Defective asset full-period management system and method

Abstract

The invention discloses a non-performing asset full-period management system and method, and relates to the technical field of non-performing asset management. The system comprises a data acquisition module, an asset analysis module, an asset verification module and an asset management module. Historical performance trends of assets are evaluated through time sequence analysis, trend indexes are generated, bad asset behavior characteristics are extracted, differences of the bad asset behavior characteristics are analyzed to evaluate abnormal risks, performance indexes are generated by integrating the trend indexes and risk indexes through an analytic hierarchy process, and risk marking is carried out through threshold value comparison. And carrying out visual display on the marked data, dynamically monitoring the unhealthy assets, and generating priority disposal information based on the performance index. According to the method, systematicness, accuracy and real-time performance of bad asset management are improved, and more efficient risk identification and resource optimization configuration are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of non-performing asset management, and in particular to a full-cycle management system and method for non-performing assets. Background Art

[0002] Traditional asset management systems often lack real-time monitoring capabilities and are unable to respond to drastic market fluctuations in a timely manner. In the context of Internet lending platforms, borrowers' risks may change at any time, so real-time monitoring and early warning become essential functions. Through data analysis and verification modules, the system generates risk-return indexes in real time and conducts comprehensive analysis, providing timely and accurate risk early warning information for the asset management module, ensuring the flexibility and response speed of non-performing asset management, and reducing the complexity of system operation and maintenance.

[0003] For example, the full life cycle non-performing asset management system and non-performing asset management method with announcement number CN109658228B include an asset release module, an asset pricing module, an asset distribution module, and an asset collection module; the asset release module integrates and connects the non-performing assets with the non-performing asset management system; the asset pricing module integrates the non-performing assets and performs standard pricing on the non-performing assets according to different market conditions and different business characteristics; the asset distribution module uses the intelligent distribution strategy of the distribution model to intelligently distribute to the matching asset processing agency; the asset collection module collects the non-performing assets. In addition, the present invention also discloses a non-performing asset management method. The full life cycle non-performing asset management system and non-performing asset management method proposed in the present invention realize the asset management of the non-performing assets throughout the life cycle, can prevent the generation of non-performing assets, and can provide customized processing solutions according to different stages of the full life cycle of non-performing assets.

[0004] For example, a full-cycle management system and method for non-performing assets with publication number CN114202407A includes an upload module, an identification module, a template module to be filled, a filling module, a pre-stored module, a pre-stored material review module, a storage module, an intelligent case division module, a case filing material template module, a case filing material generation module, a case filing module, a receiving module, an archiving module, and a case file module. The present invention has the following beneficial effects: the system collects non-performing asset information uploaded by users, files non-performing assets and archives them when closing the case, and manages the non-performing assets throughout the cycle, thereby reducing manual participation, simplifying the manual work process, and greatly improving work efficiency; it can adapt to the management of non-performing assets in different regions and with different requirements, has a wider scope of application, and is convenient for large-scale promotion and use.

[0005] However, the above-mentioned traditional non-performing asset management systems usually rely on fixed processing procedures and predetermined strategies, which limits the flexibility and response speed of the system in dealing with emergencies. When market conditions change rapidly, the system may not be able to adjust the processing strategy in time, resulting in further expansion of the risk of non-performing assets. The lack of real-time data monitoring and early warning mechanisms makes it impossible to respond in time when risks occur. This defect is particularly evident in the context of Internet lending platforms, because the risk situation of borrowers may change rapidly and traditional systems cannot capture these changes in time. Summary of the invention

[0006] In view of the deficiencies in the prior art, the present invention provides a full-cycle management system and method for non-performing assets, which solves the problems of the above-mentioned background technology.

