Reliable analysis and prediction methods for financial data

Abstract

The present invention provides a reliable analysis and prediction method for financial data, and relates to the technical field of data processing. The method comprises obtaining basic lending data of lending users, and performing initial lending risk analysis to form initial risk information; collecting lending process data of different lending users according to the initial risk information, and performing lending process reputation analysis according to the lending process data to form lending process risk information; performing lending risk prediction analysis according to the lending process risk information to form lending risk warning information. The method uses big data to perform reasonable and reliable data analysis to accurately predict and warn lending transactions, thereby ensuring the stability and security of lending transaction activities.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a reliable analysis and prediction method for financial data. Background Art

[0002] Lending is the most important mode of operation of financial activities. Through lending, financial products can be sold and used, and the value of the consumption of borrowed financial products can be obtained. With the development of society and the progress of science, the methods of financial activities have gradually diversified and become information-based. Especially for the data informationization of financial activities, lending activities can be accumulated through data retention, which makes it easier for people to have a deeper understanding of the laws of financial activities through the accumulated data.

[0003] At present, most of the analysis of lending activities is still based on a simple analysis of the lending transaction capabilities of the subject before the lending transaction. It is unable to fully control the risks of lending financial products and implement risk measures in real time, resulting in a high level of uncertainty in lending transactions, adding a risk to financial activities.

[0004] Therefore, designing a reliable analysis and prediction method for financial data, using big data to conduct reasonable and reliable data analysis to accurately predict and warn of lending transactions, and ensuring the stability and security of lending transactions is an urgent problem to be solved. Summary of the invention

[0005] The purpose of the present invention is to provide a reliable analysis and prediction method for financial data, and to analyze the initial risk of loan transactions by obtaining the basic loan information of the loan users, so as to fully grasp the loan risk situation in the early stage of the loan transaction, and provide important and reliable reference data for the loan transaction. At the same time, important loan process data is collected and reasonably analyzed during the loan process, and the real-time situation of the loan transaction is reasonably and accurately predicted on the basis of fully grasping the change law of the loan process data, so as to make a reasonable assessment of the risk of the loan transaction, and provide early warning for the possible loan transaction risks, effectively ensure the stable implementation of the loan transaction, and effectively improve the security of the loan transaction activities.

[0006] In a first aspect, the present invention provides a reliable analysis and prediction method for financial data, including obtaining basic lending data of lending users, and performing initial lending risk analysis to form initial risk information; based on the initial risk information, collecting lending process data of different lending users, and performing lending process reputation analysis based on the lending process data to form lending process risk information; performing lending risk prediction analysis based on the lending process risk information to form lending risk warning information.

[0007] In the present invention, the method analyzes the initial risk of the loan transaction by acquiring the basic loan information of the loan user, thereby fully grasping the loan risk situation in the initial stage of the loan transaction, and providing important and reliable reference data for the loan transaction. At the same time, important loan process data is collected and reasonably analyzed during the loan process, and the real-time situation of the loan transaction is reasonably and accurately predicted on the basis of fully grasping the change law of the loan process data, making a reasonable assessment of the risk of the loan transaction, and providing early warning for possible loan transaction risks, effectively ensuring the stable implementation of the loan transaction, and effectively improving the security of loan transaction activities.

[0008] As a possible implementation method, basic lending data of borrowers is obtained, and initial lending risk analysis is performed to form initial risk information, including: obtaining the lending interest rate I of the user's lending target for different borrowers n , n represents the serial number of different lending users; for different lending users, the lending method data of the user's lending target is obtained, and the equivalent value analysis is performed to form the equivalent ratio of the lending method; for different lending users, the net lending ratio of the user's lending target is obtained; according to the lending interest rate, the equivalent value of the lending method and the net lending ratio, the initial lending correlation analysis is performed to determine the initial lending risk value of the lending user for the user's lending target.

[0009] In the present invention, the initial risk analysis of the loan transaction is mainly used to determine whether the loan object has the ability to bear the subject of the loan transaction. The present application conducts reliable analysis and evaluation of this ability from three aspects: loan interest rate, loan method and net loan ratio. For the loan interest rate, the higher the loan interest rate, the longer the loan time of the loan subject, and the longer the loan time, the higher the loan risk of the loan subject to complete the transaction. Therefore, high interest rates are an important means to ensure the smooth completion of loan transactions. For the loan method, when the loan object obtains the loan subject, it is often necessary to use a value equivalent to the loan subject for loan. At this time, the basis for financial activities is generated. These loan equivalents can be real or intangible, such as equivalent items, intellectual property rights, reputation, etc., and the loan methods corresponding to different types of equivalents are different. These methods will also affect the stability of the loan transaction and generate different degrees of potential loan risks. Therefore, it is necessary to analyze and evaluate the risks based on the loan method. For the net loan ratio, it is mainly to determine the ability of the loan object to bear the loan subject when conducting a loan transaction. After all, the value of the loan subject is a liability at the financial level. Therefore, relative to the net assets of the borrower, the value of the loan subject relative to the net assets can determine the borrower's economic ability to bear the load, and to a certain extent reflects the risk of the borrower in carrying the loan subject. Of course, the combined effect of these three aspects forms an overall measure of the size of the transaction risk in the early stage of the loan transaction.

