Dynamic lease risk assessment method and system based on index data

Abstract

The invention provides a lease risk dynamic assessment method and system based on index data, and relates to the technical field of risk assessment, and the method comprises the steps: obtaining historical lease data and lease index data of a lease transaction, extracting lease features, and combining the lease index data to construct and form a feature set for training a lease risk assessment model; the method comprises the steps of constructing a target variable for model learning, constructing a lease risk assessment model to be integrated in a risk assessment engine, performing preliminary risk assessment by using a loan interest rate and a repayment amount of lease index data, and calling the lease risk assessment model to recalculate a risk score by using a tenant credit score and a historical transaction mode. Adjusting the final risk level of the lease transaction; and calculating a weighted comprehensive risk score according to the lease index data, and grading the lease transaction risk according to a comprehensive risk score interval. According to the invention, risk factors in the leasing process can be rapidly identified and responded, and the leasing risk can be analyzed and predicted in real time.

Description

Technical Field

[0001] The present invention relates to the technical field of risk assessment, and in particular to a method and system for dynamically assessing leasing risks based on indicator data. Background Art

[0002] In the leasing industry, traditional risk assessment methods mainly rely on manual analysis and static analysis based on historical data. The assessment process is limited by the experience and subjective judgment of analysts, lacks the ability to respond to dynamic changes in the leasing process, and cannot capture leasing risks in real time and comprehensively. The limitations of this static analysis method make leasing companies face the problem of being unable to identify potential risks such as default and vacancy in a timely manner, especially in situations where the market fluctuates frequently, making it difficult to provide effective risk warnings and decision support. Therefore, it is necessary to propose a dynamic leasing risk assessment method and system based on indicator data to improve the real-time and accuracy of risk assessment. Summary of the invention

[0003] In view of the above problems, the purpose of the present invention is to propose a dynamic assessment method and system for leasing risks based on indicator data, by collecting and analyzing multi-dimensional risk indicators, such as loan interest rates, repayment amounts and lessees' credit scores, combining real-time market data and historical transaction patterns, integrating multi-source data related to leasing, and using dynamic leasing risk assessment models to perform real-time analysis and prediction of leasing risks. Machine learning algorithms are used to perform comprehensive dynamic risk assessments on leasing transactions, which can quickly identify and respond to risk factors in the leasing process, such as default, vacancy, rent fluctuations, etc., provide dynamic risk warnings, and thus provide intelligent risk prediction and decision support.

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] Based on the above purpose, in a first aspect, the present invention provides a method for dynamically evaluating leasing risks based on indicator data, comprising the following steps:

[0006] Obtain historical leasing data and leasing index data of leasing transactions, where leasing index data includes loan interest rate, repayment amount, lessee credit score and historical transaction pattern, which are used to construct input variables of the evaluation model;

[0007] Extracting lease features from historical lease data and combining them with lease indicator data to construct a feature set for training a lease risk assessment model;

[0008] Use historical leasing data to divide training sets and test sets, use supervised learning to mark the risk levels in historical transaction data, and construct target variables for model learning;

[0009] Generate a leasing risk assessment model by training the training set data, and integrate the leasing risk assessment model into the assessment engine. At the same time, integrate the data input module, scenario analysis module and anomaly detection module with the model to form a complete risk assessment engine.

[0010] The loan interest rate and repayment amount of the leasing index data are used for preliminary risk assessment. The credit score and historical transaction pattern of the lessee in the leasing index data are further input. The risk assessment engine uses the leasing risk assessment model to recalculate the risk score based on the real-time market data input in real time, and adjusts the final risk level of the leasing transaction;

[0011] A weighted comprehensive risk score is calculated based on the leasing index data, and the leasing transaction risks are graded according to the comprehensive risk score range. A detailed assessment report containing the comprehensive risk score and final risk level is generated.

[0012] As a further solution of the present invention, the historical leasing data includes leasing contract data, payment record data, overdue record data, asset usage data, lessee credit score data and loan interest rate data.

[0013] As a further solution of the present invention, the extracted leasing characteristics include financial characteristics, credit characteristics, behavioral characteristics and leasing contract characteristics, the financial characteristics include loan interest rates and repayment amounts, the credit characteristics include lessee credit scores and historical default records, the behavioral characteristics include historical transaction patterns, and the historical transaction patterns include on-time repayment rates, early repayment rates and overdue repayment rates; the leasing contract characteristics include lease terms and leased asset types.