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a full-cycle management system for non-performing assets, including the following modules: a data acquisition module, an asset analysis module, an asset verification module, and an asset management module; the asset data acquisition module is used to obtain the non-performing asset data of non-performing customers, evaluate the historical performance trend of non-performing assets through time series analysis, and generate a non-performing asset trend index; the asset data analysis module is used to extract the bad behavior characteristics of non-performing asset data, analyze the characteristic differences of non-performing assets, determine the type of non-performing customers, and evaluate the abnormal risk index of non-performing assets; the asset verification module is used to comprehensively analyze the non-performing asset trend index and the non-performing asset abnormal risk index, obtain the non-performing asset performance index, verify the non-performing customers through threshold comparison and mark them; the asset management module uniformly stores and visualizes the non-performing asset data of marked non-performing customers, continuously monitors the dynamic performance of non-performing assets, sorts the non-performing customers according to the non-performing asset performance index, and generates priority disposal information.

[0008] Furthermore, the specific process of evaluating the historical performance trend of non-performing assets through time series analysis is as follows: based on the non-performing asset data of non-performing customers, the historical trend and periodicity of the non-performing asset data are analyzed through the time series analysis algorithm, and the non-performing asset trend equation is constructed; based on the non-performing asset trend equation, the future performance of the non-performing assets is predicted and a trend line is generated.

[0009] Furthermore, the specific process of generating the non-performing asset trend index is as follows: according to the non-performing asset trend equation and trend line, the slope of the trend line and the deviation of the trend line are analyzed, and the slope and the deviation are combined to generate the non-performing asset trend index.

[0010] Furthermore, the bad behavior characteristics of the non-performing asset data are extracted, the characteristic differences of the non-performing assets are analyzed, and the types of non-performing customers are determined. The specific process is as follows: behavioral characteristics are extracted from the non-performing asset data, and the behavioral characteristics include the number of overdue payments, overdue amount, and repayment history; the extracted characteristics are clustered according to the cluster analysis algorithm, and the non-performing customers are classified according to the set customer type.

[0011] Furthermore, the specific process of evaluating the abnormal risk index of non-performing assets is as follows: based on customer type and behavioral characteristics, risk assessment indicators are defined, including overdue frequency threshold, overdue amount ratio threshold, and repayment default rate threshold; based on the risk assessment indicators, the difference in abnormal risk indicators is calculated for each type of customer to generate an abnormal risk index for non-performing assets.

[0012] Furthermore, the non-performing asset trend index and the non-performing asset abnormal risk index are comprehensively analyzed through the hierarchical analysis method, and the specific process of obtaining the non-performing asset performance index is as follows: weights are assigned to the non-performing asset trend index and the non-performing asset abnormal risk index through the hierarchical analysis method to obtain the weight factor of the non-performing asset trend index and the weight factor of the non-performing asset abnormal risk index; the weight factor of the non-performing asset trend index and the weight factor of the non-performing asset abnormal risk index are comprehensively calculated with the non-performing asset trend index and the non-performing asset abnormal risk index to obtain the non-performing asset performance index.

[0013] Furthermore, the specific process of verifying and marking bad customers through threshold comparison is as follows: if the performance index of bad assets exceeds the set first threshold, the bad customer is marked as a high-risk customer; if the performance index of bad assets is between the first threshold and the second threshold, the bad customer is marked as a medium-risk customer; if the performance index of bad assets is lower than the second threshold, the bad customer is marked as a low-risk customer.

[0014] Furthermore, the specific process of sorting non-performing customers according to the non-performing asset performance index and generating priority disposal information is as follows: the marked high-risk customers, medium-risk customers and low-risk customers are stored in corresponding lists, and the non-performing customers are sorted in descending order according to the non-performing asset performance index.

[0015] A full-cycle management method for non-performing assets includes the following steps: S1. Obtaining non-performing asset data of non-performing customers, evaluating the historical performance trend of non-performing assets through time series analysis, and generating a non-performing asset trend index; S2. Extracting the bad behavior characteristics of the non-performing asset data, analyzing the characteristic differences of non-performing assets, determining the type of non-performing customers, and evaluating the abnormal risk index of non-performing assets; S3. Comprehensively analyzing the non-performing asset trend index and the non-performing asset abnormal risk index through the hierarchical analysis method to obtain the non-performing asset performance index, verifying the non-performing customers through threshold comparison and marking them; S4. Unified storage and visualization of the non-performing asset data of marked non-performing customers, and continuously monitoring the dynamic performance of non-performing assets, sorting the non-performing customers according to the non-performing asset performance index, and generating priority disposal information.