[0010] As a possible implementation method, for different borrowing users, the borrowing method data of the user's borrowing target is obtained, and an equivalent value analysis is performed to form an equivalent ratio of the borrowing method, including: determining the conversion borrowing amount M of the borrowing user's user borrowing target n ; Determine the equivalent value of different lending methods corresponding to the user's lending target i represents the number of different loan methods; according to the equivalent value and conversion loan amount M n , determine the borrowing method of the borrower in:

[0011] In the present invention, the magnitude of the risk of a loan transaction due to a loan method is mainly reflected in the difference between the equivalent value formed by different loan methods and the value of the loan subject. After all, the difference between the loan equivalent value provided by the loan subject and the value of the loan subject is too large, which is a non-equivalent loan transaction in a sense, and thus makes the loan transaction have a greater risk of value imbalance. Here, it should be noted that the equivalent objects provided by the loan subject corresponding to different loan methods are different. For example, the loan with credit guarantee is mainly based on the historical loan and trustworthy behavior of the loan subject to assess the repayment ability as the equivalent object, and the mortgage loan is mainly based on the equivalent collateral provided by the loan subject as the equivalent object, etc. Of course, for a loan transaction, it can be a combination of multiple loan methods. Therefore, when conducting risk assessment analysis of the loan method, it is necessary to consider all the loan methods included in the loan transaction, and take the sum of the equivalent amounts provided by these loan methods as the object of risk assessment.

[0012] As a possible implementation method, for different borrowers, the net borrowing ratio of the borrower's borrowing target is obtained, including: determining the total assets P of the borrower n and total liabilities L n , determine the net assets A of the borrower n , where A n =P n -L n ; According to the conversion loan amount M of the borrower's user loan target n and the net assets of the borrower A n , determine the net lending ratio of the borrower's user lending target in:

[0013] In the present invention, the net loan ratio is mainly used to determine the ratio of the value of the loan subject to the current net assets of the loan object. The size of the ratio highlights whether the loan object has sufficient ability to ensure the completion of the loan transaction at present. This is an important reference data for the initial loan transaction risk analysis.

[0014] As a possible implementation method, an initial lending correlation analysis is performed based on the lending interest rate, lending method and net lending ratio to determine the initial lending risk value of the lending user for the user's lending target, including: n , loan and borrowing method equal ratio and net borrowing ratio Determine the initial lending risk value C of the lending user's lending target n ,in: α 1 , α 2 and α 3 are the corresponding correlation factors, and α 1 +α 2 +α 3 =1.

[0015] In the present invention, the lending rate, lending method and net lending ratio are each independently characterized in different aspects of lending transactions. The overall impact of the three aspects on the risk of lending transactions is obtained, and the risk of the current lending transaction is reliably and reasonably determined. The correlation factor can be set according to the actual situation, and the impact of these three aspects on the risk of lending transactions can also be determined through big data.

[0016] As a possible implementation method, according to the initial risk information, the lending process data of different lending users are collected, and the lending process reputation analysis is performed based on the lending process data to form the lending process risk information, including: collecting the repayment information of the user lending subject of the lending user, and performing periodic statistics to form the repayment cycle data; collecting the repayment information of all lending subjects of the lending user, and performing importance analysis based on periodic statistics to form repayment importance cycle data; determining the lending additional collection interval according to the initial risk information, and obtaining the total lending amount information of the lending user according to the lending additional collection interval, and performing periodic lending additional rate analysis to form lending additional rate cycle data; aggregating the lending user's repayment cycle data, repayment importance cycle data and lending additional rate cycle data to form the lending process risk information of the user lending subject of the lending user.

[0017] In the present invention, the analysis of initial lending risk is, on the one hand, to conduct reliable and reasonable data analysis for the risk size existing in the initial stage of lending transactions, so as to provide guarantee for real-time, safe and stable transactions in the initial stage of lending transactions. On the other hand, the initial lending risk also reflects the initial lending capacity of the lending object, which is an important basic data for the subsequent analysis of the lending object in the lending process to continuously and reliably analyze the lending capacity of the lending object, and ensure the rationality and accuracy of the process data analysis. The analysis of the lending process data is mainly to evaluate and predict whether the conditions affecting the stability and security of the lending transaction have changed during the lending process, and then determine whether it has affected the risk size of the lending transaction, so as to make reasonable early warning predictions. The most important factors affecting the change of risk size in this process are mainly three aspects. One aspect is to monitor the punctuality of the lending user in completing the lending transaction, which is shown here by analyzing the repayment time. After all, the earlier the repayment, the higher the credit of the lending user in completing the lending transaction, the more sufficient the capital it has to ensure the completion of the lending transaction, and the lower the risk of the lending transaction. Here, the loan repayment information content can be broadly analyzed, mainly based on the loan repayment time point, including the early repayment time for the over-repayment time point, that is, the total loan repayment limit time is shortened according to the size of the early repayment, and the relatively delayed under-repayment time is increased. The second aspect is to consider the repayment of the loan repayment target among all the loan repayment targets of the loan repayment user. The consideration in this aspect is mainly to determine the impact of other loan repayment target transactions on the target loan transaction. After all, the total capital of the loan user is limited, and multiple loan transactions require reasonable capital allocation. Here, by analyzing the order of repayment of the target loan transaction in all the loan transactions of the loan user and the size of the loan repayment capital, the loan user's consideration of the importance of all its loan transactions can be determined, and then the risk of the target loan transaction being considered for normal completion in the case of a shortage of capital for the loan user can be analyzed. The third aspect is the analysis of the change in the total debt of the loan user, that is, the loan amount. After all, the change in the total debt of the loan user will affect the loan user's consideration of the loan repayment behavior of the loan transaction including the target loan transaction, and then have a certain risk impact on the completion of the target loan transaction. It is understandable that users with different initial lending risks have certain differences in risk analysis during the lending process. After all, for users with higher initial risks, it is necessary to conduct more rigorous analysis and monitoring during the lending process, while for users with lower initial risks, it is safer to conduct analysis and monitoring during the lending process. This can ensure reasonable analysis and monitoring of the lending process of different borrowers and provide accurate predictive analysis. On the other hand, it can fully realize the analysis and monitoring of the lending process of all borrowers while fully saving monitoring and analysis resources.

[0018] As a possible implementation method, the repayment information of the user's loan subject is collected, and periodic statistics are performed to form the repayment cycle data, including: obtaining the actual repayment date of the user's loan subject in each repayment cycle of the previous k repayment cycles including the current repayment cycle; And the corresponding maximum loan repayment date According to the actual repayment date corresponding to each loan repayment cycle and maximum repayment date Determine the on-time repayment rate for each loan repayment cycle in, The on-time repayment rate corresponding to each loan repayment cycle Arrange them in chronological order to form loan repayment cycle data.

