CN118071490B - Credit risk trend prediction system based on moving average model - Google Patents
Credit risk trend prediction system based on moving average model Download PDFInfo
- Publication number
- CN118071490B CN118071490B CN202410361518.1A CN202410361518A CN118071490B CN 118071490 B CN118071490 B CN 118071490B CN 202410361518 A CN202410361518 A CN 202410361518A CN 118071490 B CN118071490 B CN 118071490B
- Authority
- CN
- China
- Prior art keywords
- data
- comparison
- unit
- prediction
- processor
- 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
- 238000012545 processing Methods 0.000 claims abstract description 55
- 238000012544 monitoring process Methods 0.000 claims abstract description 30
- 238000004458 analytical method Methods 0.000 claims description 33
- 238000004364 calculation method Methods 0.000 claims description 27
- 230000008859 change Effects 0.000 claims description 12
- 238000013480 data collection Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 8
- 238000013500 data storage Methods 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000013058 risk prediction model Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 230000007306 turnover Effects 0.000 description 1
Abstract
The invention provides a credit risk trend prediction system based on a moving average model, which relates to the field of electric digital data processing, and comprises a data acquisition module, a model processing module, a risk prediction module and a monitoring alarm module, wherein the data acquisition module is used for acquiring credit data, the model processing module is used for carrying out moving average processing on the credit data, the risk prediction module predicts risks based on model processing results, and the monitoring alarm module is used for monitoring risk values and generating alarms; according to the system, the fluctuation is reduced by carrying out moving average processing on the data of the target object, and the credit risk is predicted by combining the relation between different data, so that the existing problems can be found and processed in time.
Description
Technical Field
The invention relates to the field of electric digital data processing, in particular to a credit risk trend prediction system based on a moving average model.
Background
In today's economic environment, the continual development and change in the credit market presents a significant challenge to risk management for financial institutions. Particularly for enterprise credit, assessment and management of credit risk is important due to the complexity of enterprise operations and uncertainty of macro economic environment. Traditional credit risk assessment methods rely mainly on expert experience and static financial index analysis, which, although capable of assessing credit risk to some extent, have limitations in predicting risk trends and identifying potential risks, and therefore, a system capable of accurately predicting credit risk is needed to assist in financial management.
The foregoing discussion of the background art is intended to facilitate an understanding of the present invention only. This discussion is not an admission or admission that any of the material referred to was common general knowledge.
A number of risk prediction systems have been developed, and through extensive searching and referencing, existing risk prediction systems are found to have the system as disclosed in publication number CN115545882B, which generally includes statistics of existing credit data, classification of the existing credit data by credit five-level classification of large types and large type subdivision, and setting of a credit failure rate standard reference type library; the method comprises the steps of monitoring newly-added credit information data in real time, and counting the newly-added credit information data to obtain newly-added credit information monitoring data; preprocessing the newly added credit information monitoring data, and analyzing the credit reject ratio standard reference type through a multi-classification support vector machine credit classification model to obtain the newly added credit reject ratio standard reference type; and according to the standard reference type of the new credit defective rate, performing intelligent early warning prediction on the new credit risk through a new credit defective rate risk prediction model. However, the system predicts by setting a standard library for comparison, which lacks of dynamics, and needs to continuously adjust standard library information to ensure the accuracy of prediction.
Disclosure of Invention
The invention aims to provide a credit risk trend prediction system based on a moving average model for overcoming the defects.
