the system of the embodiments of the present disclosure. The systems, devices, apparatuses, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the present disclosure.

In accordance with embodiments of the present disclosure, program code for executing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, these computer programs may be implemented using high level procedural and/or object oriented programming languages, and/or assembly/machine languages. The programming language includes, but is not limited to, programming languages such as Java, C + +, python, the "C" language, or the like. The program code may execute entirely on the user computing device, partly on the user device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that various combinations and/or combinations of features recited in the various embodiments and/or claims of the present disclosure can be made, even if such combinations or combinations are not expressly recited in the present disclosure. In particular, various combinations and/or combinations of the features recited in the various embodiments and/or claims of the present disclosure may be made without departing from the spirit or teaching of the present disclosure. All such combinations and/or associations are within the scope of the present disclosure.

The embodiments of the present disclosure have been described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in the embodiments cannot be used in advantageous combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be devised by those skilled in the art without departing from the scope of the present disclosure, and such alternatives and modifications are intended to be within the scope of the present disclosure.

Claims

1. A method for evaluating credit, comprising:

acquiring original indexes of a target to be evaluated and data of the original indexes, wherein the data of the original indexes comprise the weight and the score of each original index;

performing dimensionality reduction processing on the original indexes and the data of the original indexes to obtain total evaluation indexes and data of the total evaluation indexes; and

and determining an evaluation score for evaluating the credit of the target to be evaluated based on the total evaluation index and the data of the total evaluation index.

2. The method of claim 1, wherein the step of performing dimension reduction processing on the original indexes and the data of the original indexes comprises:

dividing the original index into N non-associated evaluation indexes and M candidate associated evaluation indexes, wherein M is more than or equal to 1, and N is more than or equal to 1;

determining data of M candidate related evaluation indexes corresponding to the M candidate related evaluation indexes and determining data of N non-related evaluation indexes corresponding to the N non-related evaluation indexes in the data of the original indexes;

performing principal component analysis on the M candidate relevance evaluation indexes and the data of the M candidate relevance evaluation indexes to obtain K relevance evaluation indexes and data of K relevance evaluation indexes, wherein K is less than M;

obtaining a total evaluation index based on the K associated evaluation indexes and the N non-associated evaluation indexes; and

and obtaining data of a total evaluation index based on the data of the K related evaluation indexes and the data of the N non-related evaluation indexes.

3. The method according to claim 2, wherein before the step of dividing the original index into N non-associated-class evaluation indexes and M candidate associated-class evaluation indexes, the method further comprises:

calculating the correlation information coefficient among all indexes of the original indexes;

the step of dividing the original index into N non-associated evaluation indexes and M candidate associated evaluation indexes includes: and dividing the original indexes into N non-associated evaluation indexes and M candidate associated evaluation indexes based on the associated information coefficient.

4. The method according to claim 2, wherein the step of determining an evaluation score for evaluating the credit of the object to be evaluated based on the total evaluation index and the data of the total evaluation index comprises:

multiplying the weight and the score of each evaluation index in the data of the total evaluation index and the total evaluation index to obtain the contribution score of each evaluation index; and

and adding the contribution scores of all the evaluation indexes to determine an evaluation score for evaluating the credit of the target to be evaluated.

5. The method according to claim 3, wherein the step of calculating the correlation information coefficient between the indexes of the original indexes is preceded by:

preprocessing the original index, wherein the preprocessing comprises converting the attribute of the original index into a numerical type by using Laplace smoothing.

6. The method according to claim 1, wherein the step of obtaining the original index of the target to be evaluated and the data of the original index comprises:

and obtaining external evaluation indexes and data of the external evaluation indexes by utilizing a longitudinal federal learning method, wherein the external evaluation indexes comprise at least one of credit investigation type evaluation indexes, social contact type evaluation indexes and internet type evaluation indexes.

7. An apparatus for evaluating credit, comprising:

the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring original indexes of a target to be evaluated and data of the original indexes, and the data of the original indexes comprise the weight and the score of each original index;

the dimensionality reduction module is used for carrying out dimensionality reduction processing on the original indexes and the data of the original indexes to obtain total evaluation indexes and data of the total evaluation indexes; and

and the evaluation module is used for determining an evaluation score for evaluating the credit of the target to be evaluated based on the total evaluation index and the data of the total evaluation index.

8. An electronic device, comprising:

one or more processors;

a storage device for storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-6.

9. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program which, when executed by a processor, implements a method according to any one of claims 1 to 6.