[0019] In the present invention, the analysis and monitoring of process quantity is considered, so the loan repayment cycle data is based on time statistics. The loan repayment on-time rate is characterized by the ratio of the total loan repayment time limit to the actual loan repayment time. For extracting more or less repayments or compressing or increasing the loan repayment time limit while the actual loan repayment time remains unchanged, the data can be reasonably expressed, which is convenient for the general collection of information about the loan repayment cycle to conduct accurate and reasonable loan repayment process data analysis and monitoring.

[0020] As a possible implementation method, the repayment information of all loan targets of the borrowing user is collected, and the importance analysis based on cycle statistics is performed to form the repayment importance cycle data, including: in the previous k repayment cycles including the current repayment cycle, the repayment order of the borrowing user's user loan target among all loan targets in each repayment cycle is determined, and the repayment order rate of the user's loan target is determined. in, Indicates the repayment order value of the user's loan subject in the loan repayment cycle numbered k. Indicates the maximum repayment order value of the repayment cycle numbered k; determines the proportion of the repayment amount of the user's loan target in the previous k repayment cycles including the current repayment cycle in, Indicates the repayment amount of the user's loan subject in the loan repayment cycle numbered k. Indicates the total amount of loan repayments in the loan repayment cycle numbered k; according to the loan repayment sequence rate corresponding to each loan repayment cycle and loan repayment ratio Determine the importance of loan repayment for the corresponding loan repayment period in, β 1 , β 2 are the corresponding importance factors respectively; the importance of loan repayment corresponding to each loan repayment period is Arrange them in chronological order to form loan repayment importance cycle data.

[0021] In the present invention, the importance of loan repayment is determined by obtaining the repayment sequence information of the target loan subject and the proportion of the loan repayment amount to the total loan repayment amount. After all, these two aspects simultaneously characterize the situation in which the target loan subject is affected by other loan subjects and thus causes changes in risk size.

[0022] As a possible implementation method, according to the initial risk information, the additional loan collection interval is determined, and the total loan amount information of the borrower is obtained according to the additional loan collection interval, and a cycle-based additional loan rate analysis is performed to form the additional loan rate cycle data, including: setting a risk segmentation function, obtaining the initial loan risk value C of the borrower n , and according to the risk segmentation function and the initial lending risk value C n , determine the additional lending collection interval for borrowers; take the additional lending collection interval as the data collection period, take the current time point as the interval end time of the current additional lending collection interval, and collect the change amount of borrowers' lending within the previous e additional lending collection intervals and periodic net assets According to the change amount of each additional loan collection interval and periodic net assets Determine the loan addition rate corresponding to the loan addition collection interval in, The loan additional rate corresponding to each loan additional collection interval Arrange them in chronological order to form the loan addition rate cycle data.

[0023] In the present invention, it should be noted that the risk segmentation function mainly considers that borrowers with different initial risk sizes need to conduct targeted analysis of their own debt changes. After all, borrowers with higher initial risks often have relatively frequent activities in loan transactions in order to ensure the smooth operation of their own capital, so they need to pay close attention to analysis. On the contrary, borrowers with lower initial risks have relatively fewer loan transactions due to their stable capital activities. Therefore, the main function of the risk segmentation function is to determine the frequency of debt data collection based on the initial loan risk size of the borrower. The segmented output value given by the risk segmentation function can be determined according to actual needs, or it can be determined by big data analysis of the debt of the borrower. By determining a reasonable and targeted data collection interval to collect the debt change data of the borrower, the accuracy of the real-time analysis and monitoring data can be guaranteed, and then the loan risk can be accurately and timely grasped, and accurate and reasonable risk prediction can be made.

[0024] As a possible implementation method, a loan risk prediction analysis is performed based on the risk information of the loan process to form loan risk warning information, including: setting a loan repayment on-time deviation, determining the loan repayment cycle variance of the loan repayment cycle data, and performing the following analysis and judgment: if the loan repayment cycle variance exceeds the loan repayment on-time deviation, a loan repayment importance cycle function is formed based on the loan repayment importance cycle data to determine the predicted loan repayment importance of the next loan repayment cycle; a loan replenishment rate cycle function is formed based on the loan replenishment rate cycle data to determine the predicted loan replenishment rate of the next loan replenishment collection interval; the predicted loan repayment importance and the predicted loan replenishment rate are combined to form high-risk loan repayment prediction information; if the loan repayment cycle variance does not exceed the loan repayment on-time deviation, a loan repayment importance cycle function is formed based on the loan repayment importance cycle data to determine the predicted loan repayment importance of the next loan repayment cycle; A loan addition rate cycle function is formed according to the loan addition rate cycle data to determine the predicted loan addition rate for the next loan addition collection interval; the following prediction analysis is performed according to the predicted loan repayment importance and the predicted loan addition rate: when the predicted loan repayment importance is not greater than the loan repayment importance corresponding to the current loan repayment cycle, and the predicted loan addition rate is not greater than the loan addition rate corresponding to the current loan addition collection interval, the predicted loan repayment importance and the predicted loan addition rate are combined to form low-risk loan repayment prediction information; when the predicted loan repayment importance is greater than the loan repayment importance corresponding to the current loan repayment cycle, the predicted loan repayment importance and the predicted loan addition rate are combined to form medium-risk loan repayment prediction information; when the predicted loan addition rate is greater than the loan addition rate corresponding to the current loan addition collection interval, the predicted loan repayment importance and the predicted loan addition rate are combined to form medium-risk loan repayment prediction information.

