CN117853232B - Credit risk abnormity inspection attribution early warning method and system - Google Patents
Credit risk abnormity inspection attribution early warning method and system Download PDFInfo
- Publication number
- CN117853232B CN117853232B CN202410258403.XA CN202410258403A CN117853232B CN 117853232 B CN117853232 B CN 117853232B CN 202410258403 A CN202410258403 A CN 202410258403A CN 117853232 B CN117853232 B CN 117853232B
- Authority
- CN
- China
- Prior art keywords
- risk
- index
- variation
- credit
- determining
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000007689 inspection Methods 0.000 title claims abstract description 16
- 238000011217 control strategy Methods 0.000 claims abstract description 13
- 230000005856 abnormality Effects 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000005457 optimization Methods 0.000 claims abstract description 5
- 238000012544 monitoring process Methods 0.000 claims description 53
- 238000011156 evaluation Methods 0.000 claims description 30
- 230000006866 deterioration Effects 0.000 claims description 28
- 230000015556 catabolic process Effects 0.000 claims description 13
- 238000006731 degradation reaction Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 abstract description 32
- 238000012937 correction Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000012954 risk control Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Accounting & Taxation (AREA)
- Evolutionary Biology (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Technology Law (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a credit risk abnormality inspection attribution early warning method and system, which belong to the technical field of risk management and specifically comprise the following steps: when determining attribution analysis of index change by combining change data of risk indexes and weight values, determining similar users in historical credit approval users by using application information similarity of different historical credit approval users, determining index change association degree of credit features and concerned credit features according to deviation conditions of credit features of application information among the similar users under different risk indexes, and performing optimization processing of a wind control strategy according to the index change association degree of concerned credit features, thereby reducing risks of credit application processing.
Description
Technical Field
The invention belongs to the technical field of risk management, and particularly relates to a credit risk abnormity inspection attribution early warning method and system.
Background
In the credit industry, the fluctuation of core risk indexes such as daily balance, bad account rate, reject rate, overdue loan rate and the like is normal, and how to quickly and efficiently capture anomalies and accurately attribute to the dynamic adjustment of a pneumatic control strategy is a challenge facing most practitioners.
In order to solve the technical problems, the current industry commonly uses a mode of ring-to-ring ratio fluctuation amplitude of core indexes and is basically fixed in the dimension of a certain core index for attribution analysis, and by adopting the technical scheme, on one hand, real-time inspection processing of the fluctuation condition of the core index cannot be realized, and meanwhile, only mining analysis of a certain fluctuation index cannot accurately realize identification of attribution analysis results.
Aiming at the technical problems, the invention provides a credit risk abnormity inspection attribution early warning method and system.
Disclosure of Invention
In order to achieve the purpose of the invention, the invention adopts the following technical scheme:
according to one aspect of the invention, a credit risk anomaly patrol attribution early warning method is provided.
A credit risk abnormality inspection attribution early warning method is characterized by comprising the following steps:
s1, determining monitoring frequencies of different risk indexes according to historical variation conditions of the different risk indexes and types of the risk indexes, and carrying out inspection of the different risk indexes based on the monitoring frequencies to obtain variation data of the risk indexes;
S2, determining a fluctuation risk index in the risk indexes according to the fluctuation data of the risk indexes, and determining whether attribution analysis of index fluctuation is needed or not according to the fluctuation data and the weight values of different risk indexes, if so, entering the next step, and if not, returning to the step S1 to continue monitoring;
S3, determining similar users in the historical credit approval users by using the application information similarity of different historical credit approval users, determining index variation association degree of credit features and concerned credit features according to deviation conditions of credit features of application information among the similar users under different risk indexes, and performing optimization processing of a wind control strategy according to the index variation association degree of the concerned credit features.
The invention has the beneficial effects that:
1. According to the historical change conditions of different risk indexes and the types of the risk indexes, the monitoring frequencies of the different risk indexes are determined, the difference of the importance degree of overdue risk control of financial institutions caused by the difference of the types of the risk indexes is considered, and meanwhile, the difference of the probability of the secondary change caused by the change conditions of the different risk indexes in the history is also considered, so that reliable monitoring of the risk indexes with quicker change and higher importance degree is realized.
2. According to the deviation condition of the credit characteristics of application information among similar users under different risk indexes, the index change association degree of the credit characteristics and the concerned credit characteristics are determined, so that the association degree of the different credit characteristics and the change of the risk indexes is determined according to the distribution condition of the similar users under different risk indexes in the positive and negative directions and the deviation condition of the credit characteristics in the positive and negative directions, a foundation is laid for the differentiated adjustment of the pneumatic control strategy, and the overdue risk of the credit application is further reduced.
A further embodiment is that the historical variation of the risk indicator includes a historical variation number of the risk indicator, a variation range of different historical variation numbers, and a variation amount.