[0014] As a further solution of the present invention, constructing a feature set to train a rental risk assessment model includes the following steps:

[0015] Extracting lease characteristics from historical lease data and lease index data;

[0016] All extracted rental features are combined into the feature matrix X of the training dataset, where each row represents all the features of a rental transaction and each column represents a feature; the feature matrix X is expressed as:

[0017]

[0018] In the formula, IR represents the loan interest rate; RA represents the repayment amount; CS represents the lessee's credit score; OTR represents the on-time repayment rate; ERR represents the early repayment rate; LRR represents the overdue repayment rate; and LT represents the lease term.

[0019] As a further solution of the present invention, constructing a target variable for model learning includes the following steps:

[0020] Use random allocation to divide the training set and the test set, determine the risk level indicator for marking based on the lessee's credit score, overdue record, and loan interest rate in the leasing index data, and set the risk level based on the risk level indicator;

[0021] Mark the risk level of historical transaction data, generate classification labels, and convert the marked risk levels into label encoding formats recognized by the model;

[0022] A composite score is generated based on the weight of the leasing index data as the numerical target variable for model learning to quantitatively evaluate leasing risks;

[0023] y=ω 1 CS+ω 2 ·LRR+ω 3 ·IR

[0024] Where y represents the risk score of the target variable; ω 1 ,ω 2 ,ω 3 Represents the weight of each feature; CS represents the lessee’s credit score; LRR represents the overdue rate; IR represents the loan interest rate.

[0025] As a further solution of the present invention, when using the loan interest rate and the repayment amount to conduct a preliminary risk assessment, it includes:

[0026] Collect loan interest rates and repayment amounts in leasing transactions, and set preliminary risk assessment ranges for loan interest rates and repayment amounts;

[0027] The preliminary risk score is calculated based on the loan interest rate, loan principal, and repayment amount. The calculation formula for the preliminary risk score is:

[0028]

[0029] Where RS represents the preliminary risk score; ω 3 represents the weight of the loan interest rate, IR represents the loan interest rate; ω 4 Represents the weight of the repayment amount, RA represents the repayment amount; PC represents the loan principal.

[0030] As a further solution of the present invention, when the risk assessment engine calls the rental risk assessment model based on real-time input data to recalculate the risk score, the following steps are included:

[0031] Receive new leasing data input in real time, including loan interest rates, repayment amounts, and credit scores;

[0032] Call the risk assessment engine to recalculate the risk score using the trained rental risk assessment model;

[0033] Based on the recalculated score, the final risk level of the leasing transaction is adjusted in real time.

[0034] In a second aspect, the present invention provides a dynamic evaluation system for leasing risks based on indicator data, comprising:

[0035] Data acquisition module: used to collect and store historical leasing data and leasing index data of leasing transactions;

[0036] Feature extraction module, used to extract leasing features from the acquired historical leasing data, and to construct a feature set for training the leasing risk assessment model in combination with leasing indicator data;

[0037] Model training module, which is used to divide the training set and test set using historical leasing data, mark the risk level in the historical transaction data using supervised learning, and construct the target variable for model learning;

[0038] The assessment engine integration module is used to generate a leasing risk assessment model by training the training set data, and integrate the leasing risk assessment model into the assessment engine. At the same time, the data input module, scenario analysis module and anomaly detection module are integrated with the model to form a complete risk assessment engine;

[0039] The risk calculation module is used to conduct preliminary risk assessment using the loan interest rate and repayment amount of the leasing index data, and further input the lessee's credit score and historical transaction pattern in the leasing index data. The risk assessment engine uses the real-time market data input in real time to call the leasing risk assessment model to recalculate the risk score and adjust the final risk level of the leasing transaction;

[0040] The comprehensive risk assessment module is used to calculate the weighted comprehensive risk score based on the leasing indicator data, classify the leasing transaction risks according to the comprehensive risk score range, and generate a detailed assessment report including the comprehensive risk score and the final risk level.

[0041] In another aspect of the present invention, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, any one of the above-mentioned methods for dynamic assessment of leasing risks based on indicator data according to the present invention is executed.

[0042] In another aspect of the present invention, a computer-readable storage medium is provided, storing computer program instructions, which, when executed, implement any of the above-mentioned methods for dynamic assessment of leasing risks based on indicator data according to the present invention.

[0043] Compared with the prior art, the method and system for dynamic evaluation of leasing risk based on indicator data proposed in the present invention have the following beneficial effects:

[0044] 1. The present invention realizes comprehensive modeling of leasing risks by integrating various leasing indicator data, marking risk levels in combination with historical transaction data, improving the model's ability to identify and evaluate risk factors, making accurate risk predictions based on large-scale historical data, and dynamically updating the model to adapt to changing market environments and risk factors.