[0025] In the present invention, after obtaining the lending process data of the lending user, the risk size of the target lending transaction of the lending user in the lending process can be determined by comprehensive analysis of these lending process data. Of course, the punctuality of loan repayment is an important risk judgment indicator. Inaccurate loan repayment is a gap judgment point for whether the risk is high. The punctual loan repayment cannot be considered as a high risk as long as it is completed within the final loan repayment time limit. After all, the closer the loan repayment time is to the time limit, the greater the risk. Therefore, a reasonable punctual loan repayment deviation can be determined based on big data, thereby ensuring the accuracy and rationality of the judgment analysis. For borrowers who repay on time, a comprehensive analysis is conducted by considering the loan additional rate and the importance of loan repayment, thereby determining the medium and low risk of loan repayment.

[0026] The beneficial effects of the reliable analysis and prediction method of financial data provided by the present invention are:

[0027] This method analyzes the initial risk of loan transactions by obtaining the basic loan information of the borrower, and then fully grasps the loan risk situation in the early stage of the loan transaction, providing important and reliable reference data for the loan transaction. At the same time, important loan process data is collected and reasonably analyzed during the loan process, and the real-time situation of the loan transaction is reasonably and accurately predicted on the basis of fully grasping the change law of the loan process data, making a reasonable assessment of the risk of the loan transaction, and providing early warning for possible loan transaction risks, effectively ensuring the stable implementation of the loan transaction, and effectively improving the security of loan transaction activities. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments of the present invention are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0029] Figure 1 A step diagram of a reliable analysis and prediction method for financial data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present invention will be described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0031] Lending is the most important mode of operation of financial activities. Through lending, financial products can be sold and used, and the value of the consumption of borrowed financial products can be obtained. With the development of society and the progress of science, the methods of financial activities have gradually diversified and become information-based. Especially for the data informationization of financial activities, lending activities can be accumulated through data retention, which makes it easier for people to have a deeper understanding of the laws of financial activities through the accumulated data.

[0032] At present, most of the analysis of lending activities is still based on a simple analysis of the lending transaction capabilities of the subject before the lending transaction. It is unable to fully control the risks of lending financial products and implement risk measures in real time, resulting in a high level of uncertainty in lending transactions, adding a risk to financial activities.

[0033] refer to Figure 1The embodiment of the present invention provides a reliable analysis and prediction method for financial data. The method analyzes the initial risk of loan transactions by acquiring the basic loan information of the loan users, and then fully grasps the loan risk situation in the early stage of the loan transaction, providing important and reliable reference data for the loan transaction. At the same time, important loan process data is collected and reasonably analyzed during the loan process, and the real-time situation of the loan transaction is reasonably and accurately predicted on the basis of fully grasping the change law of the loan process data, making a reasonable assessment of the risk of the loan transaction, and providing early warning for possible loan transaction risks, effectively ensuring the stable implementation of the loan transaction, and effectively improving the security of loan transaction activities.

[0034] The reliable analysis and prediction method of financial data specifically includes the following steps:

[0035] S1: Obtain the basic lending data of the borrower and conduct initial lending risk analysis to form initial risk information.

[0036] Obtain the basic lending data of borrowers and conduct initial lending risk analysis to form initial risk information, including: obtaining the lending interest rate I of the user's lending target for different borrowers n , n represents the serial number of different lending users; for different lending users, the lending method data of the user's lending target is obtained, and the equivalent value analysis is performed to form the equivalent ratio of the lending method; for different lending users, the net lending ratio of the user's lending target is obtained; according to the lending interest rate, the equivalent value of the lending method and the net lending ratio, the initial lending correlation analysis is performed to determine the initial lending risk value of the lending user for the user's lending target.

[0037] The initial risk analysis of the loan transaction is mainly to determine whether the loan object has the ability to bear the subject of the loan transaction. This application conducts reliable analysis and evaluation of this ability from three aspects: loan interest rate, loan method and net loan ratio. For the loan interest rate, the higher the loan interest rate, the longer the loan time of the loan subject, and the longer the loan time, the higher the loan risk of the loan subject to complete the transaction. Therefore, high interest rates are an important means to ensure the smooth completion of loan transactions. For the loan method, when the loan object obtains the loan subject, it is often necessary to use a value equivalent to the loan subject for loan. At this time, the basis for financial activities is generated. These loan equivalents can be real or intangible, such as equivalent items, intellectual property rights, reputation, etc., and the loan methods corresponding to different types of equivalents are different. These methods will also affect the stability of the loan transaction and generate different degrees of potential loan risks. Therefore, it is necessary to analyze and evaluate the risks based on the loan method. For the net loan ratio, it is mainly to determine the ability of the loan object to bear the loan subject when conducting a loan transaction. After all, the value of the loan subject is a liability at the financial level. Therefore, relative to the net assets of the borrower, the value of the loan subject relative to the net assets can determine the borrower's economic ability to bear the load, and to a certain extent reflects the risk of the borrower in carrying the loan subject. Of course, the combined effect of these three aspects forms an overall measure of the size of the transaction risk in the early stage of the loan transaction.

[0038] Among them, for different lending users, the lending method data of the user's lending subject is obtained, and the equivalent value analysis is performed to form the equivalent ratio of the lending method, including: determining the conversion lending amount M of the user's lending subject n ; Determine the equivalent value of different lending methods corresponding to the user's lending target i represents the number of different loan methods; according to the equivalent value and conversion loan amount M n , determine the borrowing method of the borrower in:

[0039] The magnitude of the risk of loan transactions due to different loan methods is mainly reflected in the difference between the equivalent value formed by different loan methods and the value of the loan subject. After all, the difference between the equivalent value of the loan provided by the loan object and the value of the loan subject is too large, which is a non-equivalent loan transaction in a sense, and thus makes the loan transaction have a greater risk of value imbalance. Here, it should be noted that the equivalent objects provided by the loan subject corresponding to different loan methods are different. For example, the loan with credit guarantee is mainly based on the historical loan and credit behavior of the loan object to assess the repayment ability as the equivalent object, and the mortgage loan is mainly based on the equivalent collateral provided by the loan object as the equivalent object, etc. Of course, a loan transaction can be a combination of multiple loan methods. Therefore, when conducting risk assessment analysis of loan methods, it is necessary to consider all loan methods included in the loan transaction, and take the sum of the equivalent amounts provided by these loan methods as the object of risk assessment.