Further technical solutions include, but are not limited to, daily balance, bad account rate, defective rate, overdue loan rate, and rate of entry into the incentive.
A further technical solution is that the variation data of the risk indicator includes a variation range and a variation amount of the risk indicator. Determining a fluctuating risk indicator of the risk indicators by fluctuating data of the risk indicators
Further technical solutions include determining the risk indicator as a fluctuating risk indicator when the fluctuation range or fluctuation amount of the risk indicator does not meet the requirement.
The further technical scheme is that the weight value of the risk index is determined according to the wind control stage associated with the risk index.
The further technical scheme is that when the similarity of application information among the historical credit approval users is larger than the preset similarity, the historical credit approval users are determined to be similar users.
In a second aspect, the present invention provides a computer system comprising: a communicatively coupled memory and processor, and a computer program stored on the memory and capable of running on the processor, characterized by: executing the credit risk abnormality inspection attribution early warning method when the processor runs the computer program.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the invention as set forth hereinafter.
In order to make the above objects, features and advantages of the present invention more comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the attached drawings;
FIG. 1 is a flow chart of a credit risk anomaly patrol attribution pre-warning method;
FIG. 2 is a flow chart of a method of determining a monitoring frequency of a risk indicator;
FIG. 3 is a flow chart of a method of determining whether attribution analysis of index changes is required;
FIG. 4 is a flow chart of a method of focusing on the determination of credit features;
FIG. 5 is a block diagram of a computer system.
Detailed Description
In order to make the technical solutions in the present specification better understood by those skilled in the art, the technical solutions in the embodiments of the present specification will be clearly and completely described below with reference to the drawings in the embodiments of the present specification, and it is obvious that the described embodiments are only some embodiments of the present specification, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, shall fall within the scope of the present disclosure.
The risk indexes of the financial institutions, such as daily life balance, bad account rate, reject ratio, overdue loan rate, entering rate and the like, need to be dynamically monitored, so that when certain risk indexes are poor or do not meet the requirements, the wind control strategy of the credit application is dynamically adjusted according to the change condition of the risk indexes, and the overdue risk is limited in the initial processing stage of the credit application, and the overdue loan condition of the financial institutions is reduced.
In order to solve the technical problems, when the risk index does not meet the requirement or the variation amplitude of the variation is overlarge, the invention mainly realizes the screening of the concerned credit feature through the variation condition of the risk index and the variation condition of the credit feature, thereby realizing the advanced control of the overdue risk through the weighting treatment of the concerned credit feature in the input quantity of the original wind control strategy and the like.
Specifically, the invention adopts the following technical scheme:
Firstly, determining monitoring frequencies of different risk indexes according to historical variation conditions of different risk indexes and types of the risk indexes, specifically determining a basic monitoring frequency through a corresponding relation of the types of the risk indexes, then correcting the basic monitoring frequency according to the occupation ratio of historical variation times with larger variation amplitude of the risk indexes to determine the monitoring frequency of the risk indexes, and carrying out inspection of different risk indexes based on the monitoring frequency to obtain variation data of the risk indexes;
The risk index with larger fluctuation range is used as a fluctuation risk index in the risk indexes, so that whether attribution analysis of index fluctuation is needed or not is determined according to the quantity of the fluctuation risk indexes, the fluctuation range of different risk indexes and the weight value, specifically, whether attribution analysis of index fluctuation is needed or not is determined when the quantity of the fluctuation risk indexes is large or the weight sum of the fluctuation range of different risk indexes is large, and the next step is carried out when attribution analysis of index fluctuation is determined to be needed;
Determining similar users in historical credit approval users by using application information similarity of different historical credit approval users, determining index variation association degree of credit features and concerned credit features according to deviation conditions of credit features of application information among the similar users under different risk indexes, specifically, determining index variation association degree of credit features of front similar users and reverse similar users in the similar users under the risk indexes, taking the credit features with larger index variation association degree as concerned credit features, determining correction feature quantities of different concerned credit features based on the index variation association degree of the different concerned credit features, and optimizing input features of the wind control strategy based on the correction feature quantities.
Further explanation will be made below from two perspectives of the method class embodiment and the system class embodiment.
In order to solve the above-mentioned problems, according to one aspect of the present invention, as shown in fig. 1, there is provided a credit risk anomaly patrol and attribution pre-warning method, which is characterized by comprising:
s1, determining monitoring frequencies of different risk indexes according to historical variation conditions of the different risk indexes and types of the risk indexes, and carrying out inspection of the different risk indexes based on the monitoring frequencies to obtain variation data of the risk indexes;
Specifically, the historical variation condition of the risk index includes the historical variation times of the risk index, the variation ranges of different historical variation times and the variation amounts.
The risk index includes, but is not limited to, daily balance, bad account rate, defective rate, overdue loan rate, and entry rate.