[0045] 2. The present invention can also receive and process the latest leasing index data in real time through an integrated data acquisition module and an evaluation engine, and dynamically adjust the final risk level of the leasing transaction based on the real-time calculation of the risk score. Compared with the traditional static risk assessment method, the present invention can instantly recalculate the comprehensive risk score based on the new input data to ensure the timeliness and reliability of the assessment results.

[0046] 3. The present invention also allows users to simulate the risk level of leasing transactions under different assumptions, so as to evaluate the impact of factors such as interest rate changes and fluctuations in the lessee's credit score on the overall risk. By simulating and analyzing the risks under different scenarios and analyzing historical transaction patterns, abnormal transaction behaviors or potential high-risk transactions can be identified, thereby providing risk warnings at an early stage and real-time monitoring of transaction data. Timely intervention can be made before risk characteristics emerge, thereby improving the ability to prevent abnormal leasing behaviors.

[0047] 4. The present invention can generate a comprehensive risk score through weighted calculation of leasing index data, comprehensively quantify the risk level of leasing transactions, and the risk grading mechanism can finely grade leasing transaction risks, automatically generate a detailed assessment report containing a comprehensive risk score and a final risk grade, thereby improving the ability to cope with complex risk scenarios, thereby gaining an advantage in the fierce market competition.

[0048] In summary, the dynamic assessment method and system of leasing risks based on indicator data of the present invention have the beneficial effects of high accuracy, real-time, multi-level decision support, intelligent risk identification and automated report generation, which can effectively improve the risk management level in leasing transactions and provide strong decision support for enterprises.

[0049] These and other aspects of the present application will be more concise and understandable in the following description of the embodiments. It should be understood that the above general description and the following detailed description are only exemplary and explanatory and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or related technologies, the following briefly introduces the drawings required for use in the exemplary embodiments or related technical descriptions. The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0051] Figure 1 The present invention is a flowchart of a method for dynamically evaluating leasing risks based on indicator data according to an embodiment of the present invention.

[0052] Figure 2 The present invention is a flowchart of constructing a feature set for training a leasing risk assessment model in a leasing risk dynamic assessment method based on indicator data in an embodiment of the present invention.

[0053] Figure 3 The present invention provides a flowchart for constructing target variables for model learning in a dynamic evaluation method for leasing risks based on indicator data in an embodiment of the present invention. DETAILED DESCRIPTION

[0054] Below, the present application is further described in conjunction with the accompanying drawings and specific implementation methods. It should be noted that, under the premise of no conflict, the various embodiments or technical features described below can be arbitrarily combined to form a new embodiment.

[0055] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the embodiments of the present invention are further described in detail below in combination with specific embodiments and with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0056] It should be noted that all expressions using "first" and "second" in the embodiments of the present invention are intended to distinguish two non-identical entities or non-identical parameters with the same name. It can be seen that "first" and "second" are only for the convenience of expression and should not be understood as limitations on the embodiments of the present invention. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, other steps or units inherent to a process, method, system, product or device that includes a series of steps or units.

[0057] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0058] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0059] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0060] In view of the problem that static analysis methods in the leasing industry are difficult to provide effective risk warnings and decision-making support in situations of frequent market fluctuations, the present invention proposes a dynamic assessment method and system for leasing risks based on indicator data. By collecting and analyzing multi-dimensional risk indicators, such as loan interest rates, repayment amounts, and lessees' credit scores, combining real-time market data and historical transaction patterns, integrating multi-source data related to leasing, using a dynamic leasing risk assessment model to perform real-time analysis and prediction of leasing risks, and using machine learning algorithms to perform comprehensive dynamic risk assessments on leasing transactions, the method is able to quickly identify and respond to risk factors in the leasing process, such as default, vacancy, rent fluctuations, etc., provide dynamic risk warnings, and thus provide intelligent risk prediction and decision support.

[0061] See also Figure 1 As shown, an embodiment of the present invention provides a method for dynamically evaluating lease risks based on indicator data, the method comprising the following steps:

[0062] Step S10: Obtain historical leasing data and leasing index data of leasing transactions, wherein the leasing index data includes loan interest rate, repayment amount, lessee credit score and historical transaction pattern, which are used to construct input variables of the evaluation model.

[0063] In this step, the historical lease data includes lease contract data, payment record data, overdue record data, asset usage data, lessee credit score data and loan interest rate data.

[0064] The present invention obtains historical data and leasing index data of leasing transactions through a data acquisition module. Historical leasing data includes past transaction information, such as leasing amount, lease term, repayment status, etc.; leasing index data involves loan interest rate, repayment amount, lessee's credit score, and historical transaction pattern, etc.

