CN114358519A - Intelligent credit limit interest rate adjusting method and device - Google Patents
Intelligent credit limit interest rate adjusting method and device Download PDFInfo
- Publication number
- CN114358519A CN114358519A CN202111534913.8A CN202111534913A CN114358519A CN 114358519 A CN114358519 A CN 114358519A CN 202111534913 A CN202111534913 A CN 202111534913A CN 114358519 A CN114358519 A CN 114358519A
- Authority
- CN
- China
- Prior art keywords
- module
- data
- client
- adjustment
- credit
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012544 monitoring process Methods 0.000 claims abstract description 48
- 238000012216 screening Methods 0.000 claims abstract description 44
- 238000004364 calculation method Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 34
- 230000000694 effects Effects 0.000 claims abstract description 27
- 238000002474 experimental method Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 14
- 230000002159 abnormal effect Effects 0.000 claims description 12
- 238000011835 investigation Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 7
- 239000003086 colorant Substances 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 230000004069 differentiation Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 abstract description 3
- 230000015654 memory Effects 0.000 description 15
- 238000004590 computer program Methods 0.000 description 10
- 230000006399 behavior Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 7
- 230000008859 change Effects 0.000 description 5
- 238000013524 data verification Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000013480 data collection Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 230000008713 feedback mechanism Effects 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an intelligent credit limit interest rate adjusting method and device, belonging to the technical field of computers, and the technical scheme comprises a data module: inquiring and processing relevant data for adjusting the credit rate in real time; a client screening module: according to the data transmitted by the data module: screening out a client list meeting the adjustment condition of the credit limit; the limit interest rate calculation module: calculating the planned interest rate adjustment range of the client according with the interest rate adjustment condition; an adjustment execution module: actually adjusting the calculated adjustment range of the client quota and feeding back the result to the client page; effect monitoring module: and monitoring the adjustment effect of the adjusted client. The credit system aims to improve the efficiency of maintaining credit of a credit client in credit, solve the problems that in the prior art, manual intervention is more, and system automatic long-normalization adjustment cannot be realized, improve the client experience of credit products, maximize the income of financial institutions, and realize win-win of supply and demand terminals.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to an intelligent credit limit interest rate adjusting method and device.
Background
The line interest rate is a core element of a commercial bank credit product, and a reasonable line and interest rate pricing not only needs to meet the basic risk and income requirements of banks, but also needs to match the customer requirements as much as possible, so that the profit win-win situation of financial institutions and consumers is realized. At present, after a client gives credit for the first time, according to the behavior in the credit of the client, the client often faces the requirements of adjusting the amount and interest rate of the client, increasing the amount of the client with higher fund demand, reducing the price of the client with better credit grade and the like. Therefore, an intelligent system for maintaining the full life cycle credit of the client is needed, the client requirements can be timely and accurately evaluated, and the comprehensive credit adjustment scene which can be different is covered. Thereby providing the customer with a good credit product use experience.
No system has been found that specifically adjusts the interest rate of the customer's credit. The prior financial institution limit interest rate adjustment depends on a large number of expert experiences, client data collection and manual examination and approval links. In the adjustment link, regular normalized batch adjustment cannot be achieved, and scientific and effective monitoring is lacked in the evaluation stage after adjustment.
Disclosure of Invention
In order to solve the problems that in the prior art, manual intervention is excessive, and the system cannot automatically adjust the length of the credit limit in a normalized mode, the invention provides a full-process automatic system and a full-process automatic method for adjusting the credit limit interest rate of a customer, so that the customer experience of credit products is improved, and the income of a financial institution is maximized.
The technical scheme adopted by the invention is as follows:
the invention provides an intelligent credit limit interest rate adjusting device on one hand, which specifically comprises:
a data module: inquiring and processing relevant data for adjusting the credit rate in real time through a data port;
a client screening module: screening out a client list meeting the limit interest rate adjustment condition according to the data transmitted by the data module;
the limit interest rate calculation module: calculating the planned interest rate adjustment range of the client according with the interest rate adjustment condition;
an adjustment execution module: the calculated adjustment range of the client credit limit rate is actually adjusted, the result is fed back to a client page, and the client page is displayed in a pattern and/or table form through different pixel colors;
effect monitoring module: and monitoring the adjustment effect of the adjusted client. By adopting the technical scheme, the whole online adjustment of the credit rate is realized through the data module and the client screening module, manual data collection and examination and approval under the line are not depended on, the adjustment efficiency in the credit rate of the credit rate is greatly improved, and the labor cost investment is reduced; then, system configuration of an adjustment strategy and automatic ABtest experiment grouping are realized through a credit calculation module, and regular and normalized credit adjustment is realized; secondly, an approval mechanism is introduced through adjusting an execution module, all execution actions are guaranteed to be within a specified range, and compliance risks and operation risks are reduced; and finally, data tracking is realized through the effect monitoring module, and the optimization of the limit interest rate adjustment strategy is adjusted in time according to the problems reflected by the monitoring data, so that a benign feedback mechanism is formed.