[0016] The present invention has the following beneficial effects: (1) This full-cycle management system for non-performing assets can comprehensively evaluate the historical performance trends of non-performing assets and generate trend indexes through time series analysis of the data acquisition module. It improves the accuracy and reliability of data processing and lays a solid foundation for subsequent analysis. It extracts and analyzes the key behavioral characteristics of non-performing assets, identifies characteristic differences and determines customer types, and evaluates abnormal risk indexes. It enhances the accuracy of risk identification and helps to effectively formulate risk management strategies.

[0017] (2) This is a full-cycle management method for non-performing assets. It uses the analytic hierarchy process to comprehensively analyze the non-performing asset trend index and abnormal risk index, generate a non-performing asset performance index, and mark customers for risk through threshold comparison. This comprehensive assessment method ensures the comprehensiveness of risk identification and the accuracy of marking, and provides a scientific basis for priority disposal. The marked customer data is uniformly stored and monitored in real time, and customers are sorted and prioritized according to the non-performing asset performance index. Real-time dynamic management and the generation of priority disposal information improve processing efficiency, optimize resource allocation, and make non-performing asset management more efficient and accurate.

[0018] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The present invention is a flowchart of a full-cycle management system and method for non-performing assets.

[0020] Figure 2 The present invention is a flowchart of a full-cycle management system and method for non-performing assets. DETAILED DESCRIPTION

[0021] The embodiment of the present application solves the problem of xx through a full-cycle management system and method for non-performing assets.

[0022] The overall idea of ​​the problem in the embodiment of this application is as follows: Obtain the non-performing asset data of non-performing customers, evaluate the historical performance trend of non-performing assets through time series analysis, and generate a non-performing asset trend index.

[0023] Extract bad behavior characteristics of non-performing asset data, analyze the characteristic differences of non-performing assets, determine the type of non-performing customers, and evaluate the abnormal risk index of non-performing assets.

[0024] The non-performing asset trend index and the non-performing asset abnormal risk index are comprehensively analyzed through the hierarchical analysis method to obtain the non-performing asset performance index, and the non-performing customers are verified and marked through threshold comparison.

[0025] The non-performing asset data of marked non-performing customers are uniformly stored and visualized, and the dynamic performance of non-performing assets is continuously monitored. Non-performing customers are sorted according to the non-performing asset performance index and priority disposal information is generated.

[0026] See also Figure 1 The embodiment of the present invention provides a technical solution: a full-cycle management system for non-performing assets, including the following modules: a data acquisition module, an asset analysis module, an asset verification module, and an asset management module; the asset data acquisition module is used to obtain the non-performing asset data of non-performing customers, evaluate the historical performance trend of non-performing assets through time series analysis, and generate a non-performing asset trend index; the asset data analysis module is used to extract the bad behavior characteristics of non-performing asset data, analyze the characteristic differences of non-performing assets, determine the type of non-performing customers, and evaluate the abnormal risk index of non-performing assets; the asset verification module is used to comprehensively analyze the non-performing asset trend index and the non-performing asset abnormal risk index, obtain the non-performing asset performance index, verify the non-performing customers through threshold comparison and mark them; the asset management module uniformly stores and visualizes the non-performing asset data of the marked non-performing customers, continuously monitors the dynamic performance of non-performing assets, sorts the non-performing customers according to the non-performing asset performance index, and generates priority disposal information.

[0027] In this implementation scheme, the data acquisition module is responsible for collecting data related to non-performing assets from non-performing customers, including but not limited to the overdue records, repayment history and overdue amount of assets. These data are used for subsequent analysis and processing. The asset data acquisition module is used to acquire and integrate the asset data of non-performing customers, evaluate the historical performance trend of non-performing assets through time series analysis, and generate a non-performing asset trend index. This index reflects the overall trend of non-performing assets over time. Time series analysis is used to analyze time series data (i.e., data points arranged in chronological order) to identify trends, cyclical and seasonal changes in the data. Through this analysis, a non-performing asset trend index can be generated to predict future asset performance.

[0028] The non-performing asset trend index is an index generated through time series analysis, reflecting the historical performance trend of non-performing assets. This index helps evaluate the long-term trend and future performance of assets. Cluster analysis, by grouping data (i.e. "clustering"), makes the similarity between data points in the same group higher, while the similarity between data points in different groups lower. In non-performing asset management, it is used to extract behavioral characteristics and identify the types of non-performing customers. The hierarchical analysis method decomposes complex problems into multiple levels, uses comparative judgment to quantify the relative importance of each level, and thus conducts a comprehensive analysis of the non-performing asset trend index and the abnormal risk index to generate the non-performing asset performance index. Threshold comparison is a data classification method that classifies data by setting a threshold. In non-performing asset management, by comparing with the set threshold, non-performing customers are marked as high risk, medium risk or low risk to assist decision-making and priority disposal. Priority disposal information: information generated after sorting non-performing customers based on the non-performing asset performance index, used to determine which customers need to be handled first. This helps optimize resource allocation and improve processing efficiency.

[0029] Specifically, the specific process of evaluating the historical performance trend of non-performing assets through time series analysis is as follows: based on the non-performing asset data of non-performing customers, the historical trend and periodicity of the non-performing asset data are analyzed through the time series analysis algorithm, and the non-performing asset trend equation is constructed; based on the non-performing asset trend equation, the future performance of the non-performing assets is predicted and a trend line is generated.

[0030] In this implementation, the bad asset data of bad customers are collected, including time series data, such as monthly overdue amounts and arrears records. The time series analysis algorithm is used to analyze the historical trend and periodicity of the data. A trend equation is constructed to describe the long-term trend and fluctuation of the data. The bad asset trend equation is as follows: ,explain: It represents the baseline level in the trend equation, that is, the initial value or benchmark value of the data. The mean of the data is estimated by the least squares method as the initial estimate, and then optimized by regression analysis to obtain the best fit value of the model. It represents the linear trend slope, reflecting the linear growth or decrease rate of the non-performing asset value over time. If it is positive, it means that the asset value is increasing, and if it is negative, it means that the asset value is decreasing. The regression coefficient is obtained by fitting the historical data through the linear regression model. . Represents the amplitude of periodic fluctuations in the data, estimated by periodic regression analysis or Fourier transform, and fitting the sinusoidal fluctuation components in the data by nonlinear least squares method. Represents the amplitude of the cosine function, describing the amplitude of periodic changes, but based on cosine fluctuations, estimated by periodic regression analysis or Fourier transform, and is different from the amplitude of the sine function Together they capture the periodic nature of the data. represents the frequency of periodic fluctuations in the data, The error term represents the random error in the model. It is obtained by calculating the residual between the actual value and the predicted value to evaluate the goodness of fit of the model. The predicted values ​​of the data at future time points are calculated based on the trend equation, and these values ​​are plotted as trend lines. The trend lines show the long-term trend of the data and help visualize historical performance and future forecasts. Through the trend lines, you can intuitively understand the long-term trend of non-performing assets and facilitate the identification of continuous growth or decline trends.

[0031] Specifically, the specific process of generating the non-performing asset trend index is as follows: according to the non-performing asset trend equation and trend line, the slope of the trend line and the deviation of the trend line are analyzed, and the slope and deviation are combined to generate the non-performing asset trend index.

