CN113379456A - Credit interest rate differential pricing method, device, equipment and storage medium - Google Patents
Credit interest rate differential pricing method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN113379456A CN113379456A CN202110655862.8A CN202110655862A CN113379456A CN 113379456 A CN113379456 A CN 113379456A CN 202110655862 A CN202110655862 A CN 202110655862A CN 113379456 A CN113379456 A CN 113379456A
- Authority
- CN
- China
- Prior art keywords
- current
- credit
- customer
- model
- pricing
- 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
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000012549 training Methods 0.000 claims abstract description 30
- 238000004364 calculation method Methods 0.000 claims abstract description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 14
- 230000002776 aggregation Effects 0.000 claims description 11
- 238000004220 aggregation Methods 0.000 claims description 11
- 238000013475 authorization Methods 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 8
- 238000005259 measurement Methods 0.000 abstract description 10
- 230000008901 benefit Effects 0.000 abstract description 8
- 238000012545 processing Methods 0.000 description 10
- 230000007423 decrease Effects 0.000 description 6
- 235000003642 hunger Nutrition 0.000 description 6
- 230000035922 thirst Effects 0.000 description 6
- 230000004069 differentiation Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- RWSOTUBLDIXVET-UHFFFAOYSA-N Dihydrogen sulfide Chemical compound S RWSOTUBLDIXVET-UHFFFAOYSA-N 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012954 risk control Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0283—Price estimation or determination
-
- 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)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Technology Law (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention discloses a credit granting interest rate differential pricing method, a device, equipment and a storage medium, wherein the method comprises the following steps: determining a current client and a client class to which the current client belongs as a current client class; inputting credit data of the current customer into a risk pricing model corresponding to the class of the current customer group to obtain a risk pricing score of the current customer; inputting the risk pricing score of the current customer into a measuring and calculating model corresponding to the current customer group category to obtain the credit granting and interest rate of the current customer; the risk pricing model of any customer group category is obtained by training credit data and risk pricing scores of customers which historically belong to the any customer group category, and the measuring and calculating model of any customer group category is a model capable of obtaining corresponding preferred credit granting and interest rate based on the risk pricing scores of any customers in the any customer group category. The method and the device can realize accurate measurement and calculation of the credit granting interest rate, and further avoid the problems of loss of unmatched risk and income and incapability of maximizing benefits.
Description
Technical Field
The invention relates to the technical field of computer information processing, in particular to a credit granting rate differential pricing method, device, equipment and storage medium.
Background
In the credit market, the management of credit granting rate is the key to risk control and realization of income increase in the life cycle of the loan; in the credit granting link in the prior art, all clients are generally priced according to a unified standard, and the inventor finds that the credit granting rate calculation is inaccurate in the mode, so that the problems of loss of unmatched risk and income and incapability of maximizing benefits are caused.
Disclosure of Invention
The invention aims to provide a credit granting rate differential pricing method, device, equipment and storage medium, which can realize accurate measurement and calculation of the credit granting rate, and further avoid the problems of loss of unmatched risk and income and incapability of maximizing benefits.
In order to achieve the above purpose, the invention provides the following technical scheme:
a credit interest rate differential pricing method comprises the following steps:
determining a client needing to realize credit granting interest rate pricing as a current client, and determining a client group category to which the current client belongs in a plurality of preset client group categories as a current client group category;
inputting credit data of the current customer into a risk pricing model corresponding to the current customer class, and obtaining data output by the risk pricing model as a risk pricing score of the current customer; the risk pricing model of any customer group category is obtained by utilizing credit data of customers which historically belong to the any customer group category and corresponding risk pricing scores in advance for training;
inputting the risk pricing score of the current customer into a measuring and calculating model corresponding to the current customer group category to obtain data output by the measuring and calculating model as the credit and interest rate of the current customer; the measuring and calculating model of any customer group category is a model which is acquired in advance and can obtain a corresponding preferable credit and interest granting rate based on the risk pricing score of any customer in the any customer group category.
Preferably, before the risk pricing score of the current customer is input into the calculation model corresponding to the current customer group category, the method further includes:
determining the score group to which the risk pricing score of the current client belongs as the current group, and updating the risk pricing score of the current client into the unified risk pricing score of the current group; wherein the scores are grouped by dividing all risk pricing scores which can be possessed by the client in advance.
Preferably, after updating the risk pricing score of the current client to the uniform risk pricing score of the current group, the method further includes:
and determining interest rate intervals containing all credit granting interest rates which can be possessed by the clients in the current customer group category, inputting the risk pricing score of the current client into a measuring model corresponding to the current customer group category, and simultaneously inputting the interest rate intervals corresponding to the current customer group category into the measuring model corresponding to the current customer group category, so that the credit granting interest rates obtained by the measuring model belong to the interest rate intervals corresponding to the current customer group category.
Preferably, the obtaining of the calculation model includes:
obtaining an initial model for determining a corresponding NPV value by using interest income, bad account loss and capital cost; the bad account loss is calculated based on the risk pricing score, and the interest income is calculated based on the credit granting rate;
determining a calculation model based on the initial model; the measuring and calculating model is a model which can obtain the credit granting rate which enables the NPV value to be optimal and belongs to the corresponding interest rate interval to be the preferred credit granting rate.
Preferably, the risk pricing model is obtained by training credit data of the customers of any historical customer group category and corresponding risk pricing scores, and the method comprises the following steps:
acquiring credit data and corresponding risk pricing scores of clients of any historical customer group category;
training a preset machine learning algorithm by using the obtained credit data and the corresponding risk pricing scores to obtain a corresponding risk pricing model, determining the weight occupied by each index data contained in the credit data used for training in the training process, and determining the index data corresponding to the weight meeting the requirements as the moulding-in variables corresponding to any passenger group category;
correspondingly, inputting the credit data of the current customer into the risk pricing model corresponding to the current customer group category, including:
and inputting index data corresponding to the model entering variables corresponding to the current guest group category in the credit data of the current customer into the risk pricing model corresponding to the current guest group category.