The invention adopts the following technical scheme:
A credit risk trend prediction system based on a moving average model comprises a credit risk trend prediction system based on the moving average model, and comprises a data acquisition module, a model processing module, a risk prediction module and a monitoring alarm module;
the data acquisition module is used for acquiring credit data, the model processing module is used for carrying out moving average processing on the credit data, the risk prediction module predicts risks based on model processing results, and the monitoring alarm module is used for monitoring risk values and generating alarms;
The data acquisition module comprises an object analysis unit and a data collection unit, wherein the object analysis unit is used for analyzing a target object to obtain a data path, and the data collection unit is used for acquiring credit data of the target object based on the data path;
The model processing module comprises an average processing unit and a mobile processing unit, wherein the average processing unit is used for processing the average value of various credit data, and the mobile processing unit is used for carrying out characteristic analysis on the change of the average value;
The risk prediction module comprises a feature comparison unit and a quantitative prediction unit, wherein the feature comparison unit is used for comparing different types of feature data, and the quantitative prediction unit outputs a predicted value of credit risk based on a comparison result;
the monitoring alarm module comprises a monitoring record unit and an alarm judging unit, wherein the monitoring record unit is used for recording predicted values of all target objects in different periods, and the alarm judging unit is used for judging and analyzing whether the current predicted values are to be alarmed or not;
Further, the average processing unit comprises a segment sampling processor, a mean value calculating processor and a data aligning processor, wherein the segment sampling processor is used for acquiring data information of a time period from a data storage register, the mean value calculating processor is used for calculating a mean value, and the data aligning processor is used for aligning different types of mean values;
Further, the mobile processing unit comprises a trend analysis processor and a degree analysis processor, wherein the trend analysis processor is used for analyzing and obtaining the change trend characteristics of the data set, and the degree analysis processor is used for analyzing and obtaining the change degree characteristics of the data set;
Further, the feature comparison unit comprises a comparison information register and a comparison calculation processor, wherein the comparison information register is used for storing the content of each comparison item and comparison parameters, and the comparison calculation processor is used for calculating the comparison result of each comparison item;
the content of the comparison item refers to two data types for comparison;
the contrast calculation processor calculates a contrast result RC of each contrast term according to the following formula:
;
Wherein, As the coefficient of the correlation(s),P1 and P2 are two trend indexes respectively, and Q1 and Q2 are two degree indexes respectively;
Further, the quantitative prediction unit comprises a comparison result register and a prediction calculation processor, wherein the comparison result register is used for receiving and storing a comparison result of each comparison item, and the prediction calculation processor calculates a prediction value YC based on the comparison result;
The prediction calculation processor calculates a risk value YC according to the following formula:
;
Where N is the number of comparison items, RC i is the comparison result of the ith comparison item, and k i is the weight coefficient of the ith comparison item.
The beneficial effects obtained by the invention are as follows:
The system preprocesses the collected data through the moving average model, can reduce the interference of some accidental abnormal data on the prediction result, predicts risks through analyzing trend characteristics of each type of data and comparing trend relations among different types of data, can continuously analyze effective information, timely generates alarms, and provides reliable references for financial management.
For a further understanding of the nature and the technical aspects of the present invention, reference should be made to the following detailed description of the invention and the accompanying drawings, which are provided for purposes of reference only and are not intended to limit the invention.
Drawings
FIG. 1 is a schematic diagram of the overall structural framework of the present invention;
FIG. 2 is a schematic diagram of a model processing module according to the present invention;
FIG. 3 is a schematic diagram of a risk prediction module according to the present invention;
FIG. 4 is a schematic diagram of an average processing unit configuration of the present invention;
FIG. 5 is a schematic diagram of a feature comparison unit according to the present invention.
Detailed Description
The following embodiments of the present invention are described in terms of specific examples, and those skilled in the art will appreciate the advantages and effects of the present invention from the disclosure herein. The invention is capable of other and different embodiments and its several details are capable of modification and variation in various respects, all without departing from the spirit of the present invention. The drawings of the present invention are merely schematic illustrations, and are not intended to be drawn to actual dimensions. The following embodiments will further illustrate the related art content of the present invention in detail, but the disclosure is not intended to limit the scope of the present invention.
Embodiment one: the embodiment provides a credit risk trend prediction system based on a moving average model, which comprises a credit risk trend prediction system based on the moving average model, and a data acquisition module, a model processing module, a risk prediction module and a monitoring alarm module, wherein the credit risk trend prediction system is shown in the figure 1;
the data acquisition module is used for acquiring credit data, the model processing module is used for carrying out moving average processing on the credit data, the risk prediction module predicts risks based on model processing results, and the monitoring alarm module is used for monitoring risk values and generating alarms;
The data acquisition module comprises an object analysis unit and a data collection unit, wherein the object analysis unit is used for analyzing a target object to obtain a data path, and the data collection unit is used for acquiring credit data of the target object based on the data path;
The model processing module comprises an average processing unit and a mobile processing unit, wherein the average processing unit is used for processing the average value of various credit data, and the mobile processing unit is used for carrying out characteristic analysis on the change of the average value;