[0032] In this implementation plan, the deviation of the trend line is analyzed: the specific process and calculation formula for generating the non-performing asset trend index 1. The slope of the trend line is analyzed: Definition: Slope Reflects the rate of change of data over time. Calculation formula: Slope in, It is the coefficient of the trend equation obtained by linear regression analysis, indicating the rate of change. Definition: Deviation (D) indicates the difference between the actual data point and the trend line. Calculation formula: in, For actual data, To predict data, is the total number of data points. Comprehensive slope and deviation: Definition: The slope Combined with the deviation (D), the non-performing asset trend index (TI) is generated. Calculation formula: D Among them, is the baseline level, and SD is the standardized value of the deviation. The deviation (D) quantifies the fluctuation of the data. The non-performing asset trend index (TI) combines the trend direction and data fluctuation to provide a comprehensive assessment of the performance of non-performing assets. The non-performing asset trend index is used to measure the future performance trend of non-performing assets and their rate of change.

[0033] Specifically, extract the bad behavior characteristics of non-performing asset data, analyze the characteristic differences of non-performing assets, and determine the type of non-performing customers. The specific process is as follows: extract behavioral characteristics from non-performing asset data, and the behavioral characteristics include the number of overdue payments, overdue amount, and repayment history; cluster the extracted characteristics according to the cluster analysis algorithm, and classify the non-performing customers according to the set customer type.

[0034] In this implementation plan, the number of overdue payments reflects the instability of the customer's repayments. Frequent overdue payments usually mean higher risks. Overdue amount indicates the severity of the overdue. A larger overdue amount may indicate higher financial pressure. Repayment history helps understand the customer's repayment habits and behaviors and evaluate their financial management capabilities. Cluster analysis helps understand the common characteristics of different types of customers by clustering the customer's behavioral characteristics. Customer classification helps to classify and manage customers according to their behavioral patterns and formulate corresponding risk management strategies and intervention measures for different types of customers.

[0035] Specifically, the specific process of evaluating the abnormal risk index of non-performing assets is as follows: based on customer type and behavioral characteristics, risk assessment indicators are defined, including overdue frequency threshold, overdue amount ratio threshold, and repayment default rate threshold; based on the risk assessment indicators, the difference in abnormal risk indicators is calculated for each type of customer to generate an abnormal risk index for non-performing assets.

[0036] In this implementation scheme, the threshold of overdue frequency is used to identify whether the number of overdue payments of a customer exceeds the preset standard. Usually, an average value is determined through historical data statistics, and the threshold of the ratio of the overdue amount to the total loan amount is set. Based on the historical ratio data of the loan amount and the overdue amount, an early warning ratio is set. The threshold of the repayment default rate is used to evaluate whether the customer's repayment behavior meets the expected standard. By analyzing the customer's repayment history, a default rate standard is set. For each type of customer, the abnormal risk index of non-performing assets ( ), used to assess the risk profile of the client: ; Explanation of formula parameters, represents the abnormal risk index of non-performing assets of the i-th customer, represents the number of overdue payments for the i-th customer, represents the overdue amount of the i-th customer, represents the repayment default rate of the i-th customer, Indicates the overdue frequency threshold, Indicates the overdue amount ratio threshold, Represents the repayment default rate threshold. By defining and calculating the thresholds of overdue frequency, overdue amount ratio, and repayment default rate, the customer's behavioral characteristics are quantitatively analyzed. By calculating the difference in risk indicators for each customer and normalizing it into an abnormal risk index, high-risk customers can be effectively identified and classified. This approach not only provides accurate risk assessment, but also supports more targeted risk management measures, improving the accuracy and efficiency of asset management.

[0037] Specifically, the non-performing asset trend index and the non-performing asset abnormal risk index are comprehensively analyzed through the hierarchical analysis method, and the specific process of obtaining the non-performing asset performance index is as follows: weights are assigned to the non-performing asset trend index and the non-performing asset abnormal risk index through the hierarchical analysis method to obtain the weight factor of the non-performing asset trend index and the weight factor of the non-performing asset abnormal risk index; the weight factor of the non-performing asset trend index and the weight factor of the non-performing asset abnormal risk index are comprehensively calculated with the non-performing asset trend index and the non-performing asset abnormal risk index to obtain the non-performing asset performance index.