Optionally, the data module specifically includes:
a data query module: inquiring personal credit investigation of the client, other credit investigation institution data authorized by various users and historical debit and credit behavior data of the client in the company through a data port;
a data processing module: the method is used for cleaning the data cleaning and performing derivative processing on the original variable.
Optionally, the client screening module specifically includes:
the index management module: the system comprises a data module, a display module and a display module, wherein the data module is used for managing various index data output by the data module and executing data preview and interface display of basic statistical indexes;
a decision flow configuration module: the method is used for constructing decision flow branches and screening target clients step by step according to index data.
Optionally, the credit limit calculation module specifically includes:
a policy configuration module: the strategy logic is used for constructing limit interest rate adjustment strategy logic, calculating the adjustment amplitude of each client plan and configuring a plurality of strategy versions;
an experiment grouping module: the method is used for carrying out Abtest experiment grouping, splitting the candidate client into different experiment groups and comparison groups according to a preset proportion, and configuring limit rate adjusting logic of each group in a differentiated mode.
Optionally, the adjustment execution module specifically includes:
a data checking module: the system is used for pre-running data for the screened client list, the configured experimental group, the configured control group and the limit interest rate adjusting logic, checking whether the data result is in accordance with expectation or not and reducing errors possibly occurring in the actual execution process;
an approval queue module: the method is used for adjusting the approval process executed by the client and configuring different types of adjusted approval strategies.
Optionally, the effect monitoring module specifically includes:
service growth indicator monitoring module: the system is used for monitoring service growth data of the adjustment client experimental group and the comparison group in different batches, wherein the service growth data comprises the loan amount, the loan balance and the borrowed number index;
risk indicator monitoring module: the risk data monitoring system is used for monitoring risk class data of the adjustment client experiment group and the control group in the same batch, wherein the risk class data comprises overdue persons and overdue money.
Early warning propelling movement module: and the short message early warning device is used for carrying out short message early warning on the abnormal indexes and pushing the abnormal indexes to an operator.
The invention also provides a credit line interest rate adjusting method based on the intelligent credit line interest rate adjusting device, which specifically comprises the following steps:
s1: the data module inquires personal credit investigation of a user, other credit investigation institution data authorized by various users, historical loan behavior data of a client in a company and derivative processing of original variables in real time through a data port, and generates a document in a file format according to the inquired data;
s2: receiving the document transmitted from the data module through a client screening module, extracting client data indexes in the document, screening the clients layer by layer according to a preset rule, and finally screening the clients meeting the limit interest rate adjustment condition to calculate the next limit interest rate adjustment range;
s3: calculating the planned adjustment range of the client through a credit calculation module, presetting calculation logic, calculating in the module by each client to obtain final credit adjustment range data, and generating a credit table file of the client and corresponding data;
s4: and actually adjusting the calculated customer adjustment range in the quota interest rate form file through an adjustment execution module, feeding the result back to a client page, and performing interface display through pixels with different colors.
S5: the effect monitoring module is used for monitoring the adjustment effect of the client performing adjustment, and the client with abnormal monitoring indexes is subjected to short message early warning and pushed to an operator for verification.
Optionally, the step S3 includes:
1) and establishing a quota interest rate adjustment strategy logic through a strategy configuration module, and calculating the adjustment amplitude of each client plan:
2) the test grouping module is used for carrying out Abstest test grouping, the candidate clients are split into different test groups and comparison groups according to a preset proportion, and each group can be configured with the limit rate adjusting logic of the group in a differentiation mode through the strategy configuration module.
Optionally, the data processing steps of the policy configuration calculation are as follows:
step 1: configuring a limit interest rate adjustment calculation strategy;
step 2: configuring the number of experimental groups, and naming the experimental groups;
and step 3: configuring the proportion of the number of each experimental group, wherein the total proportion is 100 percent;
and 4, step 4: policy versions are configured for each experimental group.
Optionally, the configuration credit limit adjustment calculation strategy specifically needs to determine the following aspects:
1) the average planned adjustment amplitude x% of the user, wherein x is 0 or a positive number;
2) selecting indexes, calculating an adjustment coefficient, and performing grouping assignment according to the indexes in a calculation mode;
3) repeating the operation of the step 2), and calculating other adjustment coefficients until the strategy requirement is met;
4) calculating a final adjustment coefficient:
wherein RATIO is the final adjustment coefficient, weight is the coefficient weight, RATIO is the index adjustment coefficient calculated in steps 2) and 3), and N is the number of the adjustment coefficients calculated in steps 2) and 3);
5) and calculating the final adjustment coefficient of the adjustment amplitude which is the original credit rate.
In the technical scheme, historical transaction data of a user account is adopted, a deep neural network model and a SHAP Value explanation neural network model are trained to obtain important dimensions to construct cross features, and then the important feature dimensions are used for constructing interpretable features to construct an intelligent credit limit interest rate adjusting device.
Another aspect of the invention provides a computing device comprising: one or more processors; a memory: for storing one or more computer programs, which when executed by one or more processors, cause the one or more processors to implement the method as described above.