As shown in fig. 2, the method for determining the monitoring frequency of the risk indicator in the step S1 is as follows:
determining a wind control stage associated with the risk index according to the type of the risk index, and determining a basic monitoring frequency of the risk index based on the wind control stage associated with the risk index;
Determining the historical variation times of the risk index based on the historical variation conditions of the risk index, and determining the index variation amount of the risk index by combining the variation ranges and variation amounts of different historical variation times;
Determining the historical index deterioration times and the index abnormality times of the risk index according to the historical variation conditions, and determining the index problem variation of the risk index by combining the variation ranges and variation amounts of different historical index deterioration times;
And correcting the basic monitoring frequency of the risk index based on the index problem fluctuation and the index fluctuation to obtain the monitoring frequency of the risk index.
It should be noted that the wind control stage is divided according to the overdue stage of the user, and specifically includes an overdue occurrence stage, a bad generation stage and an recovery stage.
In another possible embodiment, the method for determining the monitoring frequency of the risk indicator in the step S1 is as follows:
Determining a wind control stage associated with the risk index according to the type of the risk index, determining a basic monitoring frequency of the risk index based on the wind control stage associated with the risk index, judging whether the wind control stage associated with the risk index is in a preset wind control stage, if so, taking the basic monitoring frequency as the monitoring frequency of the risk index, and if not, entering the next step;
Determining the historical variation times of the risk index based on the historical variation conditions of the risk index, determining the index variation amount of the risk index by combining the variation range and variation amount of different historical variation times, judging whether the index variation amount of the risk index is larger than a preset variation threshold, if so, determining the monitoring frequency of the risk index through a preset monitoring frequency, and if not, entering the next step;
Determining the historical index deterioration times and the index abnormal times of the risk index according to the historical variation conditions, determining the index problem variation of the risk index according to the variation range and variation of different historical index deterioration times, judging whether the index problem variation of the risk index meets the requirements, if so, determining the monitoring frequency of the risk index according to the preset monitoring frequency, and if not, entering the next step;
And correcting the basic monitoring frequency of the risk index based on the index problem fluctuation and the index fluctuation to obtain the monitoring frequency of the risk index.
In another possible embodiment, the method for determining the monitoring frequency of the risk indicator in the step S1 is as follows:
S11, determining a wind control stage associated with the risk index according to the type of the risk index, determining a basic monitoring frequency of the risk index based on the wind control stage associated with the risk index, judging whether the risk index has historical variation times with variation amplitude larger than a preset amplitude, if so, entering a step S13, otherwise, entering a next step;
S12, judging whether the risk index has historical index deterioration times or index abnormal times, if so, entering a next step, and if not, taking the basic monitoring frequency of the risk index as the monitoring frequency of the risk index;
S13, determining the historical variation times of the risk index based on the historical variation conditions of the risk index, determining the index variation amount of the risk index by combining different variation ranges and variation amounts of the historical variation times, determining the historical index deterioration times and index abnormality times of the risk index by the historical variation conditions, and determining the index problem variation amount of the risk index by combining different variation ranges and variation amounts of the historical index deterioration times;
S14, correcting the basic monitoring frequency of the risk index based on the index problem fluctuation amount and the index fluctuation amount to obtain the monitoring frequency of the risk index.
The fluctuation data of the risk index includes a fluctuation range and a fluctuation amount of the risk index.
S2, determining a fluctuation risk index in the risk indexes according to the fluctuation data of the risk indexes, and determining whether attribution analysis of index fluctuation is needed or not according to the fluctuation data and the weight values of different risk indexes, if so, entering the next step, and if not, returning to the step S1 to continue monitoring;
Specifically, when the fluctuation range or fluctuation amount of the risk index does not meet the requirement, determining that the risk index is a fluctuation risk index.
It is understood that the weight value of the risk indicator is determined according to the wind control stage associated with the risk indicator.
In one possible embodiment, as shown in fig. 3, the determining in the step S2 includes:
determining deterioration risk indexes in the variation risk indexes based on variation data of the variation risk indexes, and determining a deterioration evaluation value of the risk indexes through the quantity of the deterioration risk indexes, the weight value of the deterioration risk indexes and the variation data;
Determining a problem risk index in different risk indexes according to the variation data of the different risk indexes, and determining a problem evaluation value of the risk indexes according to the number of the problem risk indexes, the weight value of the deterioration risk indexes and the variation data;
And acquiring the quantity and the variation data of the variation risk indexes, combining the weight values of different variation risk indexes, the problem evaluation quantity and the deterioration evaluation quantity of the risk indexes to determine the comprehensive evaluation quantity of the index variation, and determining whether attribution analysis of the index variation is needed or not based on the comprehensive evaluation quantity.