[0038] In this implementation scheme, the analytic hierarchy process is a multi-criteria decision analysis method that helps decision makers to integrate different factors to reach the final decision result by comparing and weighting decision factors. In non-performing asset management, the analytic hierarchy process can be used to integrate the non-performing asset trend index and the non-performing asset abnormal risk index to obtain the non-performing asset performance index. The process of obtaining the non-performing asset performance index is as follows: the analytic hierarchy process is used to determine the respective weight factors by comparing the relative importance of the non-performing asset trend index and the non-performing asset abnormal risk index. Represent the weights of the non-performing asset trend index and the abnormal risk index respectively. Comprehensive calculation of the non-performing asset performance index , multiply the weight factor by the corresponding index value, and then add them together to get the final non-performing asset performance index. , formula and parameter explanation, The weight factor of the non-performing asset trend index is used to measure the importance of the non-performing asset trend index in the non-performing asset performance index. The weight factor representing the abnormal risk index of non-performing assets is used to measure the importance of the abnormal risk index in the final non-performing asset performance index.

[0039] Specifically, the specific process of verifying and marking bad customers through threshold comparison is as follows: if the performance index of bad assets exceeds the set first threshold, the bad customer is marked as a high-risk customer; if the performance index of bad assets is between the first threshold and the second threshold, the bad customer is marked as a medium-risk customer; if the performance index of bad assets is lower than the second threshold, the bad customer is marked as a low-risk customer.

[0040] In this implementation scheme, through threshold classification, the system can accurately mark the risk level of customers. This precise classification can help managers quickly identify and handle customers of different risk levels and optimize resource allocation. High-risk customers are given priority, medium-risk customers are tracked regularly, and low-risk customers are under regular monitoring. This hierarchical management strategy improves overall management efficiency. Timely marking of high-risk customers can trigger an early warning mechanism, allowing managers to take quick measures, such as adjusting loan conditions or increasing guarantees. By tracking and monitoring medium- and low-risk customers, problems can be discovered and intervened in time before they become serious, thereby reducing potential losses. Focusing on high-risk customers allows resources and energy to be concentrated in areas with the greatest risk, thereby improving the effectiveness of risk control. Through effective risk classification and management, the same intensity of intervention is avoided for all customers, thereby reducing management costs. Threshold settings can be adjusted according to market changes and customer behavior to ensure the flexibility and adaptability of the system and maintain real-time response capabilities to non-performing asset risks.

[0041] Specifically, the specific process of sorting non-performing customers according to the non-performing asset performance index and generating priority disposal information is as follows: the marked high-risk customers, medium-risk customers and low-risk customers are stored in corresponding lists, and the non-performing customers are sorted in descending order according to the non-performing asset performance index.

[0042] In this implementation scheme, non-performing customers are divided into high-risk customers, medium-risk customers and low-risk customers according to their non-performing asset performance index. This mark is determined based on the comparison between the non-performing asset performance index and the set risk threshold. These marked customers are stored in corresponding lists, namely, a high-risk customer list, a medium-risk customer list and a low-risk customer list. In each list, customers are sorted according to their non-performing asset performance index. Specifically: High-risk customer list: Sort from large to small according to the non-performing asset performance index, and customers with high performance index are ranked first. Medium-risk customer list: Also sorted from large to small according to the non-performing asset performance index. Low-risk customer list: Sort from large to small according to the non-performing asset performance index. Sorting can use quick sorting to sort the customers in the list according to the index value. Sorting the marked customers is mainly to optimize resource allocation and processing priority. High-risk customers usually need to be processed first due to their high performance index because they may bring greater risks or losses to asset management. The sorting operation ensures that resources can be concentrated on the customer groups that need the most attention when processing non-performing assets. By prioritizing customers, resources can be effectively concentrated on high-risk customers, thereby improving the efficiency of risk management. Ensuring that high-risk customers are handled first helps reduce overall risk and improve the management of non-performing assets. It provides decision makers with clear customer priorities and facilitates the formulation of targeted management strategies and disposal measures.