Yet another aspect of the present invention provides a computer-readable storage medium storing computer-executable instructions for implementing the method as described above when executed.
Yet another aspect of the invention provides a computer program comprising computer executable instructions for implementing the method as described above when executed.
Due to the adoption of the technical scheme, the invention has the beneficial effects that:
according to the invention, the whole online adjustment of the credit rate is realized through the data module and the client screening module, the manual data collection and examination and approval under the line are not depended on, the adjustment efficiency in the credit rate of the credit line is greatly improved, and the investment of labor cost is reduced; then, system configuration of an adjustment strategy and automatic ABtest experiment grouping are realized through a credit calculation module, and regular and normalized credit adjustment is realized; secondly, an approval mechanism is introduced through adjusting an execution module, all execution actions are guaranteed to be within a specified range, and compliance risks and operation risks are reduced; finally, data tracking is achieved through the effect monitoring module, and the optimization of the limit interest rate adjustment strategy is adjusted in time according to the problems reflected by the monitoring data to form a benign feedback mechanism; the efficiency of customer credit maintenance in the loan is improved, the problem that the prior art has many manual interventions and can not adjust the system automatically and normally is solved, so that the customer experience of credit products is improved, the income of financial institutions can be fully maximized, and the win-win situation of supply and demand sides is realized.
Drawings
The invention will now be described, by way of example, with reference to the accompanying drawings, in which:
FIG. 1 is a block diagram of an intelligent credit limit interest rate adjustment apparatus according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for adjusting interest rate of an intelligent credit limit according to an embodiment of the present invention;
FIG. 3 is a block diagram of a data module provided by an embodiment of the present invention;
FIG. 4 is a block diagram of a client screening module provided by an embodiment of the present invention;
FIG. 5 is a block diagram of a credit calculation module according to an embodiment of the present invention;
FIG. 6 is a block diagram of an adjustment execution module provided by an embodiment of the present invention;
fig. 7 is a structural diagram of an effect monitoring module according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, 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.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
It should be noted that the terms "comprises" and "comprising," and any variations thereof, in the description and claims of the present invention and the above-described drawings, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
Example 1:
referring to fig. 1, fig. 1 is a schematic structural diagram of a system according to an embodiment of the present invention, which specifically includes: the system comprises a data module, a client screening module, a limit interest rate calculating module, an adjusting execution module and an effect monitoring module; each of the functional blocks will be described separately below.
The data module is a basic module for collecting and arranging client data required by adjustment of the credit rate: the system is used for inquiring and processing relevant data for adjusting the credit limit rate in real time, and the inquiring data comprises personal credit investigation, other credit investigation agency data authorized by various users and historical loan behavior data of a client in a company. Data processing includes data cleaning and derivative processing of raw variables.
Further, referring to fig. 3, the data module further includes a data query module and a data processing module.
The data query module comprises the following steps:
step 1: the data query module receives a data query instruction;
step 2: the data query module triggers a data interface to be queried and initiates a wiping query;
and step 3: the query data is stored in a database.
The data processing module executes the steps of:
step 1: cleaning data and processing abnormal values;
step 2: data coding, namely coding the Chinese character symbol into a code value which can be identified by a computer program;
and step 3: and (4) performing necessary data standardization and normalization.
In a specific implementation process, a data source interface needing to be queried, such as a personal credit report, is configured at a data query module, and after being triggered, the data query module queries the credit report of a corresponding client from an accessed personal credit system and stores the credit report in a local database. And then, the data processing module reads the query data in the stage from the database, performs corresponding data processing according to a preset rule, and stores the processed data in the local database.
The client screening module is used for screening clients meeting the limit interest rate adjustment condition to perform next limit interest rate adjustment amplitude calculation, and the client screening module is used for screening the clients meeting the limit interest rate adjustment condition layer by layer according to preset rules by utilizing data transmitted by the data processing module to finally obtain a client list meeting the rate-increasing condition.
Further, referring to fig. 4, the client screening module further includes an index management module and a decision flow configuration module.
The index management module is used for managing various index data output by the data module, and executing data preview and interface display of basic statistical indexes.
The index management module comprises the following data processing steps:
step 1: receiving a customer data indicator transmitted from a data module;
step 2: according to the configuration options, selecting the indexes to be displayed for previewing, and notifying that the single index can be maximized; and counting data such as values, minimum values, mean values and the like, and checking abnormal data values.
The decision flow configuration module is used for constructing decision flow branches and screening target clients step by step according to index data
The data processing steps of the decision flow configuration module are as follows:
step 1: selecting indexes screened by a user client;
step 2: configuring a client screening rule on a decision flow configuration page;
and step 3: performing data pre-running on the configured screening rules, verifying the screening effect of the rules at the stage, and checking the number of clients screened by the rules at different levels: for judging the rationality of the screening logic.