In another possible embodiment, the determining in the step S2 includes performing an attribution analysis of the index change, specifically including:
Determining deterioration risk indexes in the variation risk indexes based on the variation data of the variation risk indexes, determining problem risk indexes in the variation risk indexes through variation data of different risk indexes, and determining attribution analysis of index variation when the number of the deterioration risk indexes does not meet the requirement or the number of the problem risk indexes does not meet the requirement;
When the number of the degradation risk indexes and the number of the problem risk indexes meet the requirements:
Determining a degradation evaluation quantity of the risk indexes according to the quantity of the degradation risk indexes, the weight value of the degradation risk indexes and the change data, and determining that attribution analysis of index change is needed when the degradation evaluation quantity does not meet the requirement;
When the degradation evaluation amount meets the requirement, determining a problem risk index in the fluctuation risk indexes through fluctuation data of different risk indexes, determining a problem evaluation amount of the risk indexes through the number of the problem risk indexes, the weight value of the deterioration risk indexes and the fluctuation data, and when the problem evaluation amount does not meet the requirement, determining attribution analysis of index fluctuation;
when the problem evaluation quantity meets the requirement, the quantity and the change data of the change risk indexes are obtained, the comprehensive evaluation quantity of the index change is determined by combining the weight values of different change risk indexes, the problem evaluation quantity of the risk indexes and the degradation evaluation quantity, and whether attribution analysis of the index change is needed or not is determined based on the comprehensive evaluation quantity.
In another possible embodiment, the determining in the step S2 includes performing an attribution analysis of the index change, specifically including:
S21, judging whether a problem risk index exists in the risk indexes, if so, entering a step S23, and if not, entering a next step;
S22, determining deterioration risk indexes in the variation risk indexes based on the variation data of the variation risk indexes, judging whether the quantity of the deterioration risk indexes meets the requirement, and if so, determining that attribution analysis of index variation is not needed;
S23, determining degradation evaluation quantity of the risk indexes according to the quantity of the degradation risk indexes, the weight value of the degradation risk indexes and the change data, judging whether the degradation evaluation quantity meets the requirement, if so, entering the next step, and if not, determining that attribution analysis of index change is needed;
S24, determining a problem evaluation quantity of the risk indexes according to the quantity of the problem risk indexes, the weight value of the deterioration risk indexes and the change data, judging whether the problem evaluation quantity does not meet the requirement, if so, determining that attribution analysis of index change is needed, and if not, entering the next step;
S25, acquiring the number of the variable risk indexes and variable data, combining the weight values of different variable risk indexes, the problem evaluation values of the risk indexes and the degradation evaluation values to determine the comprehensive evaluation value of the index change, and determining whether attribution analysis of the index change is needed or not based on the comprehensive evaluation value.
S3, determining similar users in the historical credit approval users by using the application information similarity of different historical credit approval users, determining index variation association degree of credit features and concerned credit features according to deviation conditions of credit features of application information among the similar users under different risk indexes, and performing optimization processing of a wind control strategy according to the index variation association degree of the concerned credit features.
It can be understood that when the similarity of the application information between the historical credit approval users is greater than the preset similarity, the historical credit approval users are determined to be similar users.
In one possible embodiment, as shown in fig. 4, the method for determining the credit feature of interest in the step S3 is as follows:
dividing the similar users under different risk indexes into front similar users and back similar users according to the matching results of the different similar users under different risk indexes;
Determining index association of the credit feature under different risk indexes by the number of front-side similar users without the credit feature and the number ratio of the front-side similar users, the number of back-side similar users without the credit feature and the number ratio of the back-side similar users;
An index variation association of a credit feature is determined based on index association of the credit feature at different risk indices, and it is determined whether the credit feature is a credit feature of interest by the index variation association.
In another possible embodiment, the method for determining the credit feature of interest in the step S3 is as follows:
dividing the similar users under different risk indexes into front similar users and back similar users according to the matching results of the different similar users under different risk indexes;
Performing basic credit characteristics of the positive similar user under the credit characteristics through the similarity of the credit characteristics of the positive similar user, performing basic credit characteristics of the negative similar user under the credit characteristics based on the similarity of the credit characteristics of the negative similar user, judging whether the basic credit characteristics of the positive similar user under the credit characteristics deviate from the basic credit characteristics of the negative similar user under the credit characteristics, if so, entering the next step, and if not, determining that the credit characteristics do not belong to the concerned credit characteristics;
Determining the index association degree of the credit features under different risk indexes through the number of the front similar users without the credit features, the number of the back similar users without the credit features and the number of the back similar users without the front similar users, judging whether the credit features have risk indexes with the index association degree larger than a preset association degree limit value, if yes, entering the next step, and if no, determining that the credit features do not belong to the concerned credit features;
An index variation association of a credit feature is determined based on index association of the credit feature at different risk indices, and it is determined whether the credit feature is a credit feature of interest by the index variation association.
It is appreciated that when the index variation association of the credit feature is greater than a preset association, then the credit feature is determined to be a credit feature of interest.
Specifically, the optimization processing of the wind control strategy is performed according to the index variation association degree of the concerned credit feature, specifically including:
And determining correction feature quantities of different interesting credit features based on index variation association degrees of the different interesting credit features, and optimizing the input features of the wind control strategy based on the correction feature quantities.
In another aspect, as shown in FIG. 5, the present invention provides a computer system comprising: a communicatively coupled memory and processor, and a computer program stored on the memory and capable of running on the processor, characterized by: executing the credit risk abnormality inspection attribution early warning method when the processor runs the computer program.
The credit risk abnormality inspection attribution early warning method specifically comprises the following steps:
Determining a wind control stage associated with the risk index according to the type of the risk index, determining a basic monitoring frequency of the risk index based on the wind control stage associated with the risk index, judging whether the wind control stage associated with the risk index is in a preset wind control stage, if so, taking the basic monitoring frequency as the monitoring frequency of the risk index, and if not, entering the next step;
Determining the historical variation times of the risk index based on the historical variation conditions of the risk index, determining the index variation amount of the risk index by combining the variation range and variation amount of different historical variation times, judging whether the index variation amount of the risk index is larger than a preset variation threshold, if so, determining the monitoring frequency of the risk index through a preset monitoring frequency, and if not, entering the next step;
Determining the historical index deterioration times and the index abnormal times of the risk index according to the historical variation conditions, determining the index problem variation of the risk index according to the variation range and variation of different historical index deterioration times, judging whether the index problem variation of the risk index meets the requirements, if so, determining the monitoring frequency of the risk index according to the preset monitoring frequency, and if not, entering the next step;
Correcting the basic monitoring frequency of the risk index based on the index problem fluctuation amount and the index fluctuation amount to obtain the monitoring frequency of the risk index, and carrying out inspection of different risk indexes based on the monitoring frequency to obtain the fluctuation data of the risk index;
Determining a fluctuation risk index in the risk indexes according to the fluctuation data of the risk indexes, and entering a next step when attribution analysis of index fluctuation is required by combining the fluctuation data of different risk indexes and the weight value;
And determining similar users in the historical credit approval users by using the application information similarity of different historical credit approval users, determining index variation association degree of credit features and concerned credit features according to deviation conditions of credit features of application information among the similar users under different risk indexes, determining correction feature quantities of different concerned credit features according to the index variation association degree of the different concerned credit features, and optimizing the input features of the pneumatic control strategy according to the correction feature quantities.
Through the above embodiments, the present invention has the following beneficial effects:
1. According to the historical change conditions of different risk indexes and the types of the risk indexes, the monitoring frequencies of the different risk indexes are determined, the difference of the importance degree of overdue risk control of financial institutions caused by the difference of the types of the risk indexes is considered, and meanwhile, the difference of the probability of the secondary change caused by the change conditions of the different risk indexes in the history is also considered, so that reliable monitoring of the risk indexes with quicker change and higher importance degree is realized.
2. According to the deviation condition of the credit characteristics of application information among similar users under different risk indexes, the index change association degree of the credit characteristics and the concerned credit characteristics are determined, so that the association degree of the different credit characteristics and the change of the risk indexes is determined according to the distribution condition of the similar users under different risk indexes in the positive and negative directions and the deviation condition of the credit characteristics in the positive and negative directions, a foundation is laid for the differentiated adjustment of the pneumatic control strategy, and the overdue risk of the credit application is further reduced.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for apparatus, devices, non-volatile computer storage medium embodiments, the description is relatively simple, as it is substantially similar to method embodiments, with reference to the section of the method embodiments being relevant.
The foregoing describes specific embodiments of the present disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing is merely one or more embodiments of the present description and is not intended to limit the present description. Various modifications and alterations to one or more embodiments of this description will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, or the like, which is within the spirit and principles of one or more embodiments of the present description, is intended to be included within the scope of the claims of the present description.