[0040] For different borrowers, obtain the net borrowing ratio of the borrower's borrowing target, including: determining the total assets P of the borrower n and total liabilities L n , determine the net assets A of the borrower n , where A n =P n -L n ; According to the conversion loan amount M of the borrower's user loan target n and the net assets of the borrower A n , determine the net lending ratio of the borrower's user lending target in:

[0041] The net loan ratio is mainly used to determine the ratio of the value of the loan subject to the current net assets of the borrower. The size of the ratio highlights whether the borrower has sufficient capacity to ensure the completion of the loan transaction. This is an important reference data for the initial risk analysis of the loan transaction.

[0042] According to the loan interest rate, loan method and net loan ratio, an initial loan correlation analysis is performed to determine the initial loan risk value of the borrower for the user's loan target, including: according to the loan interest rate I corresponding to the borrower's user loan target n , loan and borrowing method equal ratio and net borrowing ratio Determine the initial lending risk value C of the lending user's lending target n ,in: α 1 , α 2 and α 3 are the corresponding correlation factors, and α 1 +α2 +α 3 =1.

[0043] The lending rate, lending method and net lending ratio each independently characterize the risk of lending transactions in different aspects of lending transactions. The overall acquisition of the impact of the three aspects on the risk of lending transactions can then reliably and reasonably determine the risk of the current lending transactions. The correlation factor can be set according to actual conditions, or it can be determined through big data to determine the impact of these three aspects on the risk of lending transactions.

[0044] S2: Based on the initial risk information, the lending process data of different lending users is collected, and the lending process reputation analysis is performed based on the lending process data to form lending process risk information.

[0045] According to the initial risk information, the lending process data of different lending users are collected, and the lending process reputation analysis is performed based on the lending process data to form the lending process risk information, including: collecting the repayment information of the user lending objects of the lending users, and performing periodic statistics to form the repayment cycle data; collecting the repayment information of all lending objects of the lending users, and performing importance analysis based on periodic statistics to form repayment importance cycle data; determining the lending additional collection interval according to the initial risk information, and obtaining the total lending amount information of the lending users according to the lending additional collection interval, and performing periodic lending additional rate analysis to form lending additional rate cycle data; combining the lending users' repayment cycle data, repayment importance cycle data and lending additional rate cycle data to form the lending process risk information of the user lending objects of the lending users.

[0046] On the one hand, the analysis of initial lending risk is to conduct reliable and reasonable data analysis of the risk size in the initial stage of lending transactions, so as to provide guarantee for real-time, safe and stable transactions in the initial stage of lending transactions. On the other hand, the initial lending risk also reflects the initial lending capacity of the lending object, which provides important basic data for the subsequent analysis of the lending object's lending capacity in the lending process, and ensures the rationality and accuracy of the process data analysis. The analysis of the lending process data is mainly to evaluate and predict whether the conditions that affect the stability and security of the lending transaction have changed during the lending process, and then determine whether it affects the risk size of the lending transaction, so as to make reasonable early warning predictions. There are three main factors that affect the change of risk size in this process. One aspect is to monitor the punctuality of the lending user in completing the lending transaction. Here, it is shown by analyzing the repayment time. After all, the earlier the repayment, the higher the credit of the lending user in completing the lending transaction, the more sufficient the capital it has to ensure the completion of the lending transaction, and the lower the risk of the lending transaction. Here, the loan repayment information content can be broadly analyzed, mainly based on the loan repayment time point, including the early repayment time for the over-repayment time point, that is, the total loan repayment limit time is shortened according to the size of the early repayment, and the relatively delayed under-repayment time is increased. The second aspect is to consider the repayment of the loan repayment target among all the loan repayment targets of the loan repayment user. The consideration in this aspect is mainly to determine the impact of other loan repayment target transactions on the target loan transaction. After all, the total capital of the loan user is limited, and multiple loan transactions require reasonable capital allocation. Here, by analyzing the order of repayment of the target loan transaction in all the loan transactions of the loan user and the size of the loan repayment capital, the loan user's consideration of the importance of all its loan transactions can be determined, and then the risk of the target loan transaction being considered for normal completion in the case of a shortage of capital for the loan user can be analyzed. The third aspect is the analysis of the change in the total debt of the loan user, that is, the loan amount. After all, the change in the total debt of the loan user will affect the loan user's consideration of the loan repayment behavior of the loan transaction including the target loan transaction, and then have a certain risk impact on the completion of the target loan transaction. It is understandable that users with different initial lending risks have certain differences in risk analysis during the lending process. After all, for users with higher initial risks, it is necessary to conduct more rigorous analysis and monitoring during the lending process, while for users with lower initial risks, it is safer to conduct analysis and monitoring during the lending process. This can ensure reasonable analysis and monitoring of the lending process of different borrowers and provide accurate predictive analysis. On the other hand, it can fully realize the analysis and monitoring of the lending process of all borrowers while fully saving monitoring and analysis resources.

[0047] The loan repayment information of the user's loan subject is collected and periodic statistics are performed to form the loan repayment cycle data, including: obtaining the actual loan repayment date of the user's loan subject in each loan repayment cycle in the previous k loan repayment cycles including the current loan repayment cycle; And the corresponding maximum loan repayment date According to the actual loan repayment date corresponding to each repayment cycle and maximum repayment date Determine the on-time repayment rate for each loan repayment cycle in, The on-time repayment rate corresponding to each loan repayment cycle Arrange them in chronological order to form loan repayment cycle data.

[0048] Considering the analysis and monitoring of process quantity, the data of loan repayment cycle is statistically based on time. The on-time loan repayment rate is characterized by the ratio of the total loan repayment time limit to the actual loan repayment time. The data can be reasonably expressed by extracting more or less repayments or compressing or increasing the loan repayment time limit while keeping the actual loan repayment time unchanged, which is convenient for the general collection of information about the loan repayment cycle and accurate and reasonable loan repayment process data analysis and monitoring.

[0049] Collect the repayment information of all loan targets of the borrower, and conduct importance analysis based on cycle statistics to form repayment importance cycle data, including: in the previous k repayment cycles including the current repayment cycle, determine the repayment order of the borrower's user loan target among all loan targets in each repayment cycle, and determine the repayment order rate of the user's loan target in, Indicates the repayment order value of the user's loan subject in the loan repayment cycle numbered k. Indicates the maximum repayment order value of the repayment cycle numbered k; determines the proportion of the repayment amount of the user's loan target in the previous k repayment cycles including the current repayment cycle in, Indicates the repayment amount of the user's loan subject in the loan repayment cycle numbered k. Indicates the total amount of loan repayments in the loan repayment cycle numbered k; according to the loan repayment sequence rate corresponding to each loan repayment cycle and loan repayment ratio Determine the importance of loan repayment for the corresponding loan repayment period in, β 1 , β 2 are the corresponding importance factors respectively; the importance of loan repayment corresponding to each loan repayment period is Arrange them in chronological order to form loan repayment importance cycle data.

[0050] The importance of loan repayment is determined by obtaining the repayment order information of the target loan subject and the proportion of the repayment amount to the total loan repayment amount. After all, these two aspects simultaneously represent the situation in which the target loan subject is affected by other loan subjects and thus causes changes in the size of risk.

[0051] According to the initial risk information, determine the additional loan collection interval, and obtain the total loan information of the borrower according to the additional loan collection interval, and conduct a cycle-based additional loan rate analysis to form the additional loan rate cycle data, including: setting the risk segmentation function, obtaining the initial loan risk value C of the borrower n , and according to the risk segmentation function and the initial lending risk value C n , determine the additional lending collection interval for borrowers; take the additional lending collection interval as the data collection period, take the current time point as the interval end time of the current additional lending collection interval, and collect the change amount of borrowers' lending within the previous e additional lending collection intervals and periodic net assets According to the change amount of each additional loan collection interval and periodic net assets Determine the loan addition rate corresponding to the loan addition collection interval in, The loan additional rate corresponding to each loan additional collection interval Arrange them in chronological order to form the loan addition rate cycle data.

[0052] It should be noted that the risk segmentation function mainly considers that borrowers with different initial risk sizes need to conduct targeted analysis of their own debt changes. After all, borrowers with higher initial risks often have relatively frequent lending transactions in order to ensure the smooth operation of their own capital, so they need to pay close attention to analysis. On the contrary, borrowers with lower initial risks have relatively fewer lending transactions due to their stable capital activities. Therefore, the main function of the risk segmentation function is to determine the frequency of debt data collection based on the initial lending risk size of the borrower. The segmented output value given by the risk segmentation function can be determined according to actual needs, or it can be determined by big data analysis of the debt of the borrower. By determining a reasonable and targeted data collection interval to collect the debt change data of the borrower, the accuracy of the real-time analysis and monitoring data can be guaranteed, and then the lending risk can be accurately and timely grasped, and accurate and reasonable risk prediction can be made.

[0053] S3: Conduct loan risk forecasting and analysis based on the risk information of the loan process to form loan risk warning information.

[0054] Based on the risk information of the lending process, a lending risk prediction analysis is performed to form lending risk warning information, including: setting a loan repayment on-time deviation, determining the loan repayment cycle variance of the loan repayment cycle data, and performing the following analysis and judgment: if the loan repayment cycle variance exceeds the loan repayment on-time deviation, a loan repayment importance cycle function is formed based on the loan repayment importance cycle data to determine the predicted loan repayment importance of the next loan repayment cycle; a loan replenishment rate cycle function is formed based on the loan replenishment rate cycle data to determine the predicted loan replenishment rate of the next loan replenishment collection interval; the predicted loan repayment importance and the predicted loan replenishment rate are combined to form high-risk loan repayment prediction information; if the loan repayment cycle variance does not exceed the loan repayment on-time deviation, a loan repayment importance cycle function is formed based on the loan repayment importance cycle data to determine the predicted loan repayment importance of the next loan repayment cycle; The loan addition rate cycle data forms a loan addition rate cycle function to determine the predicted loan addition rate for the next loan addition collection interval; the following prediction analysis is performed based on the predicted loan repayment importance and the predicted loan addition rate: when the predicted loan repayment importance is not greater than the loan repayment importance corresponding to the current loan repayment cycle, and the predicted loan addition rate is not greater than the loan addition rate corresponding to the current loan addition collection interval, the predicted loan repayment importance and the predicted loan addition rate are combined to form low-risk loan repayment prediction information; when the predicted loan repayment importance is greater than the loan repayment importance corresponding to the current loan repayment cycle, the predicted loan repayment importance and the predicted loan addition rate are combined to form medium-risk loan repayment prediction information; when the predicted loan addition rate is greater than the loan addition rate corresponding to the current loan addition collection interval, the predicted loan repayment importance and the predicted loan addition rate are combined to form medium-risk loan repayment prediction information.

[0055] After obtaining the lending process data of the borrower, the risk of the borrower in the target lending transaction can be determined by comprehensive analysis of these lending process data. Of course, the punctuality of loan repayment is an important risk judgment indicator. Inaccurate loan repayment is a gap judgment point for whether the risk is high. The punctuality of loan repayment cannot be regarded as a high risk as long as it is completed within the final loan repayment time limit. After all, the closer the loan repayment time is to the time limit, the greater the risk. Therefore, a reasonable deviation from the punctuality of loan repayment can be determined based on big data, thereby ensuring the accuracy and rationality of the judgment and analysis. For borrowers who repay on time, a comprehensive analysis is conducted by considering the loan additional rate and the importance of loan repayment, and then the medium and low risk of loan repayment risk is determined.

[0056] In summary, the beneficial effects of the reliable analysis and prediction method of financial data provided by the embodiment of the present invention are as follows:

[0057] This method analyzes the initial risk of loan transactions by obtaining the basic loan information of the borrower, and then fully grasps the loan risk situation in the early stage of the loan transaction, providing important and reliable reference data for the loan transaction. At the same time, important loan process data is collected and reasonably analyzed during the loan process, and the real-time situation of the loan transaction is reasonably and accurately predicted on the basis of fully grasping the change law of the loan process data, making a reasonable assessment of the risk of the loan transaction, and providing early warning for possible loan transaction risks, effectively ensuring the stable implementation of the loan transaction, and effectively improving the security of loan transaction activities.

[0058] In the embodiments of the present application, "indication" may include direct indication and indirect indication, and may also include explicit indication and implicit indication. The information indicated by a certain information is called information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated, such as but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or the index of the information to be indicated. The information to be indicated can also be indirectly indicated by indicating other information, wherein there is an association between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the other parts of the information to be indicated are known or agreed in advance. For example, the indication of specific information can also be achieved by means of the arrangement order of each piece of information agreed in advance (for example, specified by the protocol), thereby reducing the indication overhead to a certain extent. At the same time, the common parts of each piece of information can also be identified and indicated uniformly to reduce the indication overhead caused by indicating the same information separately.

[0059] In addition, the specific indication method may also be various existing indication methods, such as but not limited to the above-mentioned indication methods and various combinations thereof. The specific details of the various indication methods can refer to the prior art and will not be repeated herein. As can be seen from the above, for example, when it is necessary to indicate multiple information of the same type, different indication methods may be used for different information. In the specific implementation process, the desired indication method can be selected according to specific needs. The embodiment of the present application does not limit the selected indication method. In this way, the indication method involved in the embodiment of the present application should be understood to cover various methods that can enable the party to be indicated to obtain the information to be indicated.

[0060] It should be understood that the information to be indicated can be sent as a whole, or divided into multiple sub-information and sent separately, and the sending period and / or sending time of these sub-information can be the same or different. The specific sending method is not limited in the embodiment of the present application. Among them, the sending period and / or sending time of these sub-information can be pre-defined, for example, pre-defined according to a protocol, or can be configured by the sending end device by sending configuration information to the receiving end device.

[0061] "Pre-definition" or "pre-configuration" can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in the device, and the embodiments of the present application do not limit the specific implementation method. Among them, "saving" can mean saving in one or more memories. The one or more memories can be set separately or integrated in an encoder or decoder, a processor, or a communication device. The one or more memories can also be partially set separately and partially integrated in a decoder, a processor, or a communication device. The type of memory can be any form of storage medium, which is not limited by the embodiments of the present application.

[0062] The "protocol" involved in the embodiments of the present application may refer to a protocol family in the communication field, a standard protocol with a similar protocol family frame structure, or a related protocol used in future communication systems, and the embodiments of the present application do not make specific limitations on this.

[0063] In the embodiments of the present application, descriptions such as "when...", "in the case of...", "if" and "if" all mean that the device will make corresponding processing under certain objective circumstances. It does not limit the time, nor does it require the device to have a judgment action when implementing it, nor does it mean that there are other limitations.

[0064] In the description of the embodiments of the present application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the embodiments of the present application is only a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or its similar expression refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple. In addition, in order to facilitate the clear description of the technical solution of the embodiments of the present application, in the embodiments of the present application, the words "first" and "second" are used to distinguish the same or similar items with basically the same functions and effects. Those skilled in the art will appreciate that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference. At the same time, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way for easy understanding.

[0065] It should be understood that the processor in the embodiments of the present application may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0066] It should also be understood that the memory in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0067] The above embodiments can be implemented in whole or in part by software, hardware (such as circuits), firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0068] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0069] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0070] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0071] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0072] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0073] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0074] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0075] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0076] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0077] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A reliable analysis and prediction method for financial data, characterized in that: include: Obtain the basic lending data of borrowers and conduct initial lending risk analysis to form initial risk information; According to the initial risk information, the lending process data of different lending users are collected, and the lending process reputation analysis is performed based on the lending process data to form lending process risk information; Perform loan risk forecasting and analysis based on the loan process risk information to form loan risk warning information; Among them, the basic lending data of the borrower is obtained, and the initial lending risk analysis is performed to form the initial risk information, including: For different borrowing users, obtain the borrowing interest rate I of the borrowing target n , n represents the serial number of different borrowing users; For different borrowing users, the borrowing method data of the borrowing objects of the users are obtained, and an equivalent value analysis is performed to form an equivalent ratio of borrowing methods; For different borrowing users, obtaining the net borrowing ratio of the borrowing objects of the users; Performing an initial lending correlation analysis based on the lending interest rate, the lending method equal volume ratio, and the net lending ratio to determine the initial lending risk value of the lending user for the user's lending subject; According to the initial risk information, the lending process data of different lending users are collected, and the lending process reputation analysis is performed based on the lending process data to form lending process risk information, including: Collecting the loan repayment information of the user's loan subject of the borrower, and performing periodic statistics to form loan repayment cycle data; Collecting the loan repayment information of all loan objects of the borrower, and performing importance analysis based on periodic statistics to form loan repayment importance periodic data; Determine the additional loan collection interval according to the initial risk information, obtain the total loan amount information of the borrower according to the additional loan collection interval, and perform cycle-based additional loan rate analysis to form additional loan rate cycle data; The loan repayment cycle data, the loan repayment importance cycle data and the loan additional rate cycle data of the loan user are collected to form the loan process risk information of the user loan object of the loan user; Based on the risk information of the lending process, a lending risk forecast analysis is performed to form lending risk warning information, including: Set the loan repayment punctuality deviation, determine the loan repayment cycle variance of the loan repayment cycle data, and perform the following analysis and judgment: If the loan repayment cycle variance exceeds the loan repayment punctuality deviation, a loan repayment importance cycle function is formed according to the loan repayment importance cycle data to determine the predicted loan repayment importance of the next loan repayment cycle; a loan supplement rate cycle function is formed according to the loan supplement rate cycle data to determine the predicted loan supplement rate of the next loan supplement collection interval; the predicted loan repayment importance and the predicted loan supplement rate are combined to form high-risk loan repayment prediction information; If the repayment cycle variance does not exceed the repayment punctuality deviation, a repayment importance cycle function is formed according to the repayment importance cycle data to determine the predicted repayment importance of the next repayment cycle; a loan additional rate cycle function is formed according to the loan additional rate cycle data to determine the predicted loan additional rate of the next loan additional collection interval; and the following prediction analysis is performed according to the predicted repayment importance and the predicted loan additional rate: When the predicted loan repayment importance is not greater than the loan repayment importance corresponding to the current loan repayment cycle, and the predicted loan additional rate is not greater than the loan additional rate corresponding to the current loan additional collection interval, the predicted loan repayment importance and the predicted loan additional rate are combined to form low-risk loan repayment prediction information; When the predicted loan repayment importance is greater than the loan repayment importance corresponding to the current loan repayment cycle, the predicted loan repayment importance and the predicted loan additional rate are combined to form medium-risk loan repayment prediction information; When the predicted loan additional rate is greater than the loan additional rate corresponding to the current loan additional collection interval, the predicted loan repayment importance and the predicted loan additional rate are combined to form medium-risk loan repayment prediction information.