Preferably, the determining that the guest group category to which the current guest belongs in the preset multiple guest group categories is the current guest group category includes:
performing feature aggregation on the credit granting tag data of the current customer based on a pre-obtained clustering index threshold value to obtain the class of the current customer as the class of the current customer;
correspondingly, obtaining the clustering index threshold includes:
the method comprises the steps of obtaining credit authorization label data of a plurality of historical customers, clustering the obtained credit authorization label data of the customers to obtain a plurality of customer group categories to which the customers belong respectively, and determining a clustering index threshold value used when the customers are subjected to feature aggregation in the clustering process to obtain the corresponding customer group categories.
Preferably, the clustering the acquired credit granting tag data of the plurality of clients includes:
and clustering the acquired credit granting label data of the plurality of clients by using a density clustering algorithm and/or a hierarchical clustering algorithm.
A credit interest rate differential pricing device comprises:
a determination module to: determining a client needing to realize credit granting interest rate pricing as a current client, and determining a client group category to which the current client belongs in a plurality of preset client group categories as a current client group category;
a score acquisition module to: inputting credit data of the current customer into a risk pricing model corresponding to the current customer class, and obtaining data output by the risk pricing model as a risk pricing score of the current customer; the risk pricing model of any customer group category is obtained by utilizing credit data of customers which historically belong to the any customer group category and corresponding risk pricing scores in advance for training;
an interest rate acquisition module to: inputting the risk pricing score of the current customer into a measuring and calculating model corresponding to the current customer group category to obtain data output by the measuring and calculating model as the credit and interest rate of the current customer; the measuring and calculating model of any customer group category is a model which is acquired in advance and can obtain a corresponding preferable credit and interest granting rate based on the risk pricing score of any customer in the any customer group category.
A credit interest rate differential pricing device, comprising:
a memory for storing a computer program;
a processor, configured to implement the steps of the credit granting rate differentiation pricing method according to any one of the above items when executing the computer program.
A computer readable storage medium, having a computer program stored thereon, which when executed by a processor, implements the steps of the method for differentiated pricing of credit rates as described in any one of the above.
The invention provides a credit granting interest rate differential pricing method, a device, equipment and a storage medium, wherein the method comprises the following steps: determining a client needing to realize credit granting interest rate pricing as a current client, and determining a client group category to which the current client belongs in a plurality of preset client group categories as a current client group category; inputting credit data of the current customer into a risk pricing model corresponding to the current customer class, and obtaining data output by the risk pricing model as a risk pricing score of the current customer; inputting the risk pricing score of the current customer into a measuring and calculating model corresponding to the current customer group category to obtain data output by the measuring and calculating model as the credit and interest rate of the current customer; the risk pricing model of any customer group category is obtained by utilizing credit data of customers which historically belong to the any customer group category and corresponding risk pricing scores in advance for training, and the measuring and calculating model of the any customer group category is a model which is obtained in advance and can obtain corresponding preferred credit granting rate based on the risk pricing scores of any customers in the any customer group category. After the category of the customer group to which the customer belongs is determined, the risk pricing model corresponding to the customer group to which the customer belongs is used for determining the risk pricing score of the customer based on the credit data of the customer, then the measuring and calculating model corresponding to the customer group to which the customer belongs is used for measuring and calculating the preferred credit granting rate of the customer based on the risk pricing score of the customer, and the customers belonging to different customer groups have different characteristics, so that the model corresponding to the customer group to which the customer belongs is used for determining the credit granting rate of the customer, namely the model corresponding to the characteristics of the customer is used for determining the credit granting rate of the customer, and therefore differentiated credit granting rate pricing among different customers is achieved, accurate measuring and calculating of the credit granting rate can be achieved, and the problems that risk gain loss is unmatched and benefits cannot be maximized are avoided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a credit granting interest rate differential pricing method according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating an acquisition of a measurement model in a credit granting rate differentiated pricing method according to an embodiment of the present invention;
fig. 3 is a flowchart illustrating an acquisition of a risk pricing model in the credit interest rate differentiation pricing method according to the embodiment of the present invention;
fig. 4 is a flowchart for acquiring a clustering model in a credit granting rate differentiation pricing method provided by the embodiment of the invention;
fig. 5 is a flowchart of a differentiated pricing method for credit granting rate according to an embodiment of the present invention in a specific implementation manner;
fig. 6 is a schematic structural diagram of a differentiated pricing device for credit granting rate according to an embodiment of the present invention;
fig. 7 is a schematic diagram of a credit interest rate differential pricing device according to an embodiment of the present invention;
fig. 8 is a schematic diagram of a computer-readable storage medium according to an embodiment of the present invention.
Detailed Description
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 only a part of the embodiments of the present invention, and not all of the embodiments. 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.
Referring to fig. 1, a flowchart of a credit interest rate differential pricing method according to an embodiment of the present invention is shown, where the method includes:
s11: and determining the current customer needing to realize credit granting interest rate pricing as the current customer, and determining the current customer class of the current customer in the preset multiple customer classes as the current customer class.
The execution main body of the credit granting rate differential pricing method provided by the embodiment of the invention can be a corresponding credit granting rate differential pricing device and equipment, the credit granting rate differential pricing device and the equipment can be collectively called a pricing engine, and the execution main body of the credit granting rate differential pricing method is used as the pricing engine for specific description below.
Wherein, the interest rate refers to the ratio of interest amount to loan amount (principal) in a certain period, the credit and loan is similar to the credit card function, but has interest, and the corresponding credit and loan interest rate is the interest rate of the credit and loan; the client is a person who needs to transact business (apply for credit and loan) at the bank. In order to realize corresponding credit granting rate pricing aiming at the characteristics of customers and realize differentiated credit granting rate pricing among different customers, the embodiment of the application can predetermine a plurality of customer group categories according to the characteristics of different customers, wherein the customers belonging to the same customer group category have similar characteristics, and the customers belonging to different customer group categories have larger characteristic difference; based on this, the embodiment of the application can preset corresponding risk pricing models and measuring and calculating models for different customer group categories, and further when credit granting rate pricing is implemented for customers belonging to any customer group category, the risk pricing scores and credit granting rates of the customers need to be respectively determined according to the corresponding risk pricing models and measuring and calculating models of any customer group category. Specifically, according to the embodiment of the application, any client needing to realize credit granting interest rate pricing at present can be determined as a current client, the class of the current client is determined based on the characteristics of the current client, the class of the current client is further determined as the class of the current client, and corresponding credit granting interest rate pricing is realized for the current client belonging to the class of the current client.