In the specific implementation process, firstly, the processed data stored by the data module is pushed to the index management module, and the index management module can display the data, count the basic data and query the data. Examples are shown in Table 1:
table 1:
| index 1 | Index 2 | … | Index N |
| 1.2 | 10 | … | 13 |
| 2.3 | 20 | … | 16 |
| 1.6 | 30 | … | 11 |
| … | … | … | … |
The index statistics are shown in table 2:
table 2:
| statistical value | Index 1 | Index 2 | … | Index N |
| Maximum value | 2.3 | 30 | 16 | |
| Minimum value | 1.2 | 10 | 11 | |
| Mean value of | 1.7 | 20 | 13.33 | |
| … |
The decision flow configuration module is responsible for configuring decision flows for the indexes in the index management module, and gradually screens the clients according to preset rules to finally obtain a client list needing to be adjusted. An example of a three-tier decision flow is as follows:
number of candidate clients: 1000, parts by weight;
a first layer: screening customers with index 1>10, and screening the number of the customers 800;
a second layer: screening clients with index 2<1000 and index 3>20, and screening the number of clients 600;
and a third layer: and screening clients with index 4>0.3, and screening the number of the clients to be 300.
And finally, screening to obtain 300 clients needing to be adjusted.
The credit limit calculation module is used for calculating the planned adjustment range of the client, presetting calculation logic, and each client can calculate the final credit limit adjustment range data in the module and carry out Abstest experiment grouping.
Further, referring to fig. 5, the credit calculation module further includes a policy configuration module and an experiment grouping module.
The strategy configuration module is used for constructing limit interest rate adjustment strategy logic, calculating the adjustment amplitude of each client plan, configuring limit interest rate calculation strategies and configuring personalized configuration strategies according to client credit levels, credit limits, use rates or activities and the like.
The data processing steps of the policy configuration calculation are as follows:
configuring a credit limit adjustment calculation strategy, specifically, determining the following aspects:
1. the household plans to adjust the amplitude x%.
2. Selecting indexes (which can be different according to different requirements each time), and calculating an adjustment coefficient. The calculation mode can carry out grouping assignment according to the indexes.
3. And repeating the operation 2, and calculating other adjustment coefficients until the strategy requirements are met (the index types and the number of the strategies at each time can be different according to the actual scene).
4. Calculating a final adjustment coefficient: wherein RATIO is the final adjustment coefficient, weight is the coefficient weight, and RATIO is the index adjustment coefficient calculated by 2, 3.
5. And calculating the final adjustment coefficient of the adjustment amplitude which is the original credit rate.
The policy configuration module may configure multiple policy versions to configure an example according to the client credit level and line level:
version 1 final adjustment factor 0.7 credit rating factor +0.3 credit rating factor, as shown in table 3:
table 3:
| credit rating | Coefficient of credit rating | Quota class | Rating coefficient of quota | Final adjustment factor |
| A | 30％ | A | 10％ | 24％ |
| B | 25％ | B | 15％ | 22％ |
| … | … | … | ||
| F | 5％ | F | 20％ | 9.5％ |
Version 2 final adjustment factor 0.8 credit rating factor +0.2 credit rating factor, as shown in table 4:
table 4:
| credit rating | Coefficient of credit rating | Quota class | Rating coefficient of quota | Final adjustment factor |
| A | 30％ | A | 10％ | 26％ |
| B | 25％ | B | 15％ | 23％ |
| … | … | … | ||
| F | 5％ | F | 20％ | 8％ |
Different strategy versions can be selected according to requirements in the experimental grouping stage;
the experiment grouping module is used for carrying out Abstest experiment grouping, dividing the candidate clients into different experiment groups and comparison groups according to a preset proportion, and configuring the limit interest rate adjusting logic of each group in a differentiated mode through the strategy configuration module.
The experimental grouping data processing steps are as follows:
step 1: configuring the number of experimental groups, and naming the experimental groups;
step 2: configuring the proportion of the number of each experimental group, wherein the total proportion is 100 percent;
and step 3: policy versions are configured for each experimental group.
Table 5 shows that the abort experiment grouping module groups the clients output by the client screening module, and each group can configure the population ratio and the policy version.
Table 5:
| group of | Ratio of human numberExample (b) | Policy versions |
| Experimental group | 80％ | Version 1 |
| Control group | 20％ | Version 2 |
And the adjustment execution module is used for carrying out actual adjustment on the calculated customer adjustment amplitude and feeding back the result to the client page.
Further, referring to fig. 6, the adjustment execution module further includes a data checking module and an approval queue module.
The data checking module is used for pre-running data for the screened client list, the configured experimental group, the configured control group and the limit interest rate adjusting logic, checking whether the data result is in accordance with expectation or not and reducing errors possibly occurring in the actual execution process.
The examination and approval queue module is used for adjusting examination and approval processes executed by clients, and can be used for configuring different types of adjusted examination and approval strategies in a personalized mode (increasing or reducing examination and approval links and examination and approval personnel).