Claims (7)
1. A credit risk abnormality inspection attribution early warning method is characterized by comprising the following steps:
s1, determining monitoring frequencies of different risk indexes according to historical variation conditions of the different risk indexes and types of the risk indexes, and carrying out inspection of the different risk indexes based on the monitoring frequencies to obtain variation data of the risk indexes;
S2, determining a fluctuation risk index in the risk indexes according to the fluctuation data of the risk indexes, and determining whether attribution analysis of index fluctuation is needed or not according to the fluctuation data and the weight values of different risk indexes, if so, entering the next step, and if not, returning to the step S1 to continue monitoring;
s3, determining similar users in the historical credit approval users by using application information similarity of different historical credit approval users, determining index variation association degree of credit features and concerned credit features according to deviation conditions of credit features of application information among the similar users under different risk indexes, and performing optimization processing of a wind control strategy according to the index variation association degree of the concerned credit features;
the method for determining the monitoring frequency of the risk index comprises the following steps:
determining a wind control stage associated with the risk index according to the type of the risk index, and determining a basic monitoring frequency of the risk index based on the wind control stage associated with the risk index;
Determining the historical variation times of the risk index based on the historical variation conditions of the risk index, and determining the index variation amount of the risk index by combining the variation ranges and variation amounts of different historical variation times;
Determining the historical index deterioration times and the index abnormality times of the risk index according to the historical variation conditions, and determining the index problem variation of the risk index by combining the variation ranges and variation amounts of different historical index deterioration times;
Correcting the basic monitoring frequency of the risk index based on the index problem fluctuation amount and the index fluctuation amount to obtain the monitoring frequency of the risk index;
Determining whether an attribution analysis of index variation is required specifically includes:
determining deterioration risk indexes in the variation risk indexes based on variation data of the variation risk indexes, and determining a deterioration evaluation value of the risk indexes through the quantity of the deterioration risk indexes, the weight value of the deterioration risk indexes and the variation data;
Determining a problem risk index in different risk indexes according to the variation data of the different risk indexes, and determining a problem evaluation value of the risk indexes according to the number of the problem risk indexes, the weight value of the deterioration risk indexes and the variation data;
acquiring the number of the variable risk indexes and variable data, determining the comprehensive evaluation of the index variation by combining the weight values of different variable risk indexes, the problem evaluation values of the risk indexes and the degradation evaluation values, and determining whether attribution analysis of the index variation is needed or not based on the comprehensive evaluation values;
The method for determining the credit feature of interest comprises the following steps:
dividing the similar users under different risk indexes into front similar users and back similar users according to the matching results of the different similar users under different risk indexes;
Determining index association of the credit feature under different risk indexes by the number of front-side similar users without the credit feature and the number ratio of the front-side similar users, the number of back-side similar users without the credit feature and the number ratio of the back-side similar users;
An index variation association of a credit feature is determined based on index association of the credit feature at different risk indices, and it is determined whether the credit feature is a credit feature of interest by the index variation association.
2. The credit risk anomaly routing attribution pre-warning method according to claim 1, wherein the risk index comprises daily life balance, bad account rate, reject rate, overdue loan rate and income rate.
3. The credit risk anomaly routing attribution pre-warning method according to claim 1, wherein the wind control stage is divided according to the overdue stage of the user, specifically including an overdue occurrence stage, a bad generation stage and an adduction stage.
4. The credit risk anomaly routing attribution pre-warning method according to claim 1, wherein the variation data of the risk index includes a variation range and a variation amount of the risk index.
5. The credit risk anomaly routing attribution pre-warning method according to claim 1, wherein the weight value of the risk indicator is determined according to a wind control stage associated with the risk indicator.
6. The credit risk anomaly routing attribution pre-warning method according to claim 1, wherein when the application information similarity between the historical credit approval users is greater than a preset similarity, the historical credit approval users are determined to be similar users.
7. A computer system, comprising: a communicatively coupled memory and processor, and a computer program stored on the memory and capable of running on the processor, characterized by: the processor, when executing the computer program, performs a credit risk anomaly patrol attribution pre-warning method as claimed in any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410258403.XA CN117853232B (en) | 2024-03-07 | 2024-03-07 | Credit risk abnormity inspection attribution early warning method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410258403.XA CN117853232B (en) | 2024-03-07 | 2024-03-07 | Credit risk abnormity inspection attribution early warning method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117853232A CN117853232A (en) | 2024-04-09 |
| CN117853232B true CN117853232B (en) | 2024-05-24 |
Family
ID=90536443
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410258403.XA Active CN117853232B (en) | 2024-03-07 | 2024-03-07 | Credit risk abnormity inspection attribution early warning method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117853232B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118071492A (en) * | 2024-04-25 | 2024-05-24 | 杭银消费金融股份有限公司 | Real-time adjustment method and system for refusing strategy for credit account |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8280805B1 (en) * | 2006-01-10 | 2012-10-02 | Sas Institute Inc. | Computer-implemented risk evaluation systems and methods |
| CN108876600A (en) * | 2018-08-20 | 2018-11-23 | 平安科技（深圳）有限公司 | Warning information method for pushing, device, computer equipment and medium |
| CN110135971A (en) * | 2019-04-15 | 2019-08-16 | 上海良鑫网络科技有限公司 | Assessing credit risks System and method for based on weak variable data |
| CN110348995A (en) * | 2019-06-28 | 2019-10-18 | 北京淇瑀信息科技有限公司 | A kind of credit risk control method, apparatus and electronic equipment based on risk attribution |
| US10572945B1 (en) * | 2014-08-28 | 2020-02-25 | Cerner Innovation, Inc. | Insurance risk scoring based on credit utilization ratio |
| WO2020143345A1 (en) * | 2019-01-11 | 2020-07-16 | 中信梧桐港供应链管理有限公司 | Method and apparatus for monitoring credit risk in warehouse receipt pledge |
| CN113469807A (en) * | 2021-08-31 | 2021-10-01 | 阿里云计算有限公司 | Credit risk determination and data processing method, apparatus, medium, and program product |
| CN114819692A (en) * | 2022-05-11 | 2022-07-29 | 平安国际智慧城市科技股份有限公司 | Business risk analysis method, device, equipment and storage medium |
| EP4105872A2 (en) * | 2021-11-10 | 2022-12-21 | Beijing Baidu Netcom Science And Technology Co. Ltd. | Data processing method and apparatus |
| CN115545881A (en) * | 2022-09-02 | 2022-12-30 | 睿智合创(北京)科技有限公司 | Credit risk processing-based risk factor attribution method |
| CN115907956A (en) * | 2022-09-27 | 2023-04-04 | 睿智合创(北京)科技有限公司 | Simulation early warning method and system for asset risk |
| CN115953235A (en) * | 2022-12-23 | 2023-04-11 | 中国建设银行股份有限公司 | Risk index statistical method and device, storage medium and electronic equipment |
| CN116012138A (en) * | 2022-12-16 | 2023-04-25 | 度小满科技(北京)有限公司 | Policy adjustment method, device, terminal and storage medium |
| CN116070958A (en) * | 2023-02-17 | 2023-05-05 | 中移动信息技术有限公司 | Attribution analysis method, attribution analysis device, electronic equipment and storage medium |
| CN116452316A (en) * | 2023-02-28 | 2023-07-18 | 中国工商银行股份有限公司 | Post-loan risk monitoring method and device for agricultural loan and electronic equipment |
| CN116843452A (en) * | 2023-07-06 | 2023-10-03 | 中国工商银行股份有限公司 | Risk supervision method, apparatus, device, medium, and program product |
| CN116862661A (en) * | 2023-07-20 | 2023-10-10 | 苏银凯基消费金融有限公司 | Digital credit approval and risk monitoring system based on consumption financial scene |
| CN116882805A (en) * | 2023-06-16 | 2023-10-13 | 中科云谷科技有限公司 | Method, processor, device and storage medium for determining customer risk level |
| CN116957772A (en) * | 2023-05-26 | 2023-10-27 | 中国建设银行股份有限公司 | Credit index monitoring method, device, equipment and storage medium |
| CN116977063A (en) * | 2023-08-15 | 2023-10-31 | 深圳微众信用科技股份有限公司 | Loan risk monitoring device, method, equipment and storage medium |
| CN117132001A (en) * | 2023-10-24 | 2023-11-28 | 杭银消费金融股份有限公司 | Multi-target wind control strategy optimization method and system |
| CN117575775A (en) * | 2023-11-28 | 2024-02-20 | 中国工商银行股份有限公司 | Service risk detection method, device, equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170301024A1 (en) * | 2009-03-20 | 2017-10-19 | Pankaj B. Dalal | Multidimensional risk analysis |
-
2024
- 2024-03-07 CN CN202410258403.XA patent/CN117853232B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8280805B1 (en) * | 2006-01-10 | 2012-10-02 | Sas Institute Inc. | Computer-implemented risk evaluation systems and methods |
| US10572945B1 (en) * | 2014-08-28 | 2020-02-25 | Cerner Innovation, Inc. | Insurance risk scoring based on credit utilization ratio |
| CN108876600A (en) * | 2018-08-20 | 2018-11-23 | 平安科技（深圳）有限公司 | Warning information method for pushing, device, computer equipment and medium |
| WO2020143345A1 (en) * | 2019-01-11 | 2020-07-16 | 中信梧桐港供应链管理有限公司 | Method and apparatus for monitoring credit risk in warehouse receipt pledge |
| CN110135971A (en) * | 2019-04-15 | 2019-08-16 | 上海良鑫网络科技有限公司 | Assessing credit risks System and method for based on weak variable data |
| CN110348995A (en) * | 2019-06-28 | 2019-10-18 | 北京淇瑀信息科技有限公司 | A kind of credit risk control method, apparatus and electronic equipment based on risk attribution |
| CN113469807A (en) * | 2021-08-31 | 2021-10-01 | 阿里云计算有限公司 | Credit risk determination and data processing method, apparatus, medium, and program product |
| EP4105872A2 (en) * | 2021-11-10 | 2022-12-21 | Beijing Baidu Netcom Science And Technology Co. Ltd. | Data processing method and apparatus |
| CN114819692A (en) * | 2022-05-11 | 2022-07-29 | 平安国际智慧城市科技股份有限公司 | Business risk analysis method, device, equipment and storage medium |
| CN115545881A (en) * | 2022-09-02 | 2022-12-30 | 睿智合创(北京)科技有限公司 | Credit risk processing-based risk factor attribution method |
| CN115907956A (en) * | 2022-09-27 | 2023-04-04 | 睿智合创(北京)科技有限公司 | Simulation early warning method and system for asset risk |
| CN116012138A (en) * | 2022-12-16 | 2023-04-25 | 度小满科技(北京)有限公司 | Policy adjustment method, device, terminal and storage medium |
| CN115953235A (en) * | 2022-12-23 | 2023-04-11 | 中国建设银行股份有限公司 | Risk index statistical method and device, storage medium and electronic equipment |
| CN116070958A (en) * | 2023-02-17 | 2023-05-05 | 中移动信息技术有限公司 | Attribution analysis method, attribution analysis device, electronic equipment and storage medium |
| CN116452316A (en) * | 2023-02-28 | 2023-07-18 | 中国工商银行股份有限公司 | Post-loan risk monitoring method and device for agricultural loan and electronic equipment |
| CN116957772A (en) * | 2023-05-26 | 2023-10-27 | 中国建设银行股份有限公司 | Credit index monitoring method, device, equipment and storage medium |
| CN116882805A (en) * | 2023-06-16 | 2023-10-13 | 中科云谷科技有限公司 | Method, processor, device and storage medium for determining customer risk level |
| CN116843452A (en) * | 2023-07-06 | 2023-10-03 | 中国工商银行股份有限公司 | Risk supervision method, apparatus, device, medium, and program product |
| CN116862661A (en) * | 2023-07-20 | 2023-10-10 | 苏银凯基消费金融有限公司 | Digital credit approval and risk monitoring system based on consumption financial scene |
| CN116977063A (en) * | 2023-08-15 | 2023-10-31 | 深圳微众信用科技股份有限公司 | Loan risk monitoring device, method, equipment and storage medium |
| CN117132001A (en) * | 2023-10-24 | 2023-11-28 | 杭银消费金融股份有限公司 | Multi-target wind control strategy optimization method and system |
| CN117575775A (en) * | 2023-11-28 | 2024-02-20 | 中国工商银行股份有限公司 | Service risk detection method, device, equipment and storage medium |
Non-Patent Citations (4)
| Title |
|---|
| 信用风险管理:从估计到看见;赵先信;;金融电子化;20191115(第11期);全文 * |
| 基于数据挖掘的商户风险评分方法和系统;孙权;赵金涛;;软件产业与工程;20160110(第01期);全文 * |
| 海南农业小额贷款风险管理技术探索;吴敏;白宗钦;邵明;符江;郑德智;黄鹏云;;中国金融电脑;20171107(第11期);全文 * |
| 系统性金融风险指标的比较分析――基于实体经济风险预测的视角;黄乃静;于明哲;;系统工程理论与实践;20201023(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117853232A (en) | 2024-04-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117853232B (en) | Credit risk abnormity inspection attribution early warning method and system | |
| CN117149797B (en) | Accounting method and system based on multidimensional data monitoring | |
| CN113298121B (en) | Message sending method and device based on multi-data source modeling and electronic equipment | |
| CN111242424A (en) | Quality data processing method and device | |
| CN115795922B (en) | Equipment operation management method, system and medium based on equipment health degree | |
| CN110852602A (en) | Data monitoring method and device based on machine learning | |
| CN116485552A (en) | Fund investment wind control method, device, medium and terminal | |
| CN117333290B (en) | Integrated multi-scale wind control model construction method | |
| CN113506175A (en) | Method, device, equipment and storage medium for optimizing risk early warning model of medium and small enterprises | |
| CN117007977B (en) | Energy storage battery health state diagnosis method | |
| CN114219611A (en) | Loan amount calculation method and device, computer equipment and storage medium | |
| CN116823451B (en) | Credit risk control method and system | |
| CN116596674A (en) | External trade risk assessment method based on big data analysis | |
| CN110738327A (en) | quick pile filling equipment risk assessment method and system | |
| CN110111200A (en) | A kind of data exception intelligent control method and intelligent monitoring and controlling device based on PSI | |
| KR20230157115A (en) | Method for configuring battery portpolio for providing financial service based on e-mobility battery valuation and apparatus for performing the method | |
| CN115271907A (en) | Method for evaluating small and medium-sized micro-enterprises based on public data and related equipment | |
| CN113643125A (en) | Credit line measuring and calculating method, equipment and medium | |
| CN111967980A (en) | System and method for bank credit analysis by adopting maximum entropy model based on enterprise financial and newspaper and energy consumption data | |
| CN108280151B (en) | Method and system for monitoring data cleaning quality | |
| CN111325391A (en) | Enterprise production failure prediction system and method of nonlinear sparse twin support vector machine | |
| CN115545882B (en) | Credit risk prediction method based on newly increased credit reject ratio | |
| CN117114858B (en) | Collocation realization method of calculation checking formula based on averator expression | |
| CN118071154B (en) | Internal control intelligent auditing system and method based on data processing | |
| CN118279048B (en) | Automatic generation method and system for wind control strategy |
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 |