[0065] Assume that a leasing company holds leasing transaction records for the past three years, which include multiple transaction records with a loan interest rate of 5% and a monthly repayment amount of 2,000 yuan. At the same time, the company also collects the credit score data of the lessee (such as credit rating AA, BB, etc.) and the repayment performance of past transactions (such as whether it is overdue).

[0066] Step S20: extracting lease features from historical lease data, and combining them with lease indicator data to construct a feature set for training a lease risk assessment model.

[0067] In this step, feature engineering is performed on the collected historical leasing data to extract key features, such as loan interest rate, repayment amount, credit score, historical overdue times, etc., to construct the feature set required for the leasing risk assessment model. The extracted leasing features include financial features, credit features, behavioral features, and leasing contract features. The financial features include loan interest rate and repayment amount, the credit features include lessee credit score and historical default records, the behavioral features include historical transaction patterns, and the historical transaction patterns include on-time repayment rate, early repayment rate, and overdue repayment rate; the leasing contract features include the number of lease terms and the type of leased assets.

[0068] Among them, the interest rate (IR) is positively correlated with market risk, and the value of the interest rate is directly used as the input feature; the repayment amount (RA) reflects the lessee's ability to pay and burden level, and its historical average or current value is used as a feature; the lessee's credit score (CS) reflects the core indicator of its credit status. Its score value is directly used as an input feature; the default history (DH) indicates whether there is a historical default record, which is encoded as a categorical variable; among them:

[0069]

[0070] In this embodiment, the historical transaction pattern (HTM) reflects the lessee's past transaction habits, such as whether the repayment is on time, early repayment or often overdue. By collecting statistics on historical repayment records, the on-time repayment rate, early repayment rate and overdue repayment rate are extracted; the lease term (LT) indicates the term of the lease contract or the length of the lease period; the leased asset type (AT) reflects the type of leased property (such as vehicles, equipment, real estate, etc.), which is processed by one-hot encoding.

[0071] In this embodiment, see Figure 2 As shown, constructing a feature set to train a rental risk assessment model includes the following steps:

[0072] Step S201: extracting lease features from historical lease data and lease index data;

[0073] Step S202: combine all extracted leasing features into a feature matrix X of the training data set, where each row represents all features of a leasing transaction and each column represents a feature.

[0074] Among them, the feature matrix X is expressed as:

[0075]

[0076] In the formula, IR represents the loan interest rate; RA represents the repayment amount; CS represents the lessee's credit score; OTR represents the on-time repayment rate; ERR represents the early repayment rate; LRR represents the overdue repayment rate; and LT represents the lease term.

[0077] For example, assume that the historical data of a lease transaction is:

[0078] Loan interest rate: 5%;

[0079] Repayment amount: ￥10,000;

[0080] Lessee credit score: 720;

[0081] Number of overdue payments: 3 times;

[0082] Total number of issues: 12.

[0083] Then, through feature extraction:

[0084]

[0085] Step S30: Use historical leasing data to divide training sets and test sets, use supervised learning to mark the risk levels in historical transaction data, and construct target variables for model learning.

[0086] In this step, the historical leasing data is divided into a training set and a test set, and the historical transaction data is labeled according to the risk level (such as low, medium, and high risk) for training the supervised learning model.

[0087] See also Figure 3 As shown in Figure 1, constructing the target variable for model learning includes the following steps:

[0088] Step S301: Use random allocation to divide the training set and the test set, determine the risk level indicator for marking according to the lessee's credit score, overdue record, and loan interest rate in the leasing index data, and set the risk level based on the risk level indicator;

[0089] Step S302: Mark the risk level of historical transaction data, generate classification labels, and convert the marked risk levels into a label encoding format recognized by the model;

[0090] Step S303: Generate a composite score based on the weight of the leasing index data as the numerical target variable for model learning to quantitatively evaluate the leasing risk; wherein:

[0091] y=ω 1 CS+ω 2 ·LRR+ω 3 ·IR

[0092] Where y represents the risk score of the target variable; ω 1 ,ω 2 ,ω 3 Represents the weight of each feature; CS represents the lessee’s credit score; LRR represents the overdue rate; IR represents the loan interest rate.

[0093] In this embodiment, when setting thresholds to classify risks, the risks can be divided into:

[0094] Low risk: credit score > 700 and no overdue record;

[0095] Medium risk: credit score between 600 and 700 or with a small amount of delinquency;

[0096] High risk: credit score <600 or multiple overdue records.

[0097] Assume that a rental data sample has a credit score of 650 and has two overdue records. According to the rule method, the credit score is between 600 and 700 and there are a few overdue records, so the sample is marked as medium risk.