S12: inputting credit data of the current customer into a risk pricing model corresponding to the current customer class to obtain data output by the risk pricing model as a risk pricing score of the current customer; the risk pricing model of any customer group category is obtained by training in advance by using credit data of customers which historically belong to the any customer group category and corresponding risk pricing scores.
The training principles of the risk pricing models respectively corresponding to the passenger group classes are the same, for any passenger group class, credit data and corresponding risk pricing scores of multiple customers which historically belong to the passenger group class can be obtained, and then a preset machine learning algorithm is trained by using the obtained credit data and corresponding risk pricing scores of the multiple customers which historically belong to the passenger group class to obtain the corresponding risk pricing model. After the class of the current customer is determined to be the current class of the customer, the credit data of the current customer can be obtained, the credit data of the current customer is used as the input of the risk pricing model corresponding to the current class of the customer, and the data output by the risk pricing model can be obtained and used as the risk pricing score of the current customer. The credit data can include basic customer information, customer fund hunger and thirst degree, customer viscosity program, risk overflow level and the like, the basic customer information can include gender, academic calendar, age, unit property, public deposit payment condition, social security data and the like, the customer fund hunger and thirst degree can include examination and approval query times, credit card limit utilization rate, unsettled loan number and the like, the customer viscosity degree can include bank account opening duration of a customer, bank financial assets, bank credit card grades and the like, and the risk overflow level can include historical overdue number, house loan number, residence card or quasi-loan card average credit line and the like. It should be noted that the machine learning algorithm may be a GBDT (Gradient Boosting Decision Tree) algorithm, or may be another machine learning algorithm (such as a support vector machine algorithm, a bayesian algorithm, etc.) selected according to actual needs, and all of them are within the protection scope of the present invention.
S13: inputting the risk pricing score of the current customer into a measuring and calculating model corresponding to the current customer group class to obtain data output by the measuring and calculating model as the credit granting rate of the current customer; the measuring and calculating model of any customer group category is a model which is acquired in advance and can obtain a corresponding preferable credit and interest granting rate based on the risk pricing score of any customer in the any customer group category.
For any guest group class, a measuring and calculating model corresponding to the guest group class can be established; therefore, after the risk pricing score of the current customer is obtained, calculation can be carried out by utilizing a measuring and calculating model corresponding to the current customer group category and based on the risk pricing score of the current customer, and the credit granting rate which can enable the bank to have higher income, namely the preferred credit granting rate, is finally determined, so that the bank can have higher income after providing credit granting loan for the current customer.
After the category of the customer group to which the customer belongs is determined, the risk pricing model corresponding to the customer group to which the customer belongs is used for determining the risk pricing score of the customer based on the credit data of the customer, then the measuring and calculating model corresponding to the customer group to which the customer belongs is used for measuring and calculating the preferred credit granting rate of the customer based on the risk pricing score of the customer, and the customers belonging to different customer groups have different characteristics, so that the model corresponding to the customer group to which the customer belongs is used for determining the credit granting rate of the customer, namely the model corresponding to the characteristics of the customer is used for determining the credit granting rate of the customer, and therefore differentiated credit granting rate pricing among different customers is achieved, accurate measuring and calculating of the credit granting rate can be achieved, and the problems that risk gain loss is unmatched and benefits cannot be maximized are avoided.
Before the differential pricing method for credit granting rate provided by the embodiment of the invention inputs the risk pricing score of the current customer into the measurement model corresponding to the current customer group category, the method may further include:
determining the score group to which the risk pricing score of the current client belongs as the current group, and updating the risk pricing score of the current client into the unified risk pricing score of the current group; wherein, the grading grouping is obtained by dividing all risk pricing grades which can be possessed by the client in advance.
It should be noted that all the guest group classes may correspond to a uniform score group, and different guest group classes may also correspond to corresponding score groups; specifically, for the former case, all risk pricing scores that the user can have can be divided to obtain at least one corresponding score group, and then when the score group to which the risk pricing score of the current client belongs is determined, the score group to which the risk pricing score of the current client belongs is directly determined; for the latter case, all risk pricing scores that a user belonging to any customer group category can have are divided to obtain at least one corresponding score group, that is, the score group corresponding to the any customer group category, and when determining the score group to which the risk pricing score of the current customer belongs, the score group corresponding to the current customer group category to which the risk pricing score of the current customer belongs needs to be determined.
The embodiment of the application specifically describes that different customer group classes respectively have corresponding rating groups, and for any customer group class, the embodiment of the application can divide all risk pricing ratings which the customers in the any customer group class can have, so as to obtain a plurality of rating groups of risk pricing ratings corresponding to the any customer group class, each rating group has a corresponding unified risk pricing rating, and in a specific implementation mode, the unified risk pricing rating of any rating group can be an average value of all risk pricing ratings in the any rating group, and can also be other values set according to actual needs, and all values are within the protection range of the invention; correspondingly, after the risk pricing score of the current customer is determined, the score grouping corresponding to the current customer group category to which the risk pricing score of the current customer belongs can be determined, and then the uniform risk pricing score of the score grouping is used as the risk pricing score of the current customer, so that corresponding calculation is realized by subsequently using the uniform risk pricing score of the score grouping as the risk pricing score of the current customer, the number of risk pricing scores to be calculated subsequently is reduced, namely, the calculation amount is reduced, and the calculation efficiency is improved.
The credit granting interest rate differential pricing method provided by the embodiment of the invention can update the risk pricing score of the current customer into the unified risk pricing score of the current group, and can further include:
and determining interest rate intervals containing all credit granting interest rates which can be possessed by the clients in the current customer group category, inputting the risk pricing score of the current client into the measuring and calculating model corresponding to the current customer group category, and simultaneously inputting the interest rate intervals corresponding to the current customer group category into the measuring and calculating model corresponding to the current customer group category, so that the credit granting interest rates obtained by the measuring and calculating model belong to the interest rate intervals corresponding to the current customer group category.