The risk prediction module comprises a feature comparison unit and a quantitative prediction unit, wherein the feature comparison unit is used for comparing different types of feature data, and the quantitative prediction unit outputs a predicted value of credit risk based on a comparison result;
the monitoring alarm module comprises a monitoring record unit and an alarm judging unit, wherein the monitoring record unit is used for recording predicted values of all target objects in different periods, and the alarm judging unit is used for judging and analyzing whether the current predicted values are to be alarmed or not;
The average processing unit comprises a segment sampling processor, a mean value calculation processor and a data alignment processor, wherein the segment sampling processor is used for acquiring data information of a time period from a data storage register, the mean value calculation processor is used for calculating a mean value, and the data alignment processor is used for aligning different types of mean values;
The mobile processing unit comprises a trend analysis processor and a degree analysis processor, wherein the trend analysis processor is used for analyzing and obtaining the change trend characteristics of the data set, and the degree analysis processor is used for analyzing and obtaining the change degree characteristics of the data set;
The characteristic comparison unit comprises a comparison information register and a comparison calculation processor, wherein the comparison information register is used for storing the content of each comparison item and comparison parameters, and the comparison calculation processor is used for calculating the comparison result of each comparison item;
the content of the comparison item refers to two data types for comparison;
the contrast calculation processor calculates a contrast result RC of each contrast term according to the following formula:
;
Wherein, As the coefficient of the correlation(s),P1 and P2 are two trend indexes respectively, and Q1 and Q2 are two degree indexes respectively;
The quantitative prediction unit comprises a comparison result register and a prediction calculation processor, the comparison result register is used for receiving and storing the comparison result of each comparison item, and the prediction calculation processor calculates a prediction value YC based on the comparison result;
The prediction calculation processor calculates a risk value YC according to the following formula:
;
Where N is the number of comparison items, RC i is the comparison result of the ith comparison item, and k i is the weight coefficient of the ith comparison item.
Embodiment two: the embodiment comprises the whole content of the first embodiment, and provides a credit risk trend prediction system based on a moving average model, which comprises a data acquisition module, a model processing module, a risk prediction module and a monitoring alarm module;
the data acquisition module is used for acquiring credit data, the model processing module is used for carrying out moving average processing on the credit data, the risk prediction module predicts risks based on model processing results, and the monitoring alarm module is used for monitoring risk values and generating alarms;
The data acquisition module comprises an object analysis unit and a data collection unit, wherein the object analysis unit is used for analyzing a target object to obtain a data path, and the data collection unit is used for acquiring credit data of the target object based on the data path;
referring to fig. 2, the model processing module includes an average processing unit for processing an average value of various credit data and a mobile processing unit for performing feature analysis on a variation of the average value;
Referring to fig. 3, the risk prediction module includes a feature comparison unit for comparing different types of feature data and a quantitative prediction unit for outputting a predicted value of credit risk based on a comparison result;
the monitoring alarm module comprises a monitoring record unit and an alarm judging unit, wherein the monitoring record unit is used for recording predicted values of all target objects in different periods, and the alarm judging unit is used for judging and analyzing whether the current predicted values are to be alarmed or not;
the data collection unit comprises a communication connection processor, a data classification processor and a data storage register, wherein the communication connection processor is connected with an external server based on a data path, the data classification processor is used for acquiring data from the external server and classifying the data, and the data storage register is used for storing the classified data;
the data types collected by the data collection unit comprise information types related to credit, such as turnover, profit, debt and the like;
referring to fig. 4, the average processing unit includes a segment sampling processor, an average value calculating processor and a data alignment processor, where the segment sampling processor is configured to obtain data information of a time period from a data storage register, the average value calculating processor is configured to calculate an average value, and the data alignment processor is configured to align different types of average values;
The segmented sampling processor receives a time point t 0, and sets a time period according to the time point t 0 Wherein T is the duration of the time period;
The mean value calculation processor calculates a mean value of each time period as a data value V (t 0) of a corresponding time point according to:
;
Wherein, An i-th value in the corresponding time period is represented, and n is the number of data in the corresponding time period;
It should be noted that the number of data of different types in the corresponding time period is not necessarily the same;
The data alignment processor aligns and reorders the values of the same time points of different types to obtain a data set A single data V j (i) in the dataset represents the ith data value of the jth type;
The mobile processing unit comprises a trend analysis processor and a degree analysis processor, wherein the trend analysis processor is used for analyzing and obtaining the change trend characteristics of the data set, and the degree analysis processor is used for analyzing and obtaining the change degree characteristics of the data set;
The process of analyzing the data set by the trend analysis processor comprises the following steps:
s1, comparing two adjacent data in the data set to obtain a difference value ;
S2, counting to obtain the number of positive numbers and the number of negative numbers in the difference value, respectively usingAndA representation;
S3, comparing the first number with the last number in the data set to obtain a difference value ;
S4, calculating trend index P of the data set according to the following formula:
;
Wherein, For adjusting coefficients, m is the number of data in the data set, sig () is a positive and negative function;
the positive and negative functions have the following values:
;
wherein a is the parameter of positive and negative functions, Is a trend base;