[0098] When constructing the target variable for model learning, assuming there is a set of sample data with a credit score of 680, an overdue rate of 0.2 (20%), and a loan interest rate of 5%, the risk score can be constructed according to the following weights:

[0099] Set weight ω 1 =0.5,ω 2 =0.3,ω 3 =0.2.

[0100] The target risk score y=0.5·680+0.3·0.2+0.2·5=342.06, and the leasing transaction is classified as medium risk.

[0101] The construction of the target variable in the present invention helps the model learn how to predict the level of leasing risk based on the input features, so that the model can accurately judge the potential risks of new leasing transactions.

[0102] Step S40: Generate a lease risk assessment model by training the training set data, and integrate the lease risk assessment model into the assessment engine. At the same time, integrate the data input module, scenario analysis module and anomaly detection module with the model to form a complete risk assessment engine.

[0103] In this step, the risk assessment model is trained using the training set, the model is optimized, the trained model is integrated into the risk assessment engine, and the data input module, scenario analysis module, and anomaly detection module are integrated with the assessment engine. By integrating a complete risk assessment engine, it is possible to receive new data inputs in real time and dynamically assess risks, while providing multi-level analysis support.

[0104] Step S50: Perform a preliminary risk assessment using the loan interest rate and repayment amount of the leasing index data, further input the lessee's credit score and historical transaction pattern in the leasing index data, and the risk assessment engine calls the leasing risk assessment model to recalculate the risk score based on the real-time market data input in real time, and adjust the final risk level of the leasing transaction.

[0105] In this step, the loan interest rate and repayment amount are first used for preliminary risk assessment, and then the lessee's credit score and historical transaction patterns are further input to conduct a comprehensive risk assessment. The assessment engine can call the risk assessment model based on real-time input data to recalculate the risk score and dynamically adjust the final risk level of the leasing transaction.

[0106] Among them, when using loan interest rates and repayment amounts for preliminary risk assessment, it includes:

[0107] Collect loan interest rates and repayment amounts in leasing transactions, and set preliminary risk assessment ranges for loan interest rates and repayment amounts;

[0108] The preliminary risk score is calculated based on the loan interest rate, loan principal, and repayment amount. The calculation formula for the preliminary risk score is:

[0109]

[0110] Where RS represents the preliminary risk score; ω 3 represents the weight of the loan interest rate, IR represents the loan interest rate; ω 4 Represents the weight of the repayment amount, RA represents the repayment amount; PC represents the loan principal.

[0111] Among them, when the risk assessment engine calls the lease risk assessment model based on real-time input data to recalculate the risk score, the following steps are included:

[0112] Receive new leasing data input in real time, including loan interest rates, repayment amounts, and credit scores;

[0113] Call the risk assessment engine to recalculate the risk score using the trained rental risk assessment model;

[0114] Based on the recalculated score, the final risk level of the leasing transaction is adjusted in real time.

[0115] For example, the initial risk assessment is: setting the loan interest rate between 3% and 7% as low risk, between 7% and 10% as medium risk, and greater than 10% as high risk. The ratio of the repayment amount to the loan principal exceeds 20% for high risk. Comprehensive risk assessment: Combine the credit score (such as credit rating AA for low risk, BB for medium risk, CC for high risk) and historical overdue records (such as multiple overdue for high risk) to recalculate the risk score of the leasing transaction. By gradually adding risk assessment factors, the risk score can be dynamically adjusted to improve the accuracy and real-time nature of risk assessment.

[0116] In some embodiments, when predicting the rental risk level, the formula for each period of rent under equal principal and interest repayment is:

[0117] Where P is the principal, i is the interest rate per period, and n is the total number of periods.

[0118] Step S60: Calculate a weighted comprehensive risk score based on the leasing index data, classify the leasing transaction risks according to the comprehensive risk score range, and generate a detailed assessment report including the comprehensive risk score and the final risk level.

[0119] In this step, the leasing index data is weighted and calculated to generate a comprehensive risk score, and the risk level of the leasing transaction is divided according to the score results. An assessment report containing the comprehensive risk score and risk level is automatically generated, and corresponding risk management suggestions are provided.

[0120] For example, weighted scoring calculation: set the loan interest rate weight to 0.4, the repayment amount weight to 0.3, the credit score weight to 0.2, and the historical transaction pattern weight to 0.1 to calculate the comprehensive risk score. Generate an assessment report: scores of 85 to 100 are low risk, 60 to 84 are medium risk, and scores below 60 are high risk. The report details the scoring of each indicator and risk recommendations. Through automated report generation, visual risk assessment results can be quickly provided to help leasing companies take targeted risk response measures.