It should be noted that, all the credit granting interest rates that the client can have in each guest group category may be determined in advance, and then an interest rate interval composed of all the credit granting interest rates that the client can have in each guest group category may be determined, that is, the interest rate interval of any guest group category is an interval composed of all the credit granting interest rates that the client can have in any guest group category; correspondingly, when the risk pricing score of the current customer is input into the measuring and calculating model corresponding to the current customer group category to which the current customer belongs, the interest rate interval of the current customer group category to which the current customer belongs is input into the measuring and calculating model corresponding to the current customer group category to which the current customer belongs, so that the measuring and calculating model can realize calculation of the credit granting interest rate based on the risk pricing score of the current customer, and the calculated credit granting interest rate belongs to the interest rate interval corresponding to the current customer group category to which the current customer belongs, and therefore the obtained credit granting interest rate of the current customer is more reasonable through measuring and calculating.
The method for differentiated pricing of credit granting rate provided by the embodiment of the invention obtains a measuring model, and can comprise the following steps:
obtaining an initial model for determining a corresponding NPV value by using interest income, bad account loss and capital cost; the bad account loss is calculated based on the risk pricing score, and the interest income is calculated based on the credit granting rate;
determining a measurement model based on the initial model; the measuring and calculating model is a model which can obtain the credit granting rate which enables the NPV value to be optimal and belongs to the corresponding interest rate interval to be the preferred credit granting rate.
The measuring and calculating model of any customer group category is obtained based on corresponding data of customers in the any customer group category; it should be noted that the NPV Value (Net Present Value) refers to the difference between the current Value of future money (cash) inflow (income) and the current Value of future money (cash) outflow (expenditure), and in the embodiment of the Present application, refers to the income obtained by the bank for the credit loan issued by the customer. Specifically, in the embodiment of the present application, the corresponding NPV value may be calculated by using the interest income, the bad account loss, and the capital cost, and the calculation formula may be as follows:
interest profit PNAverage credit limit average usage rate n execution rate of the groupN；
Bad account loss ENAverage credit line average rate of usage and expected bad account rate of the group nN；
Capital cost CNAverage credit limit and average branch rate and one year ftp integrated cost nN；
NPVN＝fx(interest profit P)NBad ledger loss EN) Capital cost CN；
Wherein, NPVNSetting a present value conversion function f (x) for the NPV value because interest income and bad account loss are future occurrence values; in addition, because the risk pricing scores of all clients in the same scoring group are the uniform risk pricing scores of the scoring group, credit granting amount, supporting rate, execution interest rate (same credit granting interest rate) and expected bad account rate of all clients in the same scoring group are considered to be the same, and n is the same for any scoring groupNThe average credit line is the historical average credit line level of all the clients belonging to the arbitrary grading group, and the average support rate is the number of the clients belonging to the arbitrary grading groupThe group execution interest rate is the credit rate of the arbitrary grading group (namely the credit rate of the current customer), which is a measured value and needs trial calculation by a deduction method, the group expected bad account rate is a unified risk Pricing score (namely the risk Pricing score of the current customer) corresponding to the arbitrary grading group, and ftp (Funds Transfer Pricing, internal fund Transfer Pricing) refers to an internal operation management mode that the fund is transferred for full payment by the bank internal fund center and the business operation unit according to a certain rule so as to achieve the purposes of accounting the business fund cost or income, and the fund collected by each debt business of the business operation unit is transferred to the fund center in full payment by the ftp price of the business; the funds required for each asset industry transaction are purchased from the funds management department at the full FTP price for that transaction.
Taking the NPV value calculation formula as an initial model, and then obtaining a measurement model for performing deductive calculation on the initial model to obtain the optimal credit rate; specifically, the deduction trial calculation is performed by adjusting the execution interest rate of each group of score groups until the NPV value meets the set condition (the set condition may be that the NPV value is the maximum, or may be that the threshold set by considering factors such as market competition is larger than the threshold set according to actual needs); obtaining the value of the 'optimal interest rate' in the interest rate interval of the corresponding passenger group category according to the deduction trial calculation result, and outputting the value as the credit granting interest rate; therefore, the credit granting rate meeting the requirement can be effectively and accurately obtained.
In a specific implementation manner, as shown in fig. 2, the step of determining the credit rate implemented by the measurement model may be as follows:
(1) the measured variables to be input to the measurement model can be as follows:
(2) performing corresponding deduction, specifically including:
trial calculation is carried out by adjusting the execution interest rate of each group until the NPV value meets the following conditions:
a. the NPV value of each group is greater than 0;
b. each group of NPV values follows a generally normal distribution, i.e., the client occupancy of the middle groups is high, and the left and right sides are low (the client occupancy of the very low execution interest rate and the very high execution interest rate is low);
c. the values of all groups (NPV value/number of people) are equal or have small difference, namely the low interest of the low risk group and the high interest of the high risk group are met, and the NPV value of all groups is in a more balanced state.
(3) The outputting of the execution interest rate may specifically include:
The credit rating differentiation pricing method provided by the embodiment of the invention obtains a risk pricing model by using credit data of customers of any historical customer group category and corresponding risk pricing scoring training, and can comprise the following steps:
acquiring credit data and corresponding risk pricing scores of clients of any historical customer group category;
training a preset machine learning algorithm by using the obtained credit data and the corresponding risk pricing scores to obtain a corresponding risk pricing model, determining the weight occupied by each index data contained in the credit data used for training in the training process, and determining the index data corresponding to the weight meeting the requirements as the moulding-in variables corresponding to any passenger group category;
accordingly, entering credit data for the current customer into the risk pricing model corresponding to the current customer category may include:
and inputting index data corresponding to the model entering variables corresponding to the current guest group category in the credit data of the current customer into the risk pricing model corresponding to the current guest group category.