the process of analyzing the data set by the degree analysis processor comprises the following steps:
s21, comparing two adjacent data in the data set to obtain a difference value ;
S22, comparing the first number with the last number in the data set to obtain a difference value;
S23, calculating a degree index Q of the data set according to the following formula:
;
Wherein, Representation ofThe number of the three is a positive number,Representation ofThe middle is a negative number;
referring to fig. 5, the feature comparison unit includes a comparison information register for storing contents of each comparison item and comparison parameters, and a comparison calculation processor for calculating a comparison result of each comparison item;
the content of the comparison item refers to two data types for comparison;
the contrast calculation processor calculates a contrast result RC of each contrast term according to the following formula:
;
Wherein, As the coefficient of the correlation(s),P1 and P2 are two trend indexes respectively, and Q1 and Q2 are two degree indexes respectively;
The quantitative prediction unit comprises a comparison result register and a prediction calculation processor, the comparison result register is used for receiving and storing the comparison result of each comparison item, and the prediction calculation processor calculates a prediction value YC based on the comparison result;
The prediction calculation processor calculates a risk value YC according to the following formula:
;
Wherein N is the number of comparison items, RC i is the comparison result of the ith comparison item, and k i is the weight coefficient of the ith comparison item;
The alarm judging unit comprises a threshold value setting processor and an alarm prompting processor, wherein the threshold value setting processor analyzes the historical risk value and sets a threshold value, and the alarm prompting processor prompts an alarm when the risk value is higher than the threshold value;
the threshold setting processor sets a threshold YZ according to:
;
Wherein Y 0 is a basic value, YC' is a risk value mean value in a stable range, Is a threshold scaling factor.
The foregoing disclosure is only a preferred embodiment of the present invention and is not intended to limit the scope of the invention, so that all equivalent technical changes made by applying the description of the present invention and the accompanying drawings are included in the scope of the present invention, and in addition, elements in the present invention can be updated as the technology develops.
Claims (2)
1. The credit risk trend prediction system based on the moving average model is characterized by comprising a data acquisition module, a model processing module, a risk prediction module and a monitoring alarm module;
the data acquisition module is used for acquiring credit data, the model processing module is used for carrying out moving average processing on the credit data, the risk prediction module predicts risks based on model processing results, and the monitoring alarm module is used for monitoring risk values and generating alarms;
The data acquisition module comprises an object analysis unit and a data collection unit, wherein the object analysis unit is used for analyzing a target object to obtain a data path, and the data collection unit is used for acquiring credit data of the target object based on the data path;
The model processing module comprises an average processing unit and a mobile processing unit, wherein the average processing unit is used for processing the average value of various credit data, and the mobile processing unit is used for carrying out characteristic analysis on the change of the average value;
The risk prediction module comprises a feature comparison unit and a quantitative prediction unit, wherein the feature comparison unit is used for comparing different types of feature data, and the quantitative prediction unit outputs a predicted value of credit risk based on a comparison result;
the monitoring alarm module comprises a monitoring record unit and an alarm judging unit, wherein the monitoring record unit is used for recording predicted values of all target objects in different periods, and the alarm judging unit is used for judging and analyzing whether the current predicted values are to be alarmed or not;
The mobile processing unit comprises a trend analysis processor and a degree analysis processor, wherein the trend analysis processor is used for analyzing and obtaining the change trend characteristics of the data set, and the degree analysis processor is used for analyzing and obtaining the change degree characteristics of the data set;
The process of analyzing the data set by the trend analysis processor comprises the following steps:
s1, comparing two adjacent data in the data set to obtain a difference value ;
S2, counting to obtain the number of positive numbers and the number of negative numbers in the difference value, respectively usingAndA representation;
S3, comparing the first number with the last number in the data set to obtain a difference value ;
S4, calculating trend index P of the data set according to the following formula:
;
Wherein, For adjusting coefficients, m is the number of data in the data set, sig () is a positive and negative function;
the positive and negative functions have the following values:
;
wherein a is the parameter of positive and negative functions, Is a trend base;
the process of analyzing the data set by the degree analysis processor comprises the following steps:
s21, comparing two adjacent data in the data set to obtain a difference value ;
S22, comparing the first number with the last number in the data set to obtain a difference value;
S23, calculating a degree index Q of the data set according to the following formula:
;
Wherein, Representation ofThe number of the three is a positive number,Representation ofThe middle is a negative number;
The characteristic comparison unit comprises a comparison information register and a comparison calculation processor, wherein the comparison information register is used for storing the content of each comparison item and comparison parameters, and the comparison calculation processor is used for calculating the comparison result of each comparison item;
the content of the comparison item refers to two data types for comparison;
the contrast calculation processor calculates a contrast result RC of each contrast term according to the following formula:
;
Wherein, As the coefficient of the correlation(s),P1 and P2 are two trend indexes respectively, and Q1 and Q2 are two degree indexes respectively;
The quantitative prediction unit comprises a comparison result register and a prediction calculation processor, the comparison result register is used for receiving and storing the comparison result of each comparison item, and the prediction calculation processor calculates a prediction value YC based on the comparison result;
The prediction calculation processor calculates a risk value YC according to the following formula:
;
Where N is the number of comparison items, RC j is the comparison result of the jth comparison item, and k j is the weight coefficient of the jth comparison item.