The adjusting execution module comprises the following steps:
step 1: clicking the verification touch to perform data verification;
step 2: querying the data results and checking whether the data results are consistent with expected results;
and step 3: submitting and approving the data file;
and 4, step 4: and (4) executing the actual adjustment of the credit rate after the approval is finished.
The effect monitoring module is used for monitoring the adjustment effect of the client who performs adjustment, including the adjusted support condition, the balance increase, the overdue condition and the like.
In a specific implementation process, the approval queue module is responsible for performing actual system execution on the customer planned adjustment amplitude determined by the interest rate calculation module, firstly, the data verification module verifies whether the adjustment and expectation of the plan are consistent, and meanwhile, other rule configurations can be performed, such as maximum adjustment amplitude, minimum adjustment amplitude and the like, if the conditions are not met, the system can fail to execute, and all adjustments are ensured to be within a specified range.
And after the data verification is completed, the data enters an approval queue, and the system is implemented to take effect after each level of approval.
Further, referring to fig. 7, the effect monitoring module includes a service growth index monitoring module, a risk index monitoring module, and an early warning pushing module.
The service growth index monitoring module is used for monitoring service growth data of the adjustment client experiment group and the comparison group in different batches, and the service growth data comprise indexes such as payment amount, loan balance and the number of borrowed persons.
The risk index monitoring module is used for monitoring risk data of the adjusted client experimental group and the adjusted client contrast group in the same batch, wherein the risk data comprises overdue number, overdue amount and the like.
The early warning pushing module can set early warning, can trigger short message pushing to abnormal indexes, and timely and simultaneously verifies by operators.
The data flow steps of the effect monitoring module are as follows:
step 1: receiving adjusted repayment behavior data for the customer;
step 2: processing the data for 2 times to form a report form and a chart display form;
and step 3: and setting an early warning threshold value, monitoring data change in real time by the system, and triggering early warning short messages to push operators.
The early warning short message pushing rule is exemplified as follows:
1. adjusting the overdue rate of N days to be more than x percent;
2. adjusting the loan balance for N days increases by less than x%.
In the specific implementation process, the service index monitoring module is responsible for tracking service growth related indexes, and the risk index monitoring module is responsible for tracking risk related indexes. The display form comprises a statistical form and a change trend chart. The early warning pushing module can set early warning for index change and send the index change to the limit interest rate adjustment executive personnel in a short message form. And the result is fed back in time, and the executive personnel can adjust the strategy according to the result to form a strategy and result benign feedback closed loop.
Example 2:
in another aspect, the present invention further provides a method for adjusting interest rate of a credit line based on the above-mentioned intelligent device for adjusting interest rate of a credit line, referring to fig. 2, which specifically includes:
s1: the data module inquires personal credit investigation of the user, other credit investigation institution data authorized by various users, historical loan behavior data of the client in the company and derivative processing of the original variable in real time through the data port, and generates a document in a file format according to the inquired data. The data query steps are as follows:
step 1: the data query module receives a data query instruction;
step 2: the data query module triggers a data interface to be queried and initiates a wiping query;
and step 3: the query data is stored in a database.
The data processing steps are as follows:
step 1: cleaning data and processing abnormal values;
step 2: data coding, namely coding the Chinese character symbol into a code value which can be identified by a computer program;
and step 3: and (4) performing necessary data standardization and normalization.
S2: and receiving the document transmitted from the data module through a client screening module, extracting client data indexes in the document, screening the clients layer by layer according to a preset rule, and finally screening the clients meeting the limit interest rate adjustment condition to calculate the next limit interest rate adjustment range. The method comprises the following specific steps:
step 1: receiving a customer data indicator transmitted from a data module;
step 2: according to configuration options, selecting indexes to be displayed for previewing, notifying that data statistics such as maximum value, minimum value and mean value can be carried out on a single index, and checking abnormal data values;
and step 3: selecting indexes screened by a user client;
and 4, step 4: configuring a client screening rule on a decision flow configuration page;
and 5: performing data pre-running on the configured screening rules, verifying the screening effect of the rules at the stage, and checking the number of clients screened by the rules at different levels: for judging the rationality of the screening logic.
S3: calculating the planned adjustment range of the client through the credit calculation module, presetting calculation logic, calculating in the module by each client to obtain the final credit adjustment range data, and generating a credit table file of the client and the corresponding data.
The method comprises the following specific steps:
optionally, the step S3 includes:
1) and establishing a quota interest rate adjustment strategy logic through a strategy configuration module, and calculating the adjustment amplitude of each client plan:
2) the test grouping module is used for carrying out Abstest test grouping, the candidate clients are split into different test groups and comparison groups according to a preset proportion, and each group can be configured with the limit rate adjusting logic of the group in a differentiation mode through the strategy configuration module.
Optionally, the data processing steps of the policy configuration calculation are as follows:
step 1: configuring a limit interest rate adjustment calculation strategy;
step 2: configuring the number of experimental groups, and naming the experimental groups;
and step 3: configuring the proportion of the number of each experimental group, wherein the total proportion is 100 percent;
and 4, step 4: policy versions are configured for each experimental group.