It should be noted that each item of data included in the credit data may be referred to as index data, and since more index data are collected in the application, but some index data have a larger influence on the risk pricing score and some index data have a smaller influence on the risk pricing score, in order to further reduce the data amount of risk pricing model learning and further improve the determination efficiency of the risk pricing score, the embodiment of the application may determine the weight occupied by each index data in the training process in the process of training the machine learning algorithm by using the credit data of the customers of any historical customer group category and the corresponding risk pricing score, and the larger the occupied weight is, the larger the influence on the risk pricing score is, the corresponding application selects the index parameter meeting the requirements (larger, for example, larger than the threshold value set according to actual needs) as the entry variable corresponding to the any customer group category, and then only selecting index data corresponding to the model-entering variables of the current customer class in the credit data of the current customer as data to be learned by the risk pricing model, and inputting the data to the risk pricing model to learn the corresponding risk pricing score.
In a specific implementation, as shown in fig. 3, the training process of the risk pricing model may specifically include:
(1) selecting a mold entering variable:
the credit data may include: basic conditions of the client, including gender, academic calendar, age, unit property, accumulation deposit and payment condition, social security data and the like; the degree of hunger and thirst, including the number of examination and approval, credit card limit usage rate, outstanding loan strokes, etc.; the client viscosity degree comprises bank account opening time, bank financial assets, bank credit card grade and the like; the risk premium level includes the historical overdue amount, the housing loan amount, the average credit line of the credit card or quasi-credit card, etc.
(2) Establishing a model:
and modeling by adopting a GBDT algorithm to obtain a corresponding risk pricing model.
(3) And (3) model evaluation:
verifying the distribution condition of the risk pricing model, wherein the distribution of the risk pricing model is in accordance with the following rules: as the number of model groups (score groups) increases, the quality of the client decreases, the credit passing rate decreases, the average credit line decreases, the spending rate increases, and the lower the credit-granting ability of the client is reflected, the higher the thirst degree of the hunger for the fund is;
(4) model deployment:
and outputting the risk pricing scores and the score groups of the risk pricing model, and determining corresponding credit granting rates based on the risk pricing scores and the score groups. In addition, the risk pricing scores of any customer in any customer group category are input into the measuring and calculating model, a plurality of credit granting interest rate intervals enabling the corresponding NPV value to meet the requirements can be obtained, and then the preferred credit granting interest rate is selected from the intervals as the credit granting interest rate corresponding to the any customer. And when the interest rate interval corresponding to each customer group category is determined, the risk pricing score of each score group in any customer group category can be input into the measuring and calculating model, and the corresponding interval formed by the corresponding credit granting interest rates output by the measuring and calculating model is the interest rate interval corresponding to any customer group category.
It should be noted that, as shown in fig. 3, after obtaining credit data and corresponding risk pricing scores (samples) of customers of any historical customer category, modeling sample screening (screening out incomplete data that do not meet corresponding specifications) may be performed, then a training set and a test set are divided for retained samples, modeling is performed based on the training set to obtain a corresponding risk pricing model, verification of the risk pricing model is performed based on the test set, and it is determined that the risk pricing model can be used to obtain the corresponding risk pricing score after the verification of the risk pricing model is passed.
The method for differentially pricing the credit granting interest rate provided by the embodiment of the invention determines the class of the current customer group to which the current customer belongs in the preset classes of the multiple customer groups as the class of the current customer group, and comprises the following steps:
performing feature aggregation on the credit granting tag data of the current customer based on a pre-obtained clustering index threshold value to obtain the class of the current customer as the class of the current customer;
correspondingly, obtaining the clustering index threshold includes:
the method comprises the steps of obtaining credit authorization label data of a plurality of historical customers, clustering the obtained credit authorization label data of the customers to obtain a plurality of customer group categories to which the customers belong respectively, and determining a clustering index threshold value used when the customers are subjected to feature aggregation in the clustering process to obtain the corresponding customer group categories.
The credit label data can comprise the dimensions of basic conditions (industry, unit property, gender and region), income level, liability level, financial asset level, credit card grade and the like of a client; and the process of clustering to obtain a clustering model may include: obtaining credit granting tag data of a plurality of historical customers as input variables; inputting the number k of clusters and the maximum iteration number N, and initializing k cluster centers according to input variables; distributing each credit label data (data object) to the class with the closest distance to form a primary cluster; repeating the above process until convergence or iteration number reaches N; and outputting a clustering index threshold according to the final clustering result. The clustering model is a model for determining the class of the customer group to which the customer belongs according to each clustering index threshold, specifically, when determining the class to which the current customer belongs, the clustering model compares each data in the credit granting tag data of the current customer with the clustering index threshold of the corresponding data, so that when each data in the credit granting tag data of the current customer meets the corresponding clustering index threshold of any customer group, the class of the customer group to which the current customer belongs is determined to be the class of the any customer group, and thus, the accurate determination of the class to which the current customer belongs is realized through the mode.
In one implementation, as shown in fig. 4, the determining process of the clustering model may include:
(1) obtaining credit card label data of a plurality of historical customers as input variables, wherein the credit card label data comprise the basic conditions (industry, unit property, gender and region), income level, liability level, financial asset level, credit card grade and other dimensions of the customers;
(2) selecting a clustering algorithm (such as density clustering, hierarchical clustering and the like, namely clustering the credit granting label data of a plurality of acquired clients, wherein the density clustering algorithm and/or the hierarchical clustering algorithm can be used for clustering the credit granting label data of the plurality of acquired clients), determining the number k and the maximum iteration number N of input clusters, and clustering according to input variables;
(3) and the clustering model carries out feature aggregation on the customers and outputs a clustering index threshold value.
In a specific implementation manner, as shown in fig. 5, the method for differentiated pricing of credit rates according to an embodiment of the present invention may include the following steps:
1. obtaining at least one clustering model; the clustering model is used for carrying out feature aggregation on different passenger group categories and outputting clustering index thresholds of the passenger group categories.
Wherein obtaining at least one clustering model may include:
(1) acquiring client credit authorization tag data;
(2) based on the credit granting label data of the customer, selecting a clustering algorithm (such as density clustering, hierarchical clustering and the like), inputting the number k of clusters and the maximum iteration number N for clustering, and outputting a clustering index threshold value of the category of the customer group;
(3) and performing feature aggregation on the passenger group categories according to the clustering index threshold value output by the clustering model, and outputting classification labels representing the passenger group categories.