2. The moving average model-based credit risk trend prediction system of claim 1, wherein the average processing unit includes a segment sampling processor for acquiring data information for a period of time from the data storage registers, a mean calculation processor for calculating a mean value, and a data alignment processor for aligning different types of mean values.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410361518.1A CN118071490B (en) | 2024-03-28 | Credit risk trend prediction system based on moving average model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410361518.1A CN118071490B (en) | 2024-03-28 | Credit risk trend prediction system based on moving average model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN118071490A CN118071490A (en) | 2024-05-24 |
CN118071490B true CN118071490B (en) | 2024-07-05 |
Family
ID=
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113327160A (en) * | 2021-05-07 | 2021-08-31 | 浙江保融科技股份有限公司 | Bank post-loan risk prediction method and system based on enterprise financial and capital big data |
CN117333288A (en) * | 2023-11-21 | 2024-01-02 | 中电金信数字科技集团有限公司 | Credit risk assessment method, credit risk assessment device, electronic equipment and storage medium |
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113327160A (en) * | 2021-05-07 | 2021-08-31 | 浙江保融科技股份有限公司 | Bank post-loan risk prediction method and system based on enterprise financial and capital big data |
CN117333288A (en) * | 2023-11-21 | 2024-01-02 | 中电金信数字科技集团有限公司 | Credit risk assessment method, credit risk assessment device, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111178456B (en) | Abnormal index detection method and device, computer equipment and storage medium | |
CN107742127B (en) | Improved electricity stealing prevention intelligent early warning system and method | |
CN101714273A (en) | Rule engine-based method and system for monitoring exceptional service of bank | |
US20200286095A1 (en) | Method, apparatus and computer programs for generating a machine-learning system and for classifying a transaction as either fraudulent or genuine | |
CN116132104A (en) | Intrusion detection method, system, equipment and medium based on improved CNN-LSTM | |
CN111340086A (en) | Method, system, medium and terminal for processing label-free data | |
CN116485552A (en) | Fund investment wind control method, device, medium and terminal | |
CN115238815A (en) | Abnormal transaction data acquisition method, device, equipment, medium and program product | |
Yahaya et al. | An enhanced bank customers churn prediction model using a hybrid genetic algorithm and k-means filter and artificial neural network | |
Ahmed et al. | Enhancing stock portfolios for enterprise management and investment in energy industry | |
CN118071490B (en) | Credit risk trend prediction system based on moving average model | |
CN112329862A (en) | Decision tree-based anti-money laundering method and system | |
CN110770753B (en) | Device and method for real-time analysis of high-dimensional data | |
CN118071490A (en) | Credit risk trend prediction system based on moving average model | |
CN112348220A (en) | Credit risk assessment prediction method and system based on enterprise behavior pattern | |
US11954685B2 (en) | Method, apparatus and computer program for selecting a subset of training transactions from a plurality of training transactions | |
Wang | Abnormal behavior identification of enterprise cloud platform financial system based on artificial neural network | |
CN113935819A (en) | Method for extracting checking abnormal features | |
CN115438239A (en) | Abnormity detection method and device for automatic abnormal sample screening | |
Zimal et al. | Customer churn prediction using machine learning | |
CN117592904A (en) | Warehouse-in and warehouse-out material identification and quantity analysis method | |
CN117975204B (en) | Model training method, defect detection method and related device | |
CN115170166B (en) | Big data sensing method and system for judging monopoly behavior | |
CN113689297A (en) | Network transaction information tracing system | |
CN118212057A (en) | Credit card fraud detection neural rule construction method and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |