CN110827137A - Credit evaluation method and device - Google Patents
Credit evaluation method and device Download PDFInfo
- Publication number
- CN110827137A CN110827137A CN201810916924.4A CN201810916924A CN110827137A CN 110827137 A CN110827137 A CN 110827137A CN 201810916924 A CN201810916924 A CN 201810916924A CN 110827137 A CN110827137 A CN 110827137A
- Authority
- CN
- China
- Prior art keywords
- user
- determining
- evaluated
- attribute
- repayment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 48
- 238000013210 evaluation model Methods 0.000 claims abstract description 62
- 238000000034 method Methods 0.000 claims abstract description 28
- 230000006870 function Effects 0.000 claims description 42
- 238000011478 gradient descent method Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010586 diagram Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a credit evaluation method and a credit evaluation device. The method comprises the following steps: determining the repayment capacity of the user to be evaluated according to a credit evaluation model and the attribute characteristics of the user to be evaluated, wherein the credit evaluation model is used for indicating the relationship between the attribute characteristics of the user and the repayment capacity of the user; the attribute characteristics of the user to be evaluated comprise: at least one of gender, nationality, and annual income; determining the expected income of a loan party when the user to be evaluated applies for the target loan type according to the repayment capability of the user to be evaluated; and determining whether to offer the user to be evaluated with a loan according to the expected income. Compared with the method of credit evaluation depending on manual experience in the prior art, the accuracy of the evaluation result is improved.
Description
Technical Field
The invention relates to the technical field of big data, in particular to a credit evaluation method and a credit evaluation device.
Background
With the rapid development of the financial industry, loan transactions are becoming more common, for example: house credit, consumer credit, and business credit, etc. One core point in the loan transaction is the user's credit rating, which may provide important basis for determining whether the user has the ability to repay the loan. Therefore, how to accurately and efficiently realize the credit evaluation of the user becomes a problem to be solved urgently in the financial industry.
In the prior art, it is common practice to give comprehensive evaluation according to different information of a user through manual experience. However, this method requires a lot of labor cost and depends on the experience of the evaluator, resulting in unstable evaluation results.
Disclosure of Invention
The invention provides a credit evaluation method and a credit evaluation device. The method is used for improving the accuracy of the credit evaluation result of the user.
In a first aspect, the present invention provides a credit evaluation method, including:
determining the repayment capacity of the user to be evaluated according to a credit evaluation model and the attribute characteristics of the user to be evaluated, wherein the credit evaluation model is used for indicating the relationship between the attribute characteristics of the user and the repayment capacity of the user; the attribute characteristics of the user to be evaluated comprise: at least one of gender, nationality, and annual income;
determining the expected income of a loan party when the user to be evaluated applies for the target loan type according to the repayment capability of the user to be evaluated;
and determining whether to offer the user to be evaluated with a loan according to the expected income.
Optionally, before determining the repayment capability of the user to be evaluated according to the credit evaluation model and the attribute characteristics of the user to be evaluated, the method further includes:
and acquiring the credit evaluation model.
Optionally, the obtaining the credit evaluation model includes:
determining repayment capacity corresponding to each attribute feature in a first attribute feature set according to N pre-stored samples, wherein the first attribute feature set comprises the attribute features contained in any one of the N samples, and the repayment capacity is the repayment capacity for the target loan type;
and determining a credit evaluation model corresponding to the target loan type according to the repayment capacity corresponding to each attribute feature in the first attribute feature set.
Optionally, the determining, according to N pre-stored samples, a repayment capability corresponding to each attribute feature in the first attribute feature set includes:
determining the repayment capacity corresponding to each attribute feature in the first attribute feature set according to the following formula;
wherein, bi,jRepresenting the repayment capability of the attribute characteristics i on the target loan type j, ys,i,jProperty characteristics i representing sample s for repayment ability on target loan type j, niIndicating the number of samples.
Optionally, the determining, according to the repayment capability corresponding to each attribute feature in the first attribute feature set, a credit evaluation model corresponding to the target loan type includes:
obtaining a model parameter set W; wherein W ═ { W ═ Wi,j}，wi,jRepresenting the importance degree of the attribute characteristic i to the target loan type j; w is ai,jThe value range of (1) is (0);
determining the credit evaluation model by adopting the following formula according to the parameter set W;
wherein, Yu,jIndicating the repayment ability of user u for target loan type j, fuRepresenting a second set of attribute features comprising all attribute features of user u.
Optionally, the obtaining a model parameter set W includes:
obtaining a loan record of the user u;
determining a model loss function according to the loan record and the credit evaluation model;
determining a model parameter value corresponding to the attribute characteristic i when the model loss function is minimum by adopting a gradient descent method according to the model loss function;
and determining the model parameter set W according to the model parameter values.
Optionally, determining a model loss function according to the loan record and the credit evaluation model; the method comprises the following steps:
determining the model loss function according to the following formula;
where los (W) represents the model loss function, U represents the total loan history for user U, yu,jRepresenting the loan record, y, of user u for loan type pu,j1 indicates that user u has repayed loan type p, y on timeu,j0 indicates that the user u does not repay the loan type p on time;
θ denotes an iteration parameter.
Optionally, the determining, according to the model loss function, a model parameter value corresponding to the attribute characteristic i when the model loss function is minimum by using a gradient descent method includes:
determining said w by performing an iterative calculation according to the following formulai,j；
Where ρ represents the step size of the advance, θ represents the iteration parameter, and los (w) represents the model loss function.
Optionally, the determining, according to the repayment capability of the user to be evaluated, the expected income of the lender when the user to be evaluated applies for the target loan type includes:
determining the repayment capacity of each sample in a preset number of samples according to the preset number of samples and the credit evaluation model;
determining M credit segments according to the repayment capacity of each sample;
determining the proportion of positive samples of the corresponding segments according to the number of samples corresponding to each credit segment;
and determining the expected income according to the repayment capacity of the user to be evaluated and the positive sample proportion.
Optionally, the determining the expected profit according to the repayment capacity of the user to be evaluated and the positive sample proportion includes:
determining the expected revenue according to the following formula;
Eearn(k,j)＝Akej-(1-Ak)vj
wherein Eearn (k, j) represents the expected income of the loan party when the user to be evaluated applies for the target loan type j, k represents the credit segment corresponding to the repayment capability of the user to be evaluated, AkRepresenting the proportion of positive samples of the kth credit segment, ejThe income of the lender when the user to be evaluated can repay the target loan type j on time, vjThe loss of the loan party when the user to be evaluated cannot repay the target loan type j on time.
In a second aspect, the present invention provides a credit evaluation device, including:
the system comprises a first determining module, a second determining module and a payment processing module, wherein the first determining module is used for determining the payment capability of a user to be evaluated according to a credit evaluation model and the attribute characteristics of the user to be evaluated, and the credit evaluation model is used for indicating the relationship between the attribute characteristics of the user and the payment capability of the user; the attribute characteristics of the user to be evaluated comprise: at least one of gender, nationality, and annual income;
the second determination module is used for determining the expected income of the loan party when the user to be evaluated applies for the target loan type according to the repayment capability of the user to be evaluated;
and the third determining module is used for determining whether to send the loan to the user to be evaluated according to the expected income.
Optionally, the apparatus further includes:
and the acquisition module is used for acquiring the credit evaluation model.
Optionally, the obtaining module is specifically configured to determine, according to N pre-stored samples, a repayment capacity corresponding to each attribute feature in a first attribute feature set, where the first attribute feature set includes an attribute feature included in any sample of the N samples, and the repayment capacity is a repayment capacity for the target loan type;
and determining a credit evaluation model corresponding to the target loan type according to the repayment capacity corresponding to each attribute feature in the first attribute feature set.
Optionally, the obtaining module is specifically configured to determine a repayment capability corresponding to each attribute feature in the first attribute feature set according to the following formula;
wherein, bi,jRepresenting the repayment capability of the attribute characteristics i on the target loan type j, ys,i,jProperty characteristics i representing sample s for repayment ability on target loan type j, niIndicating the number of samples.
Optionally, the obtaining module is specifically configured to obtain a model parameter set W; wherein W ═ { W ═ Wi,j}，wi,jRepresenting the importance degree of the attribute characteristic i to the target loan type j; w is ai,jThe value range of (1) is (0);
determining the credit evaluation model by adopting the following formula according to the parameter set W;
wherein, Yu,jIndicating the repayment ability of user u for target loan type j, fuRepresenting a second set of attribute features comprising all attribute features of user u.
Optionally, the obtaining module is specifically configured to obtain a loan record of the user u;
determining a model loss function according to the loan record and the credit evaluation model;
determining a model parameter value corresponding to the attribute characteristic i when the model loss function is minimum by adopting a gradient descent method according to the model loss function;
and determining the model parameter set W according to the model parameter values.
Optionally, the obtaining module is specifically configured to determine the model loss function according to the following formula;
where los (W) represents the model loss function, U represents the total loan history for user U, yu,jRepresenting the loan record, y, of user u for loan type pu,j1 indicates that user u has repayed loan type p, y on timeu,j0 indicates that the user u does not repay the loan type p on time;
θ denotes an iteration parameter.
Optionally, the obtaining module is specifically configured to perform iterative computation according to the following formula to determine wi,j；
Where ρ represents the step size of the advance, θ represents the iteration parameter, and los (w) represents the model loss function.
Optionally, the second determining module is specifically configured to determine, according to a preset number of samples and the credit evaluation model, a repayment capability of each sample in the preset number of samples;
determining M credit segments according to the repayment capacity of each sample;
determining the proportion of positive samples of the corresponding segments according to the number of samples corresponding to each credit segment;
and determining the expected income according to the repayment capacity of the user to be evaluated and the positive sample proportion.
Optionally, the second determining module is specifically configured to determine the expected revenue according to the following formula;
Eearn(k,j)＝Akej-(1-Ak)vj
wherein Eearn (k, j) represents the expected income of the loan party when the user to be evaluated applies for the target loan type j, k represents the credit segment corresponding to the repayment capability of the user to be evaluated, AkRepresenting the proportion of positive samples of the kth credit segment, ejThe income of the lender when the user to be evaluated can repay the target loan type j on time, vjThe loss of the loan party when the user to be evaluated cannot repay the target loan type j on time.
In a third aspect, the present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above-described credit evaluation method.
In a fourth aspect, the present invention provides a server, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to implement the above-described credit evaluation method via execution of the executable instructions.
According to the credit evaluation method and the device, the repayment capacity of a user to be evaluated is determined according to a pre-established credit evaluation model and the attribute characteristics of the user to be evaluated; and then determining the expected income of the loan party when the user to be evaluated applies for the target loan type according to the repayment capability of the user to be evaluated, and if the expected income is greater than zero, determining to issue a loan for the user to be evaluated.
Drawings
FIG. 1 is a flowchart illustrating a first embodiment of a credit evaluation method according to the present invention;
FIG. 2 is a flowchart illustrating a second embodiment of a credit evaluation method according to the present invention;
FIG. 3 is another schematic flow chart of a second embodiment of a credit evaluation method according to the present invention;
FIG. 4 is a flowchart illustrating a third embodiment of a credit evaluation method according to the present invention;
FIG. 5 is a schematic structural diagram of a first embodiment of a credit evaluation apparatus provided in the present invention;
fig. 6 is a schematic diagram of a hardware structure of a server according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the present invention, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated.
In the prior art, when a user is evaluated for credit, it is a common practice to give comprehensive evaluation according to different information of the user through manual experience. However, this method requires a lot of labor cost and depends on the experience of the evaluator, resulting in unstable evaluation results.
The invention provides a credit evaluation method and a credit evaluation device. Determining the repayment capacity of the user to be evaluated through a pre-established credit evaluation model and the attribute characteristics of the user to be evaluated, wherein the attribute characteristics comprise age, nationality, annual income and the like; then determining the expected income of a loan party when the user to be evaluated applies for the target loan type according to the repayment capability of the user to be evaluated; and finally, determining whether to release the loan to the user to be evaluated according to the expected income. Compared with the method of credit evaluation depending on manual experience in the prior art, the accuracy of the evaluation result is improved.
Optionally, the method provided by the present invention may be executed by a server installed with corresponding software.
The following describes the technical solutions of the present invention and how to solve the above technical problems with specific embodiments. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments. Embodiments of the present invention will be described below with reference to the accompanying drawings.
Fig. 1 is a schematic flowchart of a first embodiment of a credit evaluation method according to the present invention. The credit evaluation method provided by the implementation comprises the following steps:
s101, determining the repayment capacity of a user to be evaluated according to a credit evaluation model and the attribute characteristics of the user to be evaluated, wherein the credit evaluation model is used for indicating the relationship between the attribute characteristics of the user and the repayment capacity of the user; the attribute characteristics of the user to be evaluated comprise: at least one of gender, nationality, and annual income.
The credit evaluation model is an evaluation model calculated according to a large number of pre-stored samples. Each sample represents a customer, and the sample information for each sample includes: attribute characteristics of the customer and a loan record for the customer. The attribute characteristics of the client can be the gender of the client, the nationality of the client or the annual income of the client and the like; the customer's loan records may include the customer's historical loan types, as well as the repayment status for each loan type, and the like.
On the basis of obtaining the attribute characteristics of the user to be evaluated, inputting the attribute characteristics of the user to be evaluated into the credit evaluation model to obtain the repayment capacity value of the user to be evaluated, wherein the larger the repayment capacity value is, the higher the repayment capacity of the user to be evaluated is represented.
And S102, determining the expected income of a loan party when the user to be evaluated applies for the target loan type according to the repayment capability of the user to be evaluated.
S103, determining whether to release a loan to the user to be evaluated according to the expected income.
On the basis of the repayment capability of the user to be evaluated obtained through S101, the expected income of the lender when the user to be evaluated can repay the target loan type on time and the loss of the lender when the user to be evaluated cannot repay the target loan type on time are combined to calculate the expected income of the lender when the user to be evaluated applies for the target loan type.
Optionally, when the expected income is greater than zero, the user to be evaluated can be determined to be loaned; when the expected profit is less than zero, the user to be evaluated may be determined not to be offered a loan.
According to the credit evaluation method provided by the embodiment, the repayment capacity of a user to be evaluated is determined according to a pre-established credit evaluation model and the attribute characteristics of the user to be evaluated; and then determining the expected income of the loan party when the user to be evaluated applies for the target loan type according to the repayment capability of the user to be evaluated, and if the expected income is greater than zero, determining to issue a loan for the user to be evaluated.
Fig. 2 is a flowchart illustrating a second embodiment of a credit evaluation method according to the present invention. In order to implement the credit evaluation for the user through the credit evaluation model, on the basis of the above embodiment, the credit evaluation method provided by this embodiment further includes, before S101: and acquiring the credit evaluation model.
Optionally, the implementation manner of obtaining the credit evaluation model is as follows:
s201, determining repayment capacity corresponding to each attribute feature in a first attribute feature set according to N pre-stored samples, wherein the first attribute feature set comprises the attribute features contained in any one of the N samples, and the repayment capacity is the repayment capacity for the target loan type;
s202, determining a credit evaluation model corresponding to the target loan type according to the repayment capacity corresponding to each attribute feature in the first attribute feature set.
Alternatively, referring to fig. 3, an achievable manner of S201 includes:
s203, determining the repayment capacity corresponding to each attribute feature in the first attribute feature set according to the following formula;
wherein, bi,jRepresenting the repayment capability of the attribute characteristics i on the target loan type j, ys,i,jProperty characteristics i representing sample s for repayment ability on target loan type j, niIndicating the number of samples.
Wherein, for the sample s, if the client corresponding to the sample s is verified to have cleared the target loan type j, then y corresponding to the sample ss,i,j1, if the client corresponding to the sample s does not yet find the target loan type j, then y corresponding to the samples,i,jIs 0.
Optionally, an achievable manner of S202 includes:
s204, obtaining a model parameter set W; wherein W ═ { W ═ Wi,j}，wi,jRepresenting the importance degree of the attribute characteristic i to the target loan type j; w is ai,jThe value range of (1) is (0).
Optionally, the model parameter set W may be obtained through the following steps a-d:
step a, obtaining a loan record of a user u;
b, determining a model loss function according to the loan record and the credit evaluation model;
alternatively to wi,jLet us order
Then
Then it is determined that,
alternatively, the model loss function may be determined according to the following formula;
where los (W) represents the model loss function, U represents the total loan history for user U, yu,jRepresenting the loan record, y, of user u for loan type pu,j1 indicates that user u has repayed loan type p, y on timeu,j0 indicates that the user u does not repay the loan type p on time;θ denotes an iteration parameter.
Step c, determining a model parameter value corresponding to the attribute characteristic i when the model loss function is minimum by adopting a gradient descent method according to the model loss function;
alternatively to wi,jCorresponding to thetaiThe w may be determined by iterative calculations based on the following formulai,j；
Where ρ represents the step size of the advance, θ represents the iteration parameter, and los (w) represents the model loss function.
And d, determining the model parameter set W according to the model parameter values.
S205, determining the credit evaluation model by adopting the following formula according to the parameter set W;
wherein, Yu,jIndicating the repayment ability of user u for target loan type j, fuRepresenting a second set of attribute features comprising all attribute features of user u.
Wherein, when calculating the repayment ability of the user to be evaluated by the formula, f is useduThe elements of (1) are replaced by the attribute characteristics of the user to be evaluated.
The credit evaluation method provided by the embodiment describes an achievable way of obtaining the credit evaluation model, and provides a basis for determining the repayment capability of the user to be evaluated according to the model subsequently.
Fig. 4 is a flowchart illustrating a third embodiment of a credit evaluation method according to the present invention. The present embodiment is further described with respect to an implementation manner of S102 in the foregoing embodiment, and as shown in fig. 4, S102 may specifically include:
s301, determining the repayment capacity of each sample in a preset number of samples according to the preset number of samples and the credit evaluation model;
s302, determining M credit segments according to the repayment capacity of each sample;
s303, determining the proportion of positive samples of corresponding segments according to the number of samples corresponding to each credit segment;
wherein, the larger the preset number is, the more accurate the obtained evaluation result is. For example, 1 ten thousand samples may be randomly selected.
After the samples with the preset number are obtained, calculating the repayment capacity corresponding to each sample according to the credit evaluation model obtained in the embodiment in the first step; secondly, arranging a preset number of samples in a descending order according to the sequence of repayment capacity from large to small; thirdly, referring to table 1, averagely dividing the samples after descending order into 100 credit segments; and fourthly, calculating the proportion of positive samples of each credit segment.
Wherein, the proportion of positive samples refers to: in each credit segment, the number of samples of the target repayment type j has been cleared on time as a proportion of the total number of samples covered by the credit segment. Taking the credit segment (S1, S2) as an example, assuming that the total number of samples covered by the credit segment (S1, S2) obtained according to the first to third steps is 100, and the number of samples for which the target loan type j has been verified to be still clear in time in the 100 samples is 50, the proportion of the positive samples of the credit segment (S1, S2) is: 50/100 is 0.5.
| Credit segmentation | Positive sample ratio |
| (S1，S2) | A1％ |
| (S2，S3) | A2％ |
| …… | …… |
| (S100，S101) | A100％ |
TABLE 1
S304, determining the expected income according to the repayment capacity of the user to be evaluated and the positive sample proportion.
On the basis of obtaining the repayment capacity of the user to be evaluated, the scoring segment to which the repayment capacity of the user to be evaluated belongs is inquired through the table 1, and then the positive sample proportion corresponding to the scoring segment is obtained, and the positive sample proportion is assumed to be Ak. Alternatively, the expected revenue may be determined according to the following formula;
Eearn(k,j)＝Akej-(1-Ak)vj
wherein Eearn (k, j) represents the expected income of the loan party when the user to be evaluated applies for the target loan type j, k represents the credit segment corresponding to the repayment capability of the user to be evaluated, AkRepresenting the proportion of positive samples of the kth credit segment, ejThe income of the lender when the user to be evaluated can repay the target loan type j on time, vjThe loss of the loan party when the user to be evaluated cannot repay the target loan type j on time.
The credit evaluation method provided by the embodiment describes an implementation manner of how to determine the expected income of a lender when the user to be evaluated applies for the target loan type according to the repayment capacity of the user to be evaluated. And providing a basis for subsequently judging whether the user to be evaluated issues the loan.
Fig. 5 is a schematic structural diagram of a first embodiment of a credit evaluation apparatus according to the present invention. As shown in fig. 5, the credit evaluation apparatus provided in this embodiment includes:
a first determining module 501, configured to determine the repayment capability of a user to be evaluated according to a credit evaluation model and attribute characteristics of the user to be evaluated, where the credit evaluation model is used to indicate a relationship between the attribute characteristics of the user and the repayment capability of the user; the attribute characteristics of the user to be evaluated comprise: at least one of gender, nationality, and annual income;
a second determining module 502, configured to determine, according to the repayment capability of the user to be evaluated, an expected income of the lender when the user to be evaluated applies for the target loan type;
a third determining module 503, configured to determine whether to offer a loan to the user to be evaluated according to the expected income.
Optionally, the credit evaluation apparatus provided in this embodiment further includes:
an obtaining module 504, configured to obtain the credit evaluation model.
Optionally, the obtaining module 504 is specifically configured to determine, according to N pre-stored samples, a repayment capacity corresponding to each attribute feature in a first attribute feature set, where the first attribute feature set includes an attribute feature included in any sample of the N samples, and the repayment capacity is a repayment capacity for the target loan type;
and determining a credit evaluation model corresponding to the target loan type according to the repayment capacity corresponding to each attribute feature in the first attribute feature set.
Optionally, the obtaining module 504 is specifically configured to determine a repayment capability corresponding to each attribute feature in the first attribute feature set according to the following formula;
wherein, bi,jRepresenting the repayment capability of the attribute characteristics i on the target loan type j, ys,i,jProperty characteristics i representing sample s for repayment ability on target loan type j, niIndicating the number of samples.
Optionally, the obtaining module 504 is specifically configured to obtain a model parameter set W; wherein W ═ { W ═ Wi,j}，wi,jRepresenting the importance degree of the attribute characteristic i to the target loan type j; w is ai,jThe value range of (1) is (0);
determining the credit evaluation model by adopting the following formula according to the parameter set W;
wherein, Yu,jIndicating the repayment ability of user u for target loan type j, fuRepresenting a second set of attribute features comprising all attribute features of user u.
Optionally, the obtaining module 504 is specifically configured to obtain a loan record of the user u;
determining a model loss function according to the loan record and the credit evaluation model;
determining a model parameter value corresponding to the attribute characteristic i when the model loss function is minimum by adopting a gradient descent method according to the model loss function;
and determining the model parameter set W according to the model parameter values.
Optionally, the obtaining module 504 is specifically configured to determine the model loss function according to the following formula;
wherein los (W)) Representing the model loss function, U representing the total loan record for user U, yu,jRepresenting the loan record, y, of user u for loan type pu,j1 indicates that user u has repayed loan type p, y on timeu,j0 indicates that the user u does not repay the loan type p on time;
θ denotes an iteration parameter.
Optionally, the obtaining module 504 is specifically configured to perform iterative computation according to the following formula to determine the wi，j；
Where ρ represents the step size of the advance, θ represents the iteration parameter, and los (w) represents the model loss function.
Optionally, the second determining module 502 is specifically configured to determine, according to a preset number of samples and the credit evaluation model, a repayment capability of each sample in the preset number of samples;
determining M credit segments according to the repayment capacity of each sample;
determining the proportion of positive samples of the corresponding segments according to the number of samples corresponding to each credit segment;
and determining the expected income according to the repayment capacity of the user to be evaluated and the positive sample proportion.
Optionally, the second determining module 502 is specifically configured to determine the expected revenue according to the following formula;
Eearn(k,j)＝Akej-(1-Ak)vj
wherein Eearn (k, j) represents the expected income of the loan party when the user to be evaluated applies for the target loan type j, k represents the credit segment corresponding to the repayment capability of the user to be evaluated, AkRepresenting the proportion of positive samples of the kth credit segment, ejThe income of the lender when the user to be evaluated can repay the target loan type j on time, vjFor the purpose of not being able to repay the user to be evaluated on timeThe loan party loses with the loan type j.
The credit evaluation apparatus provided in this embodiment may be used to execute the method in the embodiments shown in fig. 1 to 4, and the implementation principle and technical effect are similar, which are not described herein again.
Fig. 6 is a schematic diagram of a hardware structure of a server according to the present invention. As shown in fig. 6, the server of the present embodiment may include:
a memory 601 for storing program instructions.
The processor 602 is configured to implement the method described in any of the above embodiments when the program instructions are executed, and specific implementation principles may refer to the above embodiments, which are not described herein again.
The present invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the credit evaluation method of any of the above embodiments.
The invention also provides a program product comprising a computer program stored in a readable storage medium, the computer program being readable from the readable storage medium by at least one processor, the execution of the computer program by the at least one processor causing a server to implement the above described credit evaluation method.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
The integrated unit implemented in the form of a software functional unit may be stored in a computer readable storage medium. The software functional unit is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention. And the aforementioned storage medium includes: a U disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In the foregoing embodiments of the network device or the terminal device, it should be understood that the Processor may be a Central Processing Unit (CPU), or may be another general-purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in connection with the present application may be embodied directly in a hardware processor, or in a combination of the hardware and software modules in the processor.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (22)
1. A credit evaluation method, comprising:
determining the repayment capacity of the user to be evaluated according to a credit evaluation model and the attribute characteristics of the user to be evaluated, wherein the credit evaluation model is used for indicating the relationship between the attribute characteristics of the user and the repayment capacity of the user; the attribute characteristics of the user to be evaluated comprise: gender, nationality, and annual income;
determining the expected income of a loan party when the user to be evaluated applies for the target loan type according to the repayment capability of the user to be evaluated;
and determining whether to offer the user to be evaluated with a loan according to the expected income.
2. The method according to claim 1, wherein before determining the repayment capability of the user to be evaluated according to the credit evaluation model and the attribute characteristics of the user to be evaluated, the method further comprises:
and acquiring the credit evaluation model.
3. The method of claim 2, wherein obtaining the credit evaluation model comprises:
determining repayment capacity corresponding to each attribute feature in a first attribute feature set according to N pre-stored samples, wherein the first attribute feature set comprises the attribute features contained in any one of the N samples, and the repayment capacity is the repayment capacity for the target loan type;
and determining a credit evaluation model corresponding to the target loan type according to the repayment capacity corresponding to each attribute feature in the first attribute feature set.
4. The method according to claim 3, wherein the determining of the repayment capability corresponding to each attribute feature in the first attribute feature set according to the N pre-stored samples comprises:
determining the repayment capacity corresponding to each attribute feature in the first attribute feature set according to the following formula;
wherein, bi,jRepresenting the repayment capability of the attribute characteristics i on the target loan type j, ys,i,jProperty characteristics i representing sample s for repayment ability on target loan type j, niIndicating the number of samples.
5. The method according to claim 3, wherein the determining the credit evaluation model corresponding to the target loan type according to the repayment capacity corresponding to each attribute feature in the first attribute feature set comprises:
obtaining a model parameter set W; wherein W ═ { W ═ Wi,j}，wi,jRepresenting the importance degree of the attribute characteristic i to the target loan type j; w is ai,jThe value range of (1) is (0);
determining the credit evaluation model by adopting the following formula according to the parameter set W;
wherein, Yu,jIndicating the repayment ability of user u for target loan type j, fuRepresenting a second set of attribute features comprising all attribute features of user u, the second set of attribute features being a subset of the first set of attribute features.
6. The method of claim 5, wherein obtaining the set of model parameters W comprises:
obtaining a loan record of the user u;
determining a model loss function according to the loan record and the credit evaluation model;
determining a model parameter value corresponding to the attribute characteristic i when the model loss function is minimum by adopting a gradient descent method according to the model loss function;
and determining the model parameter set W according to the model parameter values.
7. The method of claim 6, wherein said determining a model loss function is based on said loan record and said credit evaluation model; the method comprises the following steps:
determining the model loss function according to the following formula;
where los (W) represents the model loss function, U represents the total loan history for user U, yu,jRepresenting the loan record, y, of user u for loan type pu,j1 indicates that user u has repayed loan type p, y on timeu,j0 indicates that the user u does not repay the loan type p on time;
θ denotes an iteration parameter.
8. The method according to claim 6, wherein the determining, according to the model loss function, the model parameter value corresponding to the attribute feature i when the model loss function is minimum by using a gradient descent method includes:
determining said w by performing an iterative calculation according to the following formulai,j；
Where ρ represents the step size of the advance, θ represents the iteration parameter, and los (w) represents the model loss function.
9. The method according to any one of claims 1 to 8, wherein the determining the expected income of the lender when the user to be evaluated applies for the target loan type according to the repayment capability of the user to be evaluated comprises:
determining the repayment capacity of each sample in a preset number of samples according to the preset number of samples and the credit evaluation model;
determining M credit segments according to the repayment capacity of each sample;
determining the proportion of positive samples of the corresponding segments according to the number of samples corresponding to each credit segment;
and determining the expected income according to the repayment capacity of the user to be evaluated and the positive sample proportion.
10. The method of claim 9, wherein determining the expected revenue based on the repayment ability of the user to be evaluated and the positive sample proportion comprises:
determining the expected revenue according to the following formula;
Eearn(k,j)＝Akej-(1-Ak)vj
wherein Eearn (k, j) represents the expected income of the loan party when the user to be evaluated applies for the target loan type j, k represents the credit segment corresponding to the repayment capability of the user to be evaluated, AkRepresenting the proportion of positive samples of the kth credit segment, ejThe income of the lender when the user to be evaluated can repay the target loan type j on time, vjThe loss of the loan party when the user to be evaluated cannot repay the target loan type j on time.
11. A credit evaluation apparatus, comprising:
the system comprises a first determining module, a second determining module and a payment processing module, wherein the first determining module is used for determining the payment capability of a user to be evaluated according to a credit evaluation model and the attribute characteristics of the user to be evaluated, and the credit evaluation model is used for indicating the relationship between the attribute characteristics of the user and the payment capability of the user; the attribute characteristics of the user to be evaluated comprise: at least one of gender, nationality, and annual income;
the second determination module is used for determining the expected income of the loan party when the user to be evaluated applies for the target loan type according to the repayment capability of the user to be evaluated;
and the third determining module is used for determining whether to send the loan to the user to be evaluated according to the expected income.
12. The apparatus of claim 11, further comprising:
and the acquisition module is used for acquiring the credit evaluation model.
13. The apparatus of claim 12,
the obtaining module is specifically configured to determine, according to N pre-stored samples, a repayment capacity corresponding to each attribute feature in a first attribute feature set, where the first attribute feature set includes the attribute features included in any sample of the N samples, and the repayment capacity is a repayment capacity for the target loan type;
and determining a credit evaluation model corresponding to the target loan type according to the repayment capacity corresponding to each attribute feature in the first attribute feature set.
14. The apparatus of claim 13,
the acquisition module is specifically used for determining the repayment capacity corresponding to each attribute feature in the first attribute feature set according to the following formula;
wherein, bi,jRepresenting the repayment capability of the attribute characteristics i on the target loan type j, ys,i,jProperty characteristics i representing sample s for repayment ability on target loan type j, niIndicating the number of samples.
15. The apparatus of claim 13,
the obtaining module is specifically configured to obtain a model parameter set W; wherein W ═ { W ═ Wi,j}，wi,jRepresenting the importance degree of the attribute characteristic i to the target loan type j; w is ai,jThe value range of (1) is (0);
determining the credit evaluation model by adopting the following formula according to the parameter set W;
wherein, Yu,jIndicating the repayment ability of user u for target loan type j, fuRepresenting a second set of attribute features comprising all attribute features of user u.
16. The apparatus of claim 15,
the obtaining module is specifically used for obtaining a loan record of the user u;
determining a model loss function according to the loan record and the credit evaluation model;
determining a model parameter value corresponding to the attribute characteristic i when the model loss function is minimum by adopting a gradient descent method according to the model loss function;
and determining the model parameter set W according to the model parameter values.
17. The apparatus of claim 16,
the obtaining module is specifically configured to determine the model loss function according to the following formula;
where los (W) represents the model loss function, U represents the total loan history for user U, yu,jRepresenting the loan record, y, of user u for loan type pu,j1 indicates that user u has repayed loan type p, y on timeu,j0 indicates that the user u does not repay the loan type p on time;θ denotes an iteration parameter.
18. The apparatus of claim 16,
the obtaining module is specifically configured to perform iterative computations according to the following formula to determine the wi,j；
Where ρ represents the step size of the advance, θ represents the iteration parameter, and los (w) represents the model loss function.
19. The apparatus according to any one of claims 11-18,
the second determining module is specifically configured to determine the repayment capacity of each sample in a preset number of samples according to the preset number of samples and the credit evaluation model;
determining M credit segments according to the repayment capacity of each sample;
determining the proportion of positive samples of the corresponding segments according to the number of samples corresponding to each credit segment;
and determining the expected income according to the repayment capacity of the user to be evaluated and the positive sample proportion.
20. The apparatus of claim 19,
the second determining module is specifically configured to determine the expected revenue according to the following formula;
Eearn(k,j)＝Akej-(1-Ak)vj
wherein Eearn (k, j) represents the expected income of the loan party when the user to be evaluated applies for the target loan type j, k represents the credit segment corresponding to the repayment capability of the user to be evaluated, AkRepresenting the proportion of positive samples of the kth credit segment, ejThe income of the lender when the user to be evaluated can repay the target loan type j on time, vjThe loss of the loan party when the user to be evaluated cannot repay the target loan type j on time.
21. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of any one of claims 1-10.
22. A server, comprising:
a processor; and
a memory for storing executable instructions of the processor;
wherein the processor is configured to implement the method of any of claims 1-10 via execution of the executable instructions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810916924.4A CN110827137A (en) | 2018-08-13 | 2018-08-13 | Credit evaluation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810916924.4A CN110827137A (en) | 2018-08-13 | 2018-08-13 | Credit evaluation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110827137A true CN110827137A (en) | 2020-02-21 |
Family
ID=69546857
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810916924.4A Pending CN110827137A (en) | 2018-08-13 | 2018-08-13 | Credit evaluation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110827137A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111382954A (en) * | 2020-03-25 | 2020-07-07 | 中国建设银行股份有限公司 | User rating method and device |
| CN113095685A (en) * | 2021-04-15 | 2021-07-09 | 深圳工盟科技有限公司 | Method and device for evaluating loan capacity of constructor |
-
2018
- 2018-08-13 CN CN201810916924.4A patent/CN110827137A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111382954A (en) * | 2020-03-25 | 2020-07-07 | 中国建设银行股份有限公司 | User rating method and device |
| CN113095685A (en) * | 2021-04-15 | 2021-07-09 | 深圳工盟科技有限公司 | Method and device for evaluating loan capacity of constructor |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108615119B (en) | Abnormal user identification method and equipment | |
| CN108665159A (en) | A kind of methods of risk assessment, device, terminal device and storage medium | |
| CN108763277B (en) | Data analysis method, computer readable storage medium and terminal device | |
| CN108764705A (en) | A kind of data quality accessment platform and method | |
| CN110503564B (en) | Security case processing method, system, equipment and storage medium based on big data | |
| CN109635029B (en) | Data processing method, device, equipment and medium based on label index system | |
| CN110060053B (en) | Identification method, equipment and computer readable medium | |
| CN110991936A (en) | Enterprise grading and rating method, device, equipment and medium | |
| CN112116245A (en) | Credit risk assessment method, credit risk assessment device, computer equipment and storage medium | |
| JP2016206983A (en) | Loan risk evaluation parameter calculating device, program and method | |
| CN110827137A (en) | Credit evaluation method and device | |
| CN107330709B (en) | Method and device for determining target object | |
| CN112819476A (en) | Risk identification method and device, nonvolatile storage medium and processor | |
| CN112148880A (en) | Customer service dialogue corpus clustering method, system, equipment and storage medium | |
| CN109460778B (en) | Activity evaluation method, activity evaluation device, electronic equipment and storage medium | |
| CN110717653A (en) | Risk identification method and device and electronic equipment | |
| CN110659981A (en) | Enterprise dependency relationship identification method and device and electronic equipment | |
| CN115829722A (en) | Training method of credit risk scoring model and credit risk scoring method | |
| CN115879819A (en) | Enterprise credit evaluation method and device | |
| CN112116405B (en) | Data processing method, device, electronic equipment and medium | |
| CN110264306B (en) | Big data-based product recommendation method, device, server and medium | |
| CN113962603A (en) | Risk assessment method and device, storage medium and electronic equipment | |
| JP5650290B1 (en) | Operational risk measurement method and apparatus | |
| CN111681090A (en) | Account grouping method and device of business system, terminal equipment and storage medium | |
| CN111126788A (en) | Risk identification method and device and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200422 Address after: 310052 room 508, floor 5, building 4, No. 699, Wangshang Road, Changhe street, Binjiang District, Hangzhou City, Zhejiang Province Applicant after: Alibaba (China) Co.,Ltd. Address before: 510000 Guangdong city of Guangzhou province Whampoa Tianhe District Road No. 163 Xiping Yun Lu Yun Ping square B radio tower 12 layer self unit 01 Applicant before: GUANGZHOU SHENMA MOBILE INFORMATION TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200221 |