2. Obtaining at least one risk pricing model; wherein the risk pricing model is used to evaluate credit granting rates for different customer class categories.
Wherein obtaining at least one risk pricing model may comprise:
(1) extracting significance indexes from several dimensions of basic information of the customer, the degree of hunger and thirst of the capital of the customer, the historical overdue of the customer and the degree of bank relation, and outputting a modeling variable;
(2) modeling by taking the model entering variable as an input item, and verifying that the model conforms to the following rules: as the number of model groups increases, the quality of the customer decreases, the credit passing rate decreases, the average credit line decreases, the spending rate increases, and the lower the credit worthiness of the customer is, the higher the thirst hunger on the fund is. Deploying the model and outputting the score and grouping of the model;
(3) and (4) performing interest rate interval grading by using the model groups as input items, and outputting interest rate pricing intervals (namely interest rate intervals) of each passenger group type.
3. And obtaining a measuring and calculating model for evaluating the value of the optimal interest rate in the interest rate interval.
The acquiring of the NPV measurement model may include:
and (4) measuring and calculating the NPV value from three important input dimensions of interest income P, bad account loss E and capital cost C to obtain an 'optimal interest rate' value in a corresponding interest rate interval, and outputting the value as the credit granting interest rate.
According to the invention, through establishing a plurality of models, credit granting interest rate judgment of different risk customer groups is realized, effective control based on a risk and income matching principle is realized, credit granting risk of a financial platform is reduced, refined and differentiated interest rate operation is realized at the same time, and further benefit maximization of the financial platform is realized; in addition, while the differentiated credit granting rate achieves 'premium punishment', the interest rate pricing range can be adjusted according to cost change, profit targets and market levels, so that the financial platform is helped to realize flexible and scientific market adjustment and benefit gain; therefore, the method and the device can accurately evaluate the proper pricing interest rate according to the risk characteristics and the interest rate sensitivity preference of the client so as to achieve the purpose of matching the optimal risk and income.
The embodiment of the present invention further provides a credit interest rate differential pricing device, as shown in fig. 6, the device may specifically include:
a determining module 11, configured to: determining a client needing to realize credit granting interest rate pricing as a current client, and determining a client group category to which the current client belongs in a plurality of preset client group categories as a current client group category;
a score obtaining module 12, configured to: inputting credit data of the current customer into a risk pricing model corresponding to the current customer class to obtain data output by the risk pricing model as a risk pricing score of the current customer; the risk pricing model of any customer group category is obtained by utilizing credit data of customers which historically belong to the any customer group category and corresponding risk pricing scores in advance for training;
an interest rate obtaining module 13 configured to: inputting the risk pricing score of the current customer into a measuring and calculating model corresponding to the current customer group class to obtain data output by the measuring and calculating model as the credit granting rate of the current customer; the measuring and calculating model of any customer group category is a model which is acquired in advance and can obtain a corresponding preferable credit and interest granting rate based on the risk pricing score of any customer in the any customer group category.
The differentiated pricing device for credit granting rate provided by the embodiment of the invention can also comprise:
an update module to: before the risk pricing scores of the current clients are input into the measuring and calculating models corresponding to the current client group, determining that the scores to which the risk pricing scores of the current clients belong are grouped into a current group, and updating the risk pricing scores of the current clients into unified risk pricing scores of the current group; wherein, the grading grouping is obtained by dividing all risk pricing grades which can be possessed by the client in advance.
In the differentiated pricing device for credit granting interest rate provided by the embodiment of the invention, the interest rate obtaining module is further configured to: after the risk pricing score of the current customer is updated to the unified risk pricing score of the current group, an interest rate interval containing all credit granting interest rates which can be possessed by the customer in the current customer group category is determined, the risk pricing score of the current customer is input into a measuring and calculating model corresponding to the current customer group category, meanwhile, the interest rate interval corresponding to the current customer group category is input into the measuring and calculating model corresponding to the current customer group category, and therefore the credit granting interest rate obtained by the measuring and calculating model belongs to the interest rate interval corresponding to the current customer group category.
The differentiated pricing device for credit granting rate provided by the embodiment of the invention can also comprise:
a model acquisition module to: obtaining an initial model for determining a corresponding NPV value by using interest income, bad account loss and capital cost; determining a measurement model based on the initial model; the bad account loss is calculated based on the risk pricing score, the interest income is calculated based on the credit granting rate, and the measuring and calculating model is a model capable of obtaining the credit granting rate which enables the NPV value to be optimal and the credit granting rate belonging to the corresponding interest rate interval to be optimal
The differentiated pricing device for credit granting rate provided by the embodiment of the invention can also comprise:
a training module to: acquiring credit data and corresponding risk pricing scores of clients of any historical customer group category; training a preset machine learning algorithm by using the obtained credit data and the corresponding risk pricing scores to obtain a corresponding risk pricing model, determining the weight occupied by each index data contained in the credit data used for training in the training process, and determining the index data corresponding to the weight meeting the requirements as the moulding-in variables corresponding to any passenger group category;
accordingly, the score obtaining module may include:
an input unit for: and inputting index data corresponding to the model entering variables corresponding to the current guest group category in the credit data of the current customer into the risk pricing model corresponding to the current guest group category.
The differentiated pricing device for credit granting rate provided by the embodiment of the invention has the following determining modules:
a determination unit configured to: performing feature aggregation on the credit granting tag data of the current customer based on a pre-obtained clustering index threshold value to obtain the class of the current customer as the class of the current customer;
correspondingly, the credit granting rate differentiation pricing device may further include:
a threshold acquisition module to: the method comprises the steps of obtaining credit authorization label data of a plurality of historical customers, clustering the obtained credit authorization label data of the customers to obtain a plurality of customer group categories to which the customers belong respectively, and determining a clustering index threshold value used when the customers are subjected to feature aggregation in the clustering process to obtain the corresponding customer group categories.
In the differentiated pricing device for credit granting rate provided by the embodiment of the present invention, the threshold obtaining module may specifically include:
a clustering unit configured to: and clustering the acquired credit granting label data of the plurality of clients by using a density clustering algorithm and/or a hierarchical clustering algorithm.