[0121] The dynamic evaluation method of leasing risk based on indicator data of the present invention realizes comprehensive modeling of leasing risk by integrating multiple leasing indicator data, annotates risk levels in combination with historical transaction data, improves the model's ability to identify and evaluate risk factors, makes accurate risk predictions based on large-scale historical data, and dynamically updates the model to adapt to changing market environments and risk factors. The present invention can also receive and process the latest leasing indicator data in real time through an integrated data acquisition module and evaluation engine, and dynamically adjust the final risk level of the leasing transaction based on the real-time calculation of risk scores; compared with traditional static risk evaluation methods, the present invention can instantly recalculate the comprehensive risk score based on new input data to ensure the timeliness and reliability of the evaluation results.

[0122] It should be noted that the above figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0123] It should be understood that, although described in a certain order, these steps are not necessarily performed in sequence in the above order. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, a part of the steps of the present embodiment may include a plurality of steps or a plurality of stages, and these steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a part of the steps or stages in other steps or other steps.

[0124] In a second aspect of the embodiment of the present invention, the present invention further provides a dynamic evaluation system for leasing risks based on indicator data, comprising:

[0125] Data acquisition module: used to collect and store historical leasing data and leasing index data of leasing transactions;

[0126] Feature extraction module, used to extract leasing features from the acquired historical leasing data, and to construct a feature set for training the leasing risk assessment model in combination with leasing indicator data;

[0127] Model training module, which is used to divide the training set and test set using historical leasing data, mark the risk level in the historical transaction data using supervised learning, and construct the target variable for model learning;

[0128] The assessment engine integration module is used to generate a leasing risk assessment model by training the training set data, and integrate the leasing risk assessment model into the assessment engine. At the same time, the data input module, scenario analysis module and anomaly detection module are integrated with the model to form a complete risk assessment engine;

[0129] The risk calculation module is used to conduct preliminary risk assessment using the loan interest rate and repayment amount of the leasing index data, and further input the lessee's credit score and historical transaction pattern in the leasing index data. The risk assessment engine uses the real-time market data input in real time to call the leasing risk assessment model to recalculate the risk score and adjust the final risk level of the leasing transaction;

[0130] The comprehensive risk assessment module is used to calculate the weighted comprehensive risk score based on the leasing indicator data, classify the leasing transaction risks according to the comprehensive risk score range, and generate a detailed assessment report including the comprehensive risk score and the final risk level.

[0131] Through the above detailed steps and examples, the dynamic evaluation system for leasing risk based on indicator data of the present invention is used to execute the steps of the dynamic evaluation method for leasing risk based on indicator data in the above embodiment, which will not be repeated here. The dynamic evaluation system for leasing risk based on indicator data of the present invention allows users to simulate the risk level of leasing transactions under different assumptions, thereby evaluating the impact of factors such as interest rate changes and fluctuations in the credit score of lessees on the overall risk. By simulating and analyzing the risks under different scenarios and analyzing the historical transaction patterns, abnormal transaction behaviors or potential high-risk transactions can be identified, thereby carrying out risk warnings at an early stage, monitoring transaction data in real time, and timely intervening before risk characteristics appear, thereby improving the ability to prevent abnormal leasing behaviors. The present invention can generate a comprehensive risk score and comprehensively quantify the risk level of leasing transactions through weighted calculation of leasing indicator data. The risk grading mechanism can finely grade the risks of leasing transactions, and automatically generate a detailed evaluation report containing a comprehensive risk score and a final risk grade, thereby improving the ability to deal with complex risk scenarios, thereby gaining an advantage in the fierce market competition.

[0132] In summary, the dynamic assessment method and system of leasing risks based on indicator data of the present invention have the beneficial effects of high accuracy, real-time, multi-level decision support, intelligent risk identification and automated report generation, which can effectively improve the risk management level in leasing transactions and provide strong decision support for enterprises.

[0133] According to a third aspect of an embodiment of the present invention, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the method of any one of the above embodiments is implemented.

[0134] The computer device includes a processor and a memory, and may also include an input system and an output system. The processor, memory, input system and output system may be connected via a bus or other means, and the input system may receive input digital or character information, and generate signal input related to the migration of the dynamic assessment of leasing risk based on indicator data. The output system may include display devices such as display screens.

[0135] As a non-volatile computer-readable storage medium, the memory can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the program instructions / modules corresponding to the dynamic evaluation method for leasing risk based on indicator data in the embodiment of the present application. The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the use of the dynamic evaluation method for leasing risk based on indicator data, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the local module via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0136] In some embodiments, the processor may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor is generally used to control the overall operation of the computer device. In this embodiment, the processor is used to run the program code stored in the memory or process data. The processors of the multiple computer devices of the computer device of this embodiment execute various functional applications and data processing of the server by running non-volatile software programs, instructions and modules stored in the memory, that is, implementing the steps of the dynamic evaluation method of leasing risk based on indicator data of the above method embodiment.

[0137] It should be understood that, unless they conflict with each other, all the embodiments, features and advantages described above for the dynamic assessment method of rental risk based on indicator data according to the present invention are equally applicable to the dynamic assessment and storage medium of rental risk based on indicator data according to the present invention.

[0138] It will also be appreciated by those skilled in the art that various exemplary logic blocks, modules, circuits and algorithm steps described in conjunction with the disclosure herein can be implemented as electronic hardware, computer software or a combination of the two. In order to clearly illustrate this interchangeability of hardware and software, a general description has been given to the functions of various schematic components, blocks, modules, circuits and steps. Whether this function is implemented as software or hardware depends on specific applications and the design constraints imposed on the entire system. Those skilled in the art can implement the function in various ways for each specific application, but this implementation decision should not be interpreted as causing a departure from the disclosed scope of the embodiments of the present invention.

[0139] Finally, it should be noted that the computer-readable storage medium (e.g., memory) herein may be a volatile memory or a non-volatile memory, or may include both a volatile memory and a non-volatile memory. As an example and not by way of limitation, a non-volatile memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. A volatile memory may include a random access memory (RAM), which may act as an external cache memory. As an example and not by way of limitation, RAM may be obtained in a variety of forms, such as synchronous RAM (DRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The storage devices of the disclosed aspects are intended to include, but are not limited to, these and other suitable types of memory.

[0140] The various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure herein may be implemented or executed using the following components designed to perform the functions herein: a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination of these components. A general purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP, and / or any other such configuration.

[0141] The above is an exemplary embodiment disclosed by the present invention, but it should be noted that, without departing from the scope disclosed by the embodiment of the present invention, various changes and modifications may be made. The functions, steps and / or actions of the method according to the disclosed embodiment described herein do not need to be performed in any particular order. In addition, although the elements disclosed by the embodiment of the present invention may be described or required in individual form, it may also be understood as multiple unless explicitly limited to the singular.

[0142] It should be understood that, as used herein, the singular form "a" or "an" is intended to include the plural form as well, unless the context clearly supports an exception. It should also be understood that, as used herein, "and / or" refers to any and all possible combinations of one or more of the items listed in association. The serial numbers of the embodiments disclosed in the above embodiments of the present invention are for description only and do not represent the advantages and disadvantages of the embodiments.

[0143] A person skilled in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the disclosure of the embodiments of the present invention is limited to these examples; under the idea of ​​the embodiments of the present invention, the technical features in the above embodiments or different embodiments can also be combined, and there are many other changes in different aspects of the above embodiments of the present invention, which are not provided in detail for the sake of simplicity. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present invention should be included in the protection scope of the embodiments of the present invention.

Claims

1. A dynamic evaluation method for leasing risk based on indicator data, characterized in that: The method comprises the following steps: Obtain historical leasing data and leasing index data of leasing transactions, where leasing index data includes loan interest rate, repayment amount, lessee credit score and historical transaction pattern, which are used to construct input variables of the evaluation model; Extracting leasing features from historical leasing data and combining them with leasing index data to construct a feature set for training leasing risk assessment models; Use historical leasing data to divide training sets and test sets, use supervised learning to mark the risk levels in historical transaction data, and construct target variables for model learning; Generate a leasing risk assessment model by training the training set data, and integrate the leasing risk assessment model into the assessment engine. At the same time, integrate the data input module, scenario analysis module and anomaly detection module with the model to form a complete risk assessment engine. The loan interest rate and repayment amount of the leasing index data are used for preliminary risk assessment. The credit score and historical transaction pattern of the lessee in the leasing index data are further input. The risk assessment engine uses the leasing risk assessment model to recalculate the risk score based on the real-time market data input in real time, and adjusts the final risk level of the leasing transaction; A weighted comprehensive risk score is calculated based on the leasing index data, and the leasing transaction risks are graded according to the comprehensive risk score range. A detailed assessment report containing the comprehensive risk score and final risk level is generated.

2. The dynamic evaluation method for leasing risk based on indicator data according to claim 1 is characterized in that: The historical lease data includes lease contract data, payment record data, overdue record data, asset usage data, lessee credit score data and loan interest rate data.

3. The dynamic evaluation method for leasing risk based on indicator data according to claim 2 is characterized in that: The extracted leasing characteristics include financial characteristics, credit characteristics, behavioral characteristics and leasing contract characteristics. The financial characteristics include loan interest rate and repayment amount, the credit characteristics include lessee credit score and historical default record, the behavioral characteristics include historical transaction patterns, and the historical transaction patterns include on-time repayment rate, early repayment rate and overdue repayment rate; the leasing contract characteristics include lease term and leased asset type.

4. The dynamic evaluation method for leasing risk based on indicator data according to claim 3 is characterized in that: Constructing the feature set to train the rental risk assessment model includes the following steps: Extracting lease characteristics from historical lease data and lease index data; All extracted rental features are combined into the feature matrix X of the training dataset, where each row represents all the features of a rental transaction and each column represents a feature; the feature matrix X is expressed as: In the formula, IR represents the loan interest rate; RA represents the repayment amount; CS represents the lessee's credit score; OTR represents the on-time repayment rate; ERR represents the early repayment rate; LRR represents the overdue repayment rate; and LT represents the lease term.

5. The dynamic evaluation method for leasing risk based on indicator data according to claim 4 is characterized in that: Constructing the target variable for model learning includes the following steps: Use random allocation to divide the training set and the test set, determine the risk level indicator for marking based on the lessee's credit score, overdue record, and loan interest rate in the leasing index data, and set the risk level based on the risk level indicator; Mark the risk level of historical transaction data, generate classification labels, and convert the marked risk levels into label encoding formats recognized by the model; A composite score is generated according to the weight of the leasing index data as the numerical target variable for model learning to quantitatively evaluate leasing risks.

6. The dynamic evaluation method for leasing risk based on indicator data according to claim 5 is characterized in that: The calculation formula for constructing the target variable for model learning is: y=ω1·CS+ω2·LRR+ω3·IR Where y represents the risk score of the target variable; ω1, ω2, and ω3 represent the weights of each feature; CS represents the lessee’s credit score; LRR represents the overdue rate; and IR represents the loan interest rate.

7. The dynamic evaluation method for leasing risk based on indicator data according to claim 6 is characterized in that: When conducting an initial risk assessment using loan interest rates and repayment amounts, include: Collect loan interest rates and repayment amounts in leasing transactions, and set preliminary risk assessment ranges for loan interest rates and repayment amounts; The preliminary risk score is calculated based on the loan interest rate, loan principal, and repayment amount. The calculation formula for the preliminary risk score is: Where RS represents the preliminary risk score; ω3 represents the weight of the loan interest rate, IR represents the loan interest rate; ω4 represents the weight of the repayment amount, RA represents the repayment amount; PC represents the loan principal.

8. The dynamic evaluation method for leasing risk based on indicator data according to claim 1 is characterized in that: When the risk assessment engine calls the lease risk assessment model to recalculate the risk score based on real-time input data, the following steps are included: Receive new leasing data input in real time, including loan interest rates, repayment amounts, and credit scores; Call the risk assessment engine to recalculate the risk score using the trained rental risk assessment model; Based on the recalculated score, the final risk level of the leasing transaction is adjusted in real time.

9. A dynamic evaluation system for leasing risks based on indicator data, characterized in that: The system is used to execute the dynamic evaluation method of leasing risk based on indicator data according to any one of claims 1 to 8, comprising: Data acquisition module: used to collect and store historical leasing data and leasing index data of leasing transactions; Feature extraction module, used to extract leasing features from the acquired historical leasing data, and to construct a feature set for training the leasing risk assessment model in combination with leasing indicator data; Model training module, which is used to divide the training set and test set using historical leasing data, mark the risk level in the historical transaction data using supervised learning, and construct the target variable for model learning; The assessment engine integration module is used to generate a leasing risk assessment model by training the training set data, and integrate the leasing risk assessment model into the assessment engine. At the same time, the data input module, scenario analysis module and anomaly detection module are integrated with the model to form a complete risk assessment engine; The risk calculation module is used to conduct preliminary risk assessment using the loan interest rate and repayment amount of the leasing index data, and further input the lessee's credit score and historical transaction pattern in the leasing index data. The risk assessment engine uses the real-time market data input in real time to call the leasing risk assessment model to recalculate the risk score and adjust the final risk level of the leasing transaction; The comprehensive risk assessment module is used to calculate the weighted comprehensive risk score based on the leasing indicator data, classify the leasing transaction risks according to the comprehensive risk score range, and generate a detailed assessment report including the comprehensive risk score and the final risk level.

Images