[0043] See also Figure 2 , a full-cycle management method for non-performing assets, including the following steps: S1. Obtaining non-performing asset data of non-performing customers, evaluating the historical performance trend of non-performing assets through time series analysis, and generating a non-performing asset trend index; S2. Extracting the bad behavior characteristics of non-performing asset data, analyzing the characteristic differences of non-performing assets, determining the type of non-performing customers, and evaluating the abnormal risk index of non-performing assets; S3. Comprehensively analyzing the non-performing asset trend index and the non-performing asset abnormal risk index through the hierarchical analysis method, obtaining the non-performing asset performance index, verifying the non-performing customers through threshold comparison and marking them; S4. Unified storage and visualization of the non-performing asset data of marked non-performing customers, and continuously monitoring the dynamic performance of non-performing assets, sorting the non-performing customers according to the non-performing asset performance index, and generating priority disposal information.

[0044] In this implementation, step S1 obtains the non-performing asset data of non-performing customers and generates a trend index, and uses a time series analysis algorithm to process historical data. It can identify the change pattern and trend of non-performing assets, which helps to predict future performance. It provides a scientific trend measurement tool to help formulate future management strategies and decisions.

[0045] Step S2: Extract the behavioral characteristics of non-performing asset data and evaluate the abnormal risk, and use algorithms such as cluster analysis to analyze the extracted characteristics, identify the characteristic differences of non-performing assets, evaluate the abnormal risk of each type of customer, and generate the abnormal risk index of non-performing assets. Through behavioral characteristic analysis, we can understand the specific performance and risk factors of non-performing assets, so as to effectively classify customers. Step S3 accurately evaluates the overall performance of non-performing assets through comprehensive analysis, and classifies risks through threshold comparison, providing a comprehensive risk assessment tool to help more accurately mark and manage non-performing customers.

[0046] In summary, this application has at least the following effects: Through time series analysis, the historical performance trend of assets is evaluated and trend index is generated. The behavioral characteristics of non-performing assets are extracted and their differences are analyzed to evaluate abnormal risks. The performance index is generated by combining trend index and risk index using the hierarchical analysis method, and risk is marked through threshold comparison. The marked data is visualized, non-performing assets are dynamically monitored, and priority disposal information is generated based on the performance index. This method improves the systematicity, accuracy and real-time nature of non-performing asset management, and achieves more efficient risk identification and resource optimization allocation.

[0047] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0048] The present invention is described with reference to flowcharts and / or block diagrams of systems, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0049] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0050] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0051] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0052] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A full-cycle management system for non-performing assets, characterized in that: It includes the following modules: data acquisition module, asset analysis module, asset verification module, and asset management module; The asset data acquisition module is used to acquire the non-performing asset data of non-performing customers, evaluate the historical performance trend of non-performing assets through time series analysis, and generate a non-performing asset trend index; The asset data analysis module is used to extract the bad behavior characteristics of non-performing asset data, analyze the characteristic differences of non-performing assets, determine the type of non-performing customers, and evaluate the abnormal risk index of non-performing assets; The asset verification module is used to conduct a comprehensive analysis of the non-performing asset trend index and the non-performing asset abnormal risk index through the hierarchical analysis method, obtain the non-performing asset performance index, verify the non-performing customers through threshold comparison and mark them; The asset management module uniformly stores and visualizes the non-performing asset data of marked non-performing customers, continuously monitors the dynamic performance of non-performing assets, sorts non-performing customers according to the non-performing asset performance index, and generates priority disposal information.