2. The method for reliable analysis and prediction of financial data according to claim 1, characterized in that: For different borrowing users, obtaining the borrowing method data of the borrowing objects of the users, and performing equivalent value analysis to form an equivalent ratio of borrowing methods includes: Determine the conversion loan amount M of the user loan target of the lending user n ; Determine the equivalent value of different loan methods corresponding to the user's loan target i represents the number of different loan methods; According to the equivalent value and the conversion loan amount M n , determine the equivalent ratio of the lending method of the lending user in:

3. The reliable analysis and prediction method of financial data according to claim 2, characterized in that: The obtaining, for different lending users, the net lending ratio of the user's lending targets includes: Determine the total assets P of the borrower n and total liabilities L n , determine the net assets A of the borrowing user n , where A n =P n -L n ; The conversion loan amount M of the user's loan target according to the loan user n and the net assets A of the lending user n , determine the net lending ratio of the user's lending target of the lending user in:

4. The method for reliable analysis and prediction of financial data according to claim 3, characterized in that: The initial lending correlation analysis is performed based on the lending interest rate, the lending method equal volume ratio and the net lending ratio to determine the initial lending risk value of the lending user for the user's lending target, including: According to the loan interest rate I corresponding to the user loan target of the loan user n 、The above-mentioned loan method is equal to the and the net borrowing ratio Determine the initial lending risk value C of the lending user's lending target n ,in: α1, α2 and α3 are corresponding correlation factors respectively, and α1+α2+α3=1.

5. The method for reliable analysis and prediction of financial data according to claim 4, characterized in that: The collecting of the loan repayment information of the user's loan subject and performing periodic statistics to form loan repayment cycle data includes: Get the actual repayment date of the user's loan subject in each loan repayment cycle in the previous k loan repayment cycles including the current loan repayment cycle And the corresponding maximum loan repayment date According to the actual loan repayment date corresponding to each loan repayment cycle and the maximum repayment date Determine the on-time repayment rate for each of the loan repayment cycles in, The loan repayment punctuality rate corresponding to each loan repayment cycle Arrange them in chronological order to form the loan repayment cycle data.

6. The method for reliable analysis and prediction of financial data according to claim 5, characterized in that: The collecting of the loan repayment information of all loan objects of the loan user and performing importance analysis based on periodic statistics to form loan repayment importance periodic data includes: In the first k loan repayment cycles including the current loan repayment cycle, determine the repayment order of the user loan target of the borrower in each loan repayment cycle among all loan targets, and determine the repayment order rate of the user loan target in, represents the repayment order value of the user's loan subject in the repayment cycle numbered k, represents the maximum loan repayment sequence value of the loan repayment cycle numbered k; Determine the proportion of the repayment amount of the user's loan subject in the previous k loan repayment cycles including the current loan repayment cycle in, represents the repayment amount of the user's loan subject in the loan repayment cycle numbered k, represents the total loan repayment amount in the loan repayment cycle numbered k; According to the repayment sequence rate corresponding to each repayment cycle and the proportion of the loan repayment amount Determine the importance of loan repayment corresponding to the loan repayment period in, β1 and β2 are the corresponding importance factors; The loan repayment importance corresponding to each loan repayment period The data are arranged in chronological order to form the loan repayment importance cycle data.

7. The method for reliable analysis and prediction of financial data according to claim 6, characterized in that: Determining the additional loan collection interval according to the initial risk information, acquiring the total loan amount information of the borrower according to the additional loan collection interval, and performing cycle-based additional loan rate analysis to form additional loan rate cycle data, including: Set the risk segmentation function to obtain the initial lending risk value C of the lending user n , and according to the risk segmentation function and the initial lending risk value C n , determining the additional loan collection interval of the lending user; The additional loan collection interval is used as the data collection period, the current time point is used as the end time of the current additional loan collection interval, and the loan change amount of the borrower in the previous e additional loan collection intervals is collected. and periodic net assets According to the change amount of the loan corresponding to each additional collection interval of the loan and net assets for the period Determine the additional lending rate corresponding to the additional lending collection interval in, The loan additional rate corresponding to each loan additional collection interval Arrange them in chronological order to form the loan addition rate cycle data.

Images