The embodiment of the invention also provides differentiated pricing equipment for credit rate, which can comprise:
a memory for storing a computer program;
and the processor is used for realizing the steps of any one of the credit and interest rate differential pricing methods when executing the computer program.
The embodiment of the invention also provides a computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when being executed by a processor, the computer program can realize the steps of any one of the credit granting rate differential pricing methods.
Those skilled in the art will appreciate that the modules in the above-described embodiments of the apparatus may be distributed as described in the apparatus, and may be correspondingly modified and distributed in one or more apparatuses other than the above-described embodiments. The modules of the above embodiments may be combined into one module, or further split into multiple sub-modules.
Those skilled in the art will appreciate that implementing all or a portion of the above described steps is implemented as a program (computer program) executed by a computer data processing apparatus; when the computer program is executed, the method provided by the invention can be realized. Furthermore, the computer program may be stored in a computer readable storage medium, which may be a readable storage medium such as a magnetic disk, an optical disk, a ROM, a RAM, or a storage array composed of a plurality of storage media, such as a magnetic disk or a magnetic tape storage array. The storage medium of (1) is not limited to centralized storage but may also be distributed storage, such as cloud storage based on cloud computing.
The following describes an embodiment of an electronic device (i.e., a credit-interest-rate-differentiated pricing device) of the present invention, which may be regarded as a specific physical implementation for the above-mentioned embodiments of the method and apparatus of the present invention. Details described in the embodiments of the electronic device of the invention should be considered supplementary to the embodiments of the method or apparatus described above; for details which are not disclosed in embodiments of the electronic device of the invention, reference may be made to the above-described embodiments of the method or the apparatus.
Fig. 7 is a block diagram of an exemplary embodiment of an electronic device according to the present invention. An electronic apparatus 200 according to this embodiment of the present invention is described below with reference to fig. 7. The electronic device 200 shown in fig. 7 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 7, the electronic device 200 is embodied in the form of a general purpose computing device. The components of the electronic device 200 may include, but are not limited to: at least one processing unit 210, at least one memory unit 220, a bus 230 connecting different system components (including the memory unit 220 and the processing unit 210), a display unit 240, and the like.
Wherein the storage unit is a memory, and stores a program code, which can be executed by the processing unit 210 (i.e. a processor), so that the processing unit 210 executes the steps according to various exemplary embodiments of the present invention described in the above method part of the present specification. For example, processing unit 210 may perform the steps shown in fig. 1.
The storage unit 220 may include readable media in the form of volatile storage units, such as a random access memory unit (RAM)2201 and/or a cache memory unit 2202, and may further include a read only memory unit (ROM) 2203.
The storage unit 220 may also include a program/utility 2204 having a set (at least one) of program modules 2205, such program modules 2205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 200 may also communicate with one or more external devices 300 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a client to interact with the electronic device 200, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 200 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 250. Also, the electronic device 200 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network such as the Internet) via the network adapter 260. The network adapter 260 may communicate with other modules of the electronic device 200 via the bus 230. It should be appreciated that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the electronic device 200, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments of the present invention described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to make a computing device (which can be a personal computer, a server, or a network device, etc.) execute the above-mentioned method according to the present invention. The computer program, when executed by a data processing apparatus, enables the computer readable medium to carry out the above-described methods of the invention. The computer program may be stored on one or more computer readable media, as shown in FIG. 8. The computer readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
A computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the client computing device, partly on the client device, as a stand-alone software package, partly on the client computing device and 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 client computing device over 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., over the internet using an internet service provider).
In summary, the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components in an implementation consistent with the invention may be implemented in practice using a general purpose data processing device, such as a microprocessor or a Digital Signal Processor (DSP). The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
While the foregoing embodiments have described the objects, aspects and advantages of the present invention in further detail, it should be understood that the present invention is not inherently related to any particular computer, virtual machine or electronic device, and various general-purpose machines may be used to implement the present invention. The present invention is not limited to the above embodiments, and any modifications, equivalent substitutions, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The invention is suitable for internet credit products or online credit granting products, has strong deployability and high flexibility, and can greatly meet the operation thought of fine and differentiated interest rates under the internet credit background so as to achieve the optimal risk-income matching.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A credit interest rate differential pricing method is characterized by comprising the following steps:
determining a client needing to realize credit granting interest rate pricing as a current client, and determining a client group category to which the current client belongs in a plurality of preset client group categories as a current client group category;
inputting credit data of the current customer into a risk pricing model corresponding to the current customer class, and obtaining data output by the risk pricing model as a risk pricing score of the current customer; the risk pricing model of any customer group category is obtained by utilizing credit data of customers which historically belong to the any customer group category and corresponding risk pricing scores in advance for training;
inputting the risk pricing score of the current customer into a measuring and calculating model corresponding to the current customer group category to obtain data output by the measuring and calculating model as the credit and interest rate of the current customer; the measuring and calculating model of any customer group category is a model which is acquired in advance and can obtain a corresponding preferable credit and interest granting rate based on the risk pricing score of any customer in the any customer group category.
2. The method of claim 1, wherein before inputting the risk pricing score of the current customer into the calculation model corresponding to the current customer class, further comprising:
determining the score group to which the risk pricing score of the current client belongs as the current group, and updating the risk pricing score of the current client into the unified risk pricing score of the current group; wherein the scores are grouped by dividing all risk pricing scores which can be possessed by the client in advance.
3. The method of claim 2, wherein after updating the risk pricing score of the current customer to the unified risk pricing score of the current group, further comprising:
and determining interest rate intervals containing all credit granting interest rates which can be possessed by the clients in the current customer group category, inputting the risk pricing score of the current client into a measuring model corresponding to the current customer group category, and simultaneously inputting the interest rate intervals corresponding to the current customer group category into the measuring model corresponding to the current customer group category, so that the credit granting interest rates obtained by the measuring model belong to the interest rate intervals corresponding to the current customer group category.
4. The method of claim 3, wherein obtaining the estimation model comprises:
obtaining an initial model for determining a corresponding NPV value by using interest income, bad account loss and capital cost; the bad account loss is calculated based on the risk pricing score, and the interest income is calculated based on the credit granting rate;
determining a calculation model based on the initial model; the measuring and calculating model is a model which can obtain the credit granting rate which enables the NPV value to be optimal and belongs to the corresponding interest rate interval to be the preferred credit granting rate.
5. The method of claim 4, wherein training a risk pricing model using credit data and corresponding risk pricing scores of customers of historically any customer class comprises:
acquiring credit data and corresponding risk pricing scores of clients of any historical customer group category;
training a preset machine learning algorithm by using the obtained credit data and the corresponding risk pricing scores to obtain a corresponding risk pricing model, determining the weight occupied by each index data contained in the credit data used for training in the training process, and determining the index data corresponding to the weight meeting the requirements as the moulding-in variables corresponding to any passenger group category;
correspondingly, inputting the credit data of the current customer into the risk pricing model corresponding to the current customer group category, including:
and inputting index data corresponding to the model entering variables corresponding to the current guest group category in the credit data of the current customer into the risk pricing model corresponding to the current guest group category.
6. The method of claim 5, wherein determining that the current client class of the plurality of client classes is the current client class comprises:
performing feature aggregation on the credit granting tag data of the current customer based on a pre-obtained clustering index threshold value to obtain the class of the current customer as the class of the current customer;
correspondingly, obtaining the clustering index threshold includes:
the method comprises the steps of obtaining credit authorization label data of a plurality of historical customers, clustering the obtained credit authorization label data of the customers to obtain a plurality of customer group categories to which the customers belong respectively, and determining a clustering index threshold value used when the customers are subjected to feature aggregation in the clustering process to obtain the corresponding customer group categories.
7. The method of claim 6, wherein clustering the obtained trust tag data for the plurality of customers comprises:
and clustering the acquired credit granting label data of the plurality of clients by using a density clustering algorithm and/or a hierarchical clustering algorithm.
8. A credit interest rate differential pricing device is characterized by comprising:
a determination module to: determining a client needing to realize credit granting interest rate pricing as a current client, and determining a client group category to which the current client belongs in a plurality of preset client group categories as a current client group category;
a score acquisition module to: inputting credit data of the current customer into a risk pricing model corresponding to the current customer class, and obtaining data output by the risk pricing model as a risk pricing score of the current customer; the risk pricing model of any customer group category is obtained by utilizing credit data of customers which historically belong to the any customer group category and corresponding risk pricing scores in advance for training;
an interest rate acquisition module to: inputting the risk pricing score of the current customer into a measuring and calculating model corresponding to the current customer group category to obtain data output by the measuring and calculating model as the credit and interest rate of the current customer; the measuring and calculating model of any customer group category is a model which is acquired in advance and can obtain a corresponding preferable credit and interest granting rate based on the risk pricing score of any customer in the any customer group category.
9. A credit interest rate differential pricing device, comprising:
a memory for storing a computer program;
a processor for implementing the steps of the credit-rate differential pricing method according to any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, wherein a computer program is stored on the computer-readable storage medium, and when executed by a processor, the computer program implements the steps of the method for differentiated pricing of credit as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110655862.8A CN113379456A (en) | 2021-06-11 | 2021-06-11 | Credit interest rate differential pricing method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110655862.8A CN113379456A (en) | 2021-06-11 | 2021-06-11 | Credit interest rate differential pricing method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113379456A true CN113379456A (en) | 2021-09-10 |
Family
ID=77574149
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110655862.8A Pending CN113379456A (en) | 2021-06-11 | 2021-06-11 | Credit interest rate differential pricing method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113379456A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118154303A (en) * | 2024-05-10 | 2024-06-07 | 杭银消费金融股份有限公司 | Differential adjustment method and system based on data analysis |
-
2021
- 2021-06-11 CN CN202110655862.8A patent/CN113379456A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118154303A (en) * | 2024-05-10 | 2024-06-07 | 杭银消费金融股份有限公司 | Differential adjustment method and system based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109460795A (en) | Classifier training method, apparatus, electronic equipment and computer-readable medium | |
| CN109035003A (en) | Anti- fraud model modelling approach and anti-fraud monitoring method based on machine learning | |
| CN106600369A (en) | Real-time recommendation system and method of financial products of banks based on Naive Bayesian classification | |
| CN108648074A (en) | Loan valuation method, apparatus based on support vector machines and equipment | |
| US20110238550A1 (en) | Systems and methods for predicting financial behaviors | |
| CN109961368A (en) | Data processing method and device based on machine learning | |
| CN108062674A (en) | Order fraud recognition methods, system, storage medium and electronic equipment based on GPS | |
| CN111985937A (en) | Method, system, storage medium and computer equipment for evaluating value information of transaction traders | |
| CN107516246A (en) | Determination method, determining device, medium and the electronic equipment of user type | |
| CN113344700A (en) | Wind control model construction method and device based on multi-objective optimization and electronic equipment | |
| CN111861487A (en) | Financial transaction data processing method, and fraud monitoring method and device | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| CN115526700A (en) | Risk prediction method and device and electronic equipment | |
| CN113379456A (en) | Credit interest rate differential pricing method, device, equipment and storage medium | |
| CN111667307B (en) | Method and device for predicting financial product sales volume | |
| CN117114689A (en) | Fraud detection model construction method, fraud detection model construction device, fraud detection model construction equipment and storage medium | |
| CN111144899A (en) | Method and device for identifying false transactions and electronic equipment | |
| Sun et al. | Determination of temporal stock investment styles via biclustering trading patterns | |
| CN115034685A (en) | Customer value evaluation method, customer value evaluation device and computer-readable storage medium | |
| CN115545909A (en) | Approval method, device, equipment and storage medium | |
| Mahjoub et al. | A hybrid model for customer credit scoring in stock brokerages using data mining approach | |
| CN113191570A (en) | Fund planning recommendation method, device and equipment based on deep learning | |
| Pulkkinen et al. | A multi-objective rule optimizer with an application to risk management | |
| US20210383466A1 (en) | Banking operation support system, banking operation support method, and banking operation support program | |
| Persson et al. | Comparing machine learning models for predicting stock market volatility using social media sentiment: A comparison of the predictive power of the Artificial Neural Network, Support Vector Machine and Decision Trees models on price volatility using social media sentiment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210910 |