2. The full-cycle management system for non-performing assets according to claim 1 is characterized by: The specific process of evaluating the historical performance trend of non-performing assets through time series analysis is as follows: Based on the non-performing asset data of bad customers, the historical trend and periodicity of the non-performing asset data are analyzed through the time series analysis algorithm, and the non-performing asset trend equation is constructed; Based on the NPL trend equation, the future performance of NPLs is predicted and a trend line is generated.

3. The full-cycle management system for non-performing assets according to claim 2 is characterized by: The specific process of generating the non-performing asset trend index is as follows: According to the non-performing asset trend equation and trend line, the slope of the trend line and the deviation of the trend line are analyzed, and the slope and deviation are combined to generate the non-performing asset trend index.

4. The full-cycle management system for non-performing assets according to claim 3 is characterized by: Extract the bad behavior characteristics of non-performing asset data, analyze the characteristic differences of non-performing assets, and determine the type of non-performing customers. The specific process is as follows: Extract behavioral features from the non-performing asset data, including the number of overdue payments, overdue amount, and repayment history; The extracted features are clustered according to the cluster analysis algorithm, and bad customers are classified according to the set customer types.

5. The full-cycle management system for non-performing assets according to claim 4 is characterized by: The specific process of evaluating the abnormal risk index of non-performing assets is as follows: Define risk assessment indicators based on customer type and behavioral characteristics, including overdue frequency threshold, overdue amount ratio threshold, and repayment default rate threshold; Based on the risk assessment indicators, the difference in abnormal risk indicators is calculated for each type of customer to generate the abnormal risk index of non-performing assets.

6. A full-cycle management system for non-performing assets according to claim 5, characterized in that: The specific process of comprehensively analyzing the non-performing asset trend index and the non-performing asset abnormal risk index to obtain the non-performing asset performance index is as follows: By using hierarchical analysis, weights are assigned to the non-performing asset trend index and the non-performing asset abnormal risk index, and the weight factors of the non-performing asset trend index and the non-performing asset abnormal risk index are obtained; The weight factor of the non-performing asset trend index and the weight factor of the non-performing asset abnormal risk index are comprehensively calculated with the non-performing asset trend index and the non-performing asset abnormal risk index to obtain the non-performing asset performance index.

7. The full-cycle management system for non-performing assets according to claim 6 is characterized by: The specific process of verifying and marking bad customers through threshold comparison is as follows: If the non-performing asset performance index exceeds the set first threshold, the non-performing customer will be marked as a high-risk customer; If the non-performing asset performance index is between the first threshold and the second threshold, the non-performing customer is marked as a medium-risk customer; If the performance index of the non-performing assets is lower than the second threshold, the non-performing customer is marked as a low-risk customer.

8. The full-cycle management system for non-performing assets according to claim 7 is characterized by: The specific process of sorting non-performing customers according to the non-performing asset performance index and generating priority disposal information is as follows: The marked high-risk customers, medium-risk customers and low-risk customers are stored in corresponding lists, and the non-performing customers are sorted from large to small according to the non-performing asset performance index.

9. A full-cycle management method for non-performing assets, applied to a full-cycle management system for non-performing assets as claimed in any one of claims 1 to 8, characterized in that: The following steps are involved: S1. Obtain the non-performing asset data of non-performing customers, evaluate the historical performance trend of non-performing assets through time series analysis, and generate the non-performing asset trend index; S2. Extract the bad behavior characteristics of non-performing asset data, analyze the characteristic differences of non-performing assets, determine the types of non-performing customers, and evaluate the abnormal risk index of non-performing assets; S3. Comprehensively analyze the NPL trend index and NPL abnormal risk index through analytic hierarchy process to obtain the NPL performance index, verify the NPL customers through threshold comparison and mark them; S4. The non-performing asset data of marked non-performing customers are uniformly stored and visualized, and the dynamic performance of non-performing assets is continuously monitored. The non-performing customers are sorted according to the non-performing asset performance index and priority disposal information is generated.

Images