Optionally, the configuration credit limit adjustment calculation strategy specifically needs to determine the following aspects:
1) the average planned adjustment amplitude x% of the user, wherein x is 0 or a positive number;
2) selecting indexes, calculating an adjustment coefficient, and performing grouping assignment according to the indexes in a calculation mode;
3) repeating the operation of the step 2), and calculating other adjustment coefficients until the strategy requirement is met;
4) calculating a final adjustment coefficient:
wherein RATIO is the final adjustment coefficient, weight is the coefficient weight, RATIO is the index adjustment coefficient calculated in steps 2) and 3), and N is the number of adjustment coefficients calculated in steps 2) and 3).
In the technical scheme, historical transaction data of a user account is adopted, a deep neural network model and a SHAP Value explanation neural network model are trained to obtain important dimensions to construct cross features, and then the important feature dimensions are used for constructing interpretable features to construct an intelligent credit limit interest rate adjusting device.
S4: and actually adjusting the calculated customer adjustment range in the quota interest rate form file through an adjustment execution module, feeding the result back to a client page, and performing interface display through pixels with different colors.
The method comprises the following specific steps:
step 1: clicking the verification touch to perform data verification;
step 2: querying the data results and checking whether the data results are consistent with expected results;
and step 3: submitting and approving the data file;
and 4, step 4: and (4) executing the actual adjustment of the credit rate after the approval is finished.
S5: the effect monitoring module is used for monitoring the adjustment effect of the client performing adjustment, and the client with abnormal monitoring indexes is subjected to short message early warning and pushed to an operator for verification.
The method comprises the following specific steps:
step 1: receiving adjusted repayment behavior data for the customer;
step 2: processing the data for 2 times to form a report form and a chart display form;
and step 3: and setting an early warning threshold value, monitoring data change in real time by the system, and triggering early warning short messages to push operators.
Example 3:
in order to achieve the above object, a computer device is also provided. The computer device comprises a memory, a processor, a communication interface and a communication bus, wherein a computer program which can run on the processor is stored in the memory, and the steps of the method of the embodiment are realized when the processor executes the computer program.
The processor may be a Central Processing Unit (CPU).
The memory, which is a non-transitory computer readable storage medium, may be used to store non-transitory software programs, non-transitory computer executable programs, and units, such as the corresponding program units in the above-described method embodiments of the present invention. The processor executes various functional applications of the processor and the processing of the work data by executing the non-transitory software programs, instructions and modules stored in the memory, that is, the method in the above method embodiment is realized.
The memory may include high speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory located remotely from the processor, and such remote memory may be coupled to the processor via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more units are stored in the memory and when executed by the processor perform the method of the above embodiments.
The specific details of the computer device may be understood by referring to the corresponding related descriptions and effects in the above embodiments, and are not described herein again.
Example 4:
in order to achieve the above object, another aspect of the present invention also provides a computer-readable storage medium storing a computer program which, when executed in a computer processor, implements the steps in the above fraudulent transaction identification method. It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD) or a Solid State Drive (SSD), etc.; the storage medium may also comprise a combination of memories of the kind described above.
It will be apparent to those skilled in the art that the modules or steps of the present invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and they may alternatively be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, or fabricated separately as individual integrated circuit modules, or fabricated as a single integrated circuit module from multiple modules or steps. Thus, the present invention is not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The utility model provides an intelligence credit limit interest rate adjusting device which characterized in that specifically includes:
a data module: inquiring and processing relevant data for adjusting the credit rate in real time through a data port;
a client screening module: screening out a client list meeting the limit interest rate adjustment condition according to the data transmitted by the data module;
the limit interest rate calculation module: calculating the planned interest rate adjustment range of the client according with the interest rate adjustment condition;
an adjustment execution module: the calculated adjustment range of the client credit limit rate is actually adjusted, the result is fed back to a client page, and the client page is displayed in a pattern and/or table form through different pixel colors;
effect monitoring module: and monitoring the adjustment effect of the adjusted client.
2. The intelligent credit limit interest rate adjustment device of claim 1, wherein the data module specifically comprises:
a data query module: inquiring personal credit investigation of the client, other credit investigation institution data authorized by various users and historical debit and credit behavior data of the client in the company through a data port;
a data processing module: the method is used for cleaning the data cleaning and performing derivative processing on the original variable.
3. The intelligent credit limit interest rate adjustment device of claim 1, wherein the client filter module specifically comprises:
the index management module: the system comprises a data module, a display module and a display module, wherein the data module is used for managing various index data output by the data module and executing data preview and interface display of basic statistical indexes;
a decision flow configuration module: the method is used for constructing decision flow branches and screening target clients step by step according to index data.
4. The intelligent credit limit interest rate adjustment device of claim 1, wherein the limit interest rate calculation module specifically comprises:
a policy configuration module: the strategy logic is used for constructing limit interest rate adjustment strategy logic, calculating the adjustment amplitude of each client plan and configuring a plurality of strategy versions;
an experiment grouping module: the method is used for carrying out Abtest experiment grouping, splitting the candidate client into different experiment groups and comparison groups according to a preset proportion, and configuring limit rate adjusting logic of each group in a differentiated mode.
5. The intelligent credit limit interest rate adjustment device of claim 4, wherein the adjustment execution module specifically comprises:
a data checking module: the system is used for pre-running data for the screened client list, the configured experimental group, the configured control group and the limit interest rate adjusting logic, checking whether the data result is in accordance with expectation or not and reducing errors possibly occurring in the actual execution process;
an approval queue module: the method is used for adjusting the approval process executed by the client and configuring different types of adjusted approval strategies.
6. The intelligent credit limit interest rate adjustment device of claim 5, wherein the effect monitoring module specifically comprises:
service growth indicator monitoring module: the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for monitoring service growth data of an experimental group and a comparison group of adjustment clients in different batches, and the service growth data comprises a loan amount, a loan balance and borrower number indexes;
risk indicator monitoring module: the risk data monitoring system is used for monitoring risk class data of the adjustment client experimental group and the adjustment client control group in the same batch, and comprises overdue people and overdue money;
early warning propelling movement module: and the short message early warning device is used for carrying out short message early warning on the abnormal indexes and pushing the abnormal indexes to an operator.
7. The method for adjusting the interest rate of a credit line based on the intelligent device for adjusting the interest rate of a credit line according to any one of claims 1 to 6, which comprises the following steps:
s1: the data module inquires personal credit investigation of a user, other credit investigation institution data authorized by various users, historical loan behavior data of a client in a company and derivative processing of original variables in real time through a data port, and generates a document in a file format according to the inquired data;
s2: receiving the document transmitted from the data module through a client screening module, extracting client data indexes in the document, screening the clients layer by layer according to a preset rule, and finally screening the clients meeting the limit interest rate adjustment condition to calculate the next limit interest rate adjustment range;
s3: calculating the planned adjustment range of the client through a credit calculation module, presetting calculation logic, calculating in the module by each client to obtain final credit adjustment range data, and generating a credit table file of the client and corresponding data;
s4: and actually adjusting the calculated customer adjustment range in the quota interest rate form file through an adjustment execution module, feeding the result back to a client page, and performing interface display through pixels with different colors.
S5: the effect monitoring module is used for monitoring the adjustment effect of the client performing adjustment, and the client with abnormal monitoring indexes is subjected to short message early warning and pushed to an operator for verification.
8. The intelligent method for adjusting interest rate on a credit line as claimed in claim 7, wherein the step S3 includes:
1) and establishing a quota interest rate adjustment strategy logic through a strategy configuration module, and calculating the adjustment amplitude of each client plan:
2) the test grouping module is used for carrying out Abstest test grouping, the candidate clients are split into different test groups and comparison groups according to a preset proportion, and each group can be configured with the limit rate adjusting logic of the group in a differentiation mode through the strategy configuration module.
9. The intelligent method of adjusting credit limit interest rate as claimed in claim 8, wherein the data processing steps of the policy configuration calculation are as follows:
step 1: configuring a limit interest rate adjustment calculation strategy;
step 2: configuring the number of experimental groups, and naming the experimental groups;
and step 3: configuring the proportion of the number of each experimental group, wherein the total proportion is 100 percent;
and 4, step 4: policy versions are configured for each experimental group.
10. The intelligent method of adjusting credit limit interest rate of claim 9, wherein the credit limit interest rate is adjusted according to the interest rate of the user,
the configuration limit interest rate adjustment calculation strategy specifically needs to determine the following aspects:
1) the average planned adjustment amplitude x% of the user, wherein x is 0 or a positive number;
2) selecting indexes, calculating an adjustment coefficient, and performing grouping assignment according to the indexes in a calculation mode;
3) repeating the operation of the step 2), and calculating other adjustment coefficients until the strategy requirement is met;
4) calculating a final adjustment coefficient:
wherein RATIO is the final adjustment coefficient, weight is the coefficient weight, RATIO is the index adjustment coefficient calculated in steps 2) and 3), and N is the number of the adjustment coefficients calculated in steps 2) and 3);
5) and calculating the final adjustment coefficient of the adjustment amplitude which is the original credit rate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111534913.8A CN114358519B (en) | 2021-12-15 | 2021-12-15 | Intelligent credit line interest rate adjusting method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111534913.8A CN114358519B (en) | 2021-12-15 | 2021-12-15 | Intelligent credit line interest rate adjusting method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114358519A true CN114358519A (en) | 2022-04-15 |
| CN114358519B CN114358519B (en) | 2024-04-05 |
Family
ID=81098810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111534913.8A Active CN114358519B (en) | 2021-12-15 | 2021-12-15 | Intelligent credit line interest rate adjusting method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114358519B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116071103A (en) * | 2023-03-07 | 2023-05-05 | 天津金城银行股份有限公司 | Method and device for prompting client to borrow and electronic equipment |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030002394A (en) * | 2001-06-29 | 2003-01-09 | 삼성캐피탈 주식회사 | System and Method for adjusting a maximum loan limit and interest rate |
| CN110458696A (en) * | 2019-08-16 | 2019-11-15 | 中国工商银行股份有限公司 | Interest on deposit method of adjustment, device, computer system and medium |
| TW202011316A (en) * | 2018-09-12 | 2020-03-16 | 華南商業銀行股份有限公司 | Deposit interest rate bargaining adjustment system and method thereof |
| CN111461875A (en) * | 2020-04-13 | 2020-07-28 | 四川新网银行股份有限公司 | Multi-scenario staged automatic credit method based on decision engine |
| CN111815429A (en) * | 2020-06-02 | 2020-10-23 | 福建省农村信用社联合社 | Interest rate adjusting system based on client contribution degree and FTP pricing |
| CN112102073A (en) * | 2020-09-27 | 2020-12-18 | 长安汽车金融有限公司 | Credit risk control method and system, electronic device and readable storage medium |
| CN112232871A (en) * | 2020-10-15 | 2021-01-15 | 赣南师范大学 | Differentiated loan interest rate pricing system and method |
| CN113379533A (en) * | 2021-06-11 | 2021-09-10 | 重庆农村商业银行股份有限公司 | Method, device, equipment and storage medium for improving circulating loan quota |
-
2021
- 2021-12-15 CN CN202111534913.8A patent/CN114358519B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20030002394A (en) * | 2001-06-29 | 2003-01-09 | 삼성캐피탈 주식회사 | System and Method for adjusting a maximum loan limit and interest rate |
| TW202011316A (en) * | 2018-09-12 | 2020-03-16 | 華南商業銀行股份有限公司 | Deposit interest rate bargaining adjustment system and method thereof |
| CN110458696A (en) * | 2019-08-16 | 2019-11-15 | 中国工商银行股份有限公司 | Interest on deposit method of adjustment, device, computer system and medium |
| CN111461875A (en) * | 2020-04-13 | 2020-07-28 | 四川新网银行股份有限公司 | Multi-scenario staged automatic credit method based on decision engine |
| CN111815429A (en) * | 2020-06-02 | 2020-10-23 | 福建省农村信用社联合社 | Interest rate adjusting system based on client contribution degree and FTP pricing |
| CN112102073A (en) * | 2020-09-27 | 2020-12-18 | 长安汽车金融有限公司 | Credit risk control method and system, electronic device and readable storage medium |
| CN112232871A (en) * | 2020-10-15 | 2021-01-15 | 赣南师范大学 | Differentiated loan interest rate pricing system and method |
| CN113379533A (en) * | 2021-06-11 | 2021-09-10 | 重庆农村商业银行股份有限公司 | Method, device, equipment and storage medium for improving circulating loan quota |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116071103A (en) * | 2023-03-07 | 2023-05-05 | 天津金城银行股份有限公司 | Method and device for prompting client to borrow and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114358519B (en) | 2024-04-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104866484B (en) | A kind of data processing method and device | |
| CN108932585B (en) | Merchant operation management method and equipment, storage medium and electronic equipment thereof | |
| CN108665366A (en) | Determine method, terminal device and the computer readable storage medium of consumer's risk grade | |
| CN106651570A (en) | System and method for real-time loan approval | |
| CN107103548A (en) | The monitoring method and system and risk monitoring and control method and system of network behavior data | |
| CN108898476A (en) | A kind of loan customer credit-graded approach and device | |
| CN102117459A (en) | Risk control system and method | |
| CN102496126B (en) | Custody asset transaction data monitoring equipment | |
| CN109816509A (en) | Generation method, terminal device and the medium of scorecard model | |
| CN109727136A (en) | The configuration method and device of financial asset | |
| US11687936B2 (en) | System and method for managing chargeback risk | |
| US20100217725A1 (en) | Apparatus for automatic financial portfolio monitoring and associated methods | |
| CN107609771A (en) | A kind of supplier's value assessment method | |
| CN110147389A (en) | Account number treating method and apparatus, storage medium and electronic device | |
| CN109376922A (en) | A kind of short-term trading Optimal Management System and method based on big data | |
| CN107688901B (en) | Data adjusting method and device | |
| CN112598225A (en) | Evaluation index determination method and apparatus, storage medium, and electronic apparatus | |
| CN109492863A (en) | The automatic generation method and device of financial document | |
| CN115545886A (en) | Overdue risk identification method, overdue risk identification device, overdue risk identification equipment and storage medium | |
| KR20120032606A (en) | Stock investment system enabling participattion of stock investment clients and method thereof | |
| CN114358519A (en) | Intelligent credit limit interest rate adjusting method and device | |
| CN110309566B (en) | Medium-and-long-term power transaction clearing rule simulation system and method | |
| CN105321001A (en) | Power selling data processing method and apparatus | |
| CN116645134A (en) | Method, device, equipment and medium for recommending credit card in stages | |
| CN208061256U (en) | A kind of electronic transaction strategy generating 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |