Multi-source information-oriented credit data management method and system

Abstract

The invention discloses a credit data management method and system for multi-source information, and relates to the field of data processing, and the main scheme is as follows: collecting personal income stability data, consumption behavior data, credit historical data, public service payment data, insurance record data and judicial record data, and calculating corresponding indexes; the credit evaluation dimension is more perfect, and the problem that the accuracy of personal credit condition evaluation is affected due to insufficient data types during information collection is solved; the personal credit score # imgabs1 # is calculated according to the credit good probability # imgabs0 #, the credit probability threshold set and the credit score threshold set, so that the quantification of the personal credit condition is facilitated, and the problem that the effectiveness of the personal credit score is reduced as time goes on is solved; the credit rating is divided according to the personal credit score # imgabs2 and the credit rating threshold set, which is beneficial to risk management and resource allocation of financial institutions.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a credit data management method and system for multi-source information. Background Art

[0002] With the rapid development of economic globalization and information technology, the management of credit data has become increasingly important. In the era of big data, the sources of credit data are increasingly diverse, including but not limited to bank credit records, public utility payment records, court judgment information, consumer information on online trading platforms, etc. And with the convenience and popularity of online transactions such as the Internet, when evaluating personal credit scores, it is particularly important to pay attention to the transaction data of online platforms.

[0003] However, in the existing credit assessment system, existing technologies still have the problem of a single data type when collecting information and are unable to reflect multi-faceted aspects, which can easily affect the accuracy of personal credit status assessment; over time, the distribution of credit data may change, and the effectiveness of calculating personal credit scores based on personal credit probabilities will decrease, resulting in insufficient effectiveness of personal credit. Summary of the invention

[0004] 1. Technical issues to be resolved In view of the shortcomings of the prior art, the present invention provides a credit data management method and system for multi-source information. By collecting personal income stability data, consumption behavior data, credit history data, public utility payment data, insurance record data and judicial record data and calculating corresponding indicators, the problem of insufficient data types when collecting information, which affects the accuracy of personal credit status assessment, is solved. , credit probability threshold set and credit score threshold set to calculate personal credit score , which addresses the problem of personal credit scores becoming less effective over time.

[0005] (II) Technical solution To achieve the above objectives, the present invention is implemented through the following technical solutions: a credit data management method and system for multi-source information, characterized in that it includes the following steps: Collect personal income stability data, consumer behavior data, credit history data, utility payment data, insurance record data, and judicial record data; Calculate income stability score based on individual income stability data , job stability score and occupation type score ; and further calculate the income stability index ; Calculate consumption ratio based on consumption behavior data and personal income stability data , according to the consumption ratio Calculate consumption ratio score ; Calculate consumption diversity indicators based on consumption behavior data , according to the consumption diversity index Calculating consumption diversity scores ; Score based on consumption ratio and consumption diversity score Calculate consumption index ; Calculate repayment stability based on credit history data ; Calculate repayment capacity indicators based on credit history data and personal income stability data ; Based on repayment stability and solvency indicators Calculating credit indicators ; Calculation of public utility indicators based on public utility payment data ; Calculate insurance indicators based on insurance record data ; Calculating case indicators based on judicial record data and crime indicators ; and further calculate judicial indicators ; The income stability index , consumption indicators , credit indicators , public utility indicators , Insurance Indicators and judicial indicators Perform preprocessing and calculate the probability of good credit ; Preset credit probability threshold set and credit score threshold; Based on good credit probability , credit probability threshold set and credit score threshold set to calculate personal credit score ; Preset credit rating threshold set, based on personal credit score Credit ratings are divided according to credit rating thresholds.

[0006] In the preferred embodiment of the credit data management method for multi-source information, the income stability index is calculated. The method is: Income stability data includes monthly fixed job income value , Monthly part-time job income , Continuous working years , Number of career changes , Industry type stability score and occupational stability score ; Based on the monthly fixed work income and monthly part-time job income Calculating the income stability score , the formula based on is:

[0007] in, For the Months of fixed job income; For the Months’ worth of part-time job income; It is the serial number corresponding to different months, and its value is ; is the total number of months in a unit of time, and the value is a positive integer; Based on continuous working years and number of career changes Calculating job stability scores , the formula based on is:

[0008] Stability score by industry type and occupational stability score Calculating Occupational Type Score , the formula based on is: =

[0009] Among them, the industry type stability score For the Stability score of each industry type; is the serial number corresponding to different industry types, and the value is a positive integer; occupational stability score For the The stability score of the occupational nature; is the serial number corresponding to different occupational natures, and its value is a positive integer; Score stability for industry types The weight coefficient is between 0.4 and 0.6; Score for job stability The weight coefficient is between 0.4 and 0.6; and + =1; Based on income stability score , job stability score and occupation type score , calculate the income stability index , the formula based on is:

[0010] in, Score income stability The weight coefficient is between 0.2 and 0.5; Score job stability The weight coefficient is 0.3 to 0.5; Score for career type The weight coefficient is between 0.2 and 0.5; and + + =1.

[0011] In the preferred embodiment of the credit data management method for multi-source information, the consumption index is calculated. The method is: Consumption behavior data includes personal monthly consumption amount , Consumption Category Amount and total amount of consumption ; Based on monthly consumption , Monthly fixed job income and monthly part-time job income Calculate consumption ratio , the formula based on is:

[0012] According to consumption ratio Calculate consumption ratio score , based on the following criteria:

[0013] Amount by consumption category and total amount of consumption Calculating consumption diversity indicators , the formula based on is:

[0014] in, For the The amount of consumption in each consumption category; is the serial number corresponding to different consumption categories, and its value is ; is the total number of different consumption categories, which is a positive integer; According to the consumption diversity index Calculating consumption diversity scores , based on the following criteria:

[0015] Score based on consumption ratio and consumption diversity score Calculate consumption index , the formula based on is: .

[0016] In the preferred embodiment of the credit data management method for multi-source information, the credit index is calculated. The method is: Credit history data includes the total number of personal credit repayments , Number of overdue payments and repayment amount ; Based on the total number of personal loan repayments and number of overdue payments Calculate repayment stability , the formula based on is:

[0017] According to the repayment amount , Monthly fixed job income and monthly part-time job income Calculating solvency index , the formula based on is:

[0018] Based on repayment stability and solvency indicators Calculating credit indicators , the formula based on is:

[0019] in, For repayment stability The weight coefficient is between 0.4 and 0.6; The solvency indicator The weight coefficient is between 0.4 and 0.6, and =1.

[0020] In the preferred embodiment of the credit data management method for multi-source information, the public utility index is calculated. The method is: Utility bill payment data including number of days late for payment ; Calculation of public utility indicators based on public utility payment data , the formula based on is:

[0021] in, For the Months of delayed payment.

[0022] In the preferred embodiment of the credit data management method for multi-source information, the insurance index is calculated. The method is: Insurance record data including the number of times premiums were paid on time , the number of premiums payable , Insurance Diversity Score and insurance purchase continuity score ; Calculate insurance indicators based on insurance record data , the formula based on is: .

[0023] In the preferred embodiment of the credit data management method for multi-source information, the judicial index is calculated. The method is: Judicial records data includes the number of cases involving individuals involved in financial disputes , Number of successful cases involving economic disputes , Economic Crime Severity Score and the crime decay time coefficient ; According to the number of cases involving economic disputes and the number of cases involving economic disputes won Calculating case indicators , the formula based on is:

[0024] Score based on severity of economic crime and the crime decay time coefficient Calculating crime indicators , the formula based on is:

[0025] According to case indicators and crime indicators Calculating judicial indicators , the formula based on is: + .

[0026] In the preferred embodiment of the credit data management method for multi-source information, the probability of good credit is calculated. The method is: The income stability index , consumption indicators , credit indicators , public utility indicators , Insurance Indicators and judicial indicators Input the logistic regression model for preprocessing, and calculate the probability of good credit based on the preprocessed indicators , the formula based on is:

[0027] in, is the intercept; Standard income stability indicator The characteristic coefficient of Standard consumption index The characteristic coefficient of Standard credit indicators The characteristic coefficient of Standard utility indicators The characteristic coefficient of Standard insurance index The characteristic coefficient of Standard judicial indicators Characteristic coefficient of; standard income stability index Income stability indicator Parameter values ​​after preprocessing; standard consumption indicators For consumption indicators Preprocessed parameter values; standard credit indicators Credit Indicator Preprocessed parameter values; standard utility indicators Public utility indicators Preprocessed parameter values; standard insurance indicators For insurance indicators Preprocessed parameter values; standard judicial indicators For judicial indicators The parameter value after preprocessing.

[0028] In the preferred solution of the credit data management method for multi-source information, the method of dividing the credit level is: The credit probability threshold set includes the credit probability low threshold and credit probability high threshold ; Credit score threshold set includes low credit score threshold and high credit score threshold ; Based on the probability of good credit , credit probability threshold set and credit score threshold set to calculate personal credit score The method is: When 0 Calculate personal credit score The method is:

[0029] when Calculate personal credit score The method is:

[0030] when Calculate personal credit score The method is:

[0031] The credit rating threshold set includes low credit rating Threshold and credit rating high threshold ; Based on personal credit score The credit rating threshold set is divided into the following standards:

[0032] Among them, A-level credit is a high credit rating, B-level credit is a medium credit rating, and C-level credit is a low credit rating.

[0033] The present invention also discloses a credit data management system for multi-source information, which is characterized by comprising: Data collection module, used to collect personal income stability data, consumption behavior data, credit history data, public utility payment data, insurance record data and judicial record data; Indicator calculation module, used to calculate income stability scores based on personal income stability data , job stability score and occupation type score ; and further calculate the income stability index ; Calculate consumption ratio based on consumption behavior data and personal income stability data , according to the consumption ratio Calculate consumption ratio score ; Calculate consumption diversity indicators based on consumption behavior data , according to the consumption diversity index Calculating consumption diversity scores ; Score based on consumption ratio and consumption diversity score Calculate consumption index ; Calculate repayment stability based on credit history data ; Calculate repayment capacity indicators based on credit history data and personal income stability data ; Based on repayment stability and solvency indicators Calculating credit indicators ; Calculation of public utility indicators based on public utility payment data ; Calculate insurance indicators based on insurance record data ; Calculating case indicators based on judicial record data and crime indicators ; and further calculate judicial indicators ; Credit rating module, used to convert income stability indicators , consumption indicators , credit indicators , public utility indicators , Insurance Indicators and judicial indicators Perform preprocessing and calculate the probability of good credit ; Preset credit probability threshold set and credit score threshold; Based on good credit probability , credit probability threshold set and credit score threshold set to calculate personal credit score ; Preset credit rating threshold set, based on personal credit score Credit ratings are divided according to credit rating thresholds.

[0034] (III) Beneficial effects The present invention provides a credit data management method and system for multi-source information, which has the following beneficial effects: (1) By collecting personal income stability data, consumption behavior data, credit history data, public utility payment data, insurance record data, and judicial record data, it can provide effective data for the subsequent calculation of various indicators, thereby improving the accuracy of credit assessment; (2) Based on the income stability score , job stability score and occupation type score Calculating the income stability index , which helps to understand the individual's economic foundation; score based on consumption ratio and consumption diversity score Calculate consumption index , can measure whether an individual's consumption habits are reasonable; according to the repayment stability ratio and solvency indicators Calculating credit indicators , which can reflect the individual's credit risk level and help financial institutions to reasonably allocate credit resources; calculate public utility indicators based on public utility payment data , which can improve the comprehensiveness of credit assessment and help improve the credit system; calculate insurance indicators based on insurance record data , which can quantify individual insurance risk situations; calculate judicial indicators based on judicial record data , can complement other indicators to make the credit evaluation dimension more complete; (3) Income stability index , consumption indicators , credit indicators , public utility indicators , Insurance Indicators and judicial indicators Perform standardization preprocessing and calculate the probability of good credit , can more comprehensively reflect the credit status of an individual; according to the probability of good credit , credit probability threshold set and credit score threshold set to calculate personal credit score , which is conducive to quantifying personal credit status and reflecting the differences in personal credit in a more detailed manner. At the same time, it solves the problem that the effectiveness of personal credit scores decreases over time; based on personal credit scores The division of credit ratings based on a set of credit rating thresholds is beneficial for financial institutions to conduct risk management and resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The figure is a schematic diagram of the working steps of a credit data management method for multi-source information of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0037] See also Figure 1 The present invention provides a credit data management method for multi-source information, comprising: Step 1: Collect personal income stability data, consumer behavior data, credit history data, utility payment data, insurance record data, and judicial record data.

[0038] Combined with the content of step 1: By collecting personal income stability data, consumption behavior data, credit history data, utility payment data, insurance record data and judicial record data, it is possible to provide effective data for the subsequent calculation of various indicators, thereby improving the accuracy of credit assessment.

[0039] Step 2: Calculate income stability score based on individual income stability data , job stability score and occupation type score ; and further calculate the income stability index .

[0040] Calculate consumption ratio based on consumption behavior data and personal income stability data , according to the consumption ratio Calculate consumption ratio score ; Calculate consumption diversity indicators based on consumption behavior data , according to the consumption diversity index Calculating consumption diversity scores ; Score based on consumption ratio and consumption diversity score Calculate consumption index .

[0041] Calculate the overdue repayment ratio based on credit history data ; Calculate the credit ratio based on credit history data and personal income stability data ; Based on the overdue repayment ratio and credit ratio Calculating credit indicators ; Calculation of public utility indicators based on public utility payment data .

[0042] Calculate insurance indicators based on insurance record data .

[0043] Calculating case indicators based on judicial record data and crime indicators ; and further calculate judicial indicators .

[0044] Step 2 includes the following steps: Step 201: Calculate the income stability index The method is: Income stability data includes monthly fixed job income value , Monthly part-time job income , Continuous working years , Number of career changes , Industry type stability score and occupational stability score .

[0045] Among them, the monthly fixed work income value The monthly income that can be obtained stably under normal working conditions is obtained through the salary payment records of the salary payment bank. The relevant data can be obtained through third-party part-time job platforms. The part-time job platforms can be online platforms such as Douyin, Kuaishou, Xiaohongshu and other third-party online platforms. The total time from the employee's entry date to the current date, obtained by querying the employee's file through the company's human resources department. The number of times an individual has changed jobs, obtained through the human resources platform or the Social Security Bureau. Industry type stability score The method of obtaining the score is as follows: industry experts refer to reports and macroeconomic data released by industry research institutions, such as the industry's growth rate, market demand volatility, and policy support for the industry, and divide industry stability into three levels: high, medium, and low. The high level is the industry type stability score of 3 points, such as the high-tech industry; the medium level is the industry type stability score of 2 points, such as the education industry; and the low level is the industry type stability score of 1 point, such as the retail industry. Occupational stability score The way to obtain it is: when the occupation is a long-term contract worker, the occupational stability score is 15 points. When the occupation is a short-term contract worker or a part-time employee, the occupational stability score is 10 points. When the occupation is a flexible worker or a freelancer, the occupational stability score is 5 points.

[0046] Based on the monthly fixed work income and monthly part-time job income Calculating the income stability score , the formula based on is:

[0047] It should be noted that this formula is calculated by calculating the monthly fixed work income value The ratio of monthly income to total income is used to measure income stability; the higher the ratio, the more stable the income, and the income stability score is The higher.

[0048] in, For the Months of fixed job income; For the Months’ worth of part-time job income; It is the serial number corresponding to different months, and its value is ; is the total number of months in a unit of time, and the value is a positive integer; Based on continuous working years and number of career changes Calculating job stability scores , the formula based on is:

[0049] It should be noted that The principle is: when the continuous working years If it is less than 10 years, select the continuous working years The value is used as the working years score. If the number of years of service is greater than or equal to 10, 10 is selected as the service experience score. and number of career changes Two factors to get a job stability score Continuous working years The longer the job tenure, the higher the score; the more stable the job, the higher the job stability score. The higher the number of career changes The fewer the number, the more stable the job, and the job stability score The higher.

[0050] Stability score by industry type and occupational stability score Calculating Occupational Type Score , the formula based on is: =

[0051] Among them, the industry type stability score For the Stability score of each industry type; is the serial number corresponding to different industry types, and the value is a positive integer; occupational stability score For the The stability score of the occupational nature; is the serial number corresponding to different occupational natures, and its value is a positive integer; Score stability for industry types The weight coefficient is 0.4 to 0.6, and the stability score is based on the industry type. Score for occupation type Determine the importance of Score for job stability The weight coefficient is 0.4 to 0.6, and the stability score is based on the occupational nature. Score for occupation type The importance of + =1; Based on income stability score , job stability score and occupation type score , calculate the income stability index , the formula based on is:

[0052] It should be noted that the income stability index Used to measure an individual's financial situation. Income stability score The higher the score, the better the individual's financial situation and the more stable the income. The higher the job stability score The higher the score, the better the individual's financial situation and the more stable the income. The higher the score. The higher the score, the better the individual's financial situation and the more stable the income. The higher.

[0053] in, Score income stability The weight coefficient is 0.2 to 0.5, based on the income stability score. Income stability index Determine the importance of Score job stability The weight coefficient is 0.3 to 0.5, based on the job stability score. Income stability index Determine the importance of Score for career type The weight coefficient is 0.2 to 0.5, and the score is based on the occupation type. Income stability index The importance of + + =1.

[0054] Step 202: Calculate consumption index The method is: Consumption behavior data includes personal monthly consumption amount , Consumption Category Amount and total amount of consumption .

[0055] It should be noted that the monthly personal consumption amount and total amount of consumption Obtained by querying bank card statements and third-party payment platform records. Consumption category amount By providing rich data from bank bills and third-party payment platform records, third-party payment platforms such as Alipay, WeChat Pay, JD Pay, and Cloud QuickPass can help individuals understand their consumption habits and financial status in detail. By viewing the merchant name, transaction description, and other information of the consumption, the consumption category and amount can be more accurately determined, thereby conducting effective financial planning and management. For example, through bank bills, you can clearly see the amount, date, and merchant name of each consumption, which is very helpful for tracking large-scale consumption and daily expenses. Third-party payment platforms such as Alipay and WeChat Pay have become important channels for personal consumption. These platforms record users' online and offline payment information, including transaction descriptions, amounts, and times. Through these records, users can understand the transaction data of individuals on multiple e-commerce platforms, physical stores, service providers, etc., especially obtaining e-commerce shopping platforms such as Taobao, JD.com, Pinduoduo, or platforms that can provide shopping such as Douyin and Dewu.

[0056] Consumption categories include: daily necessities, clothing and accessories, housing-related, transportation, education and learning, healthcare, communications and social networking, financial services, etc.

[0057] Based on monthly consumption , Monthly fixed job income and monthly part-time job income Calculate consumption ratio , the formula based on is:

[0058] It should be noted that this formula calculates the average of the proportion of consumption amount to income amount to obtain the consumption ratio. .

[0059] Among them, the consumption ratio The value range is 0 to 1.

[0060] According to consumption ratio Calculate consumption ratio score , based on the following criteria:

[0061] It should be noted that when the consumption ratio 0.3 to 0.6 is considered the most reasonable range, and the consumption ratio score is is 10. When the consumption ratio 0.2-0.3 or 0.6-0.8 is considered to be a reasonable range, and the consumption ratio score is is 5. When the consumption ratio When it is less than 0.2 and greater than 0.8, it is considered to be a relatively unreasonable range. is 1.

[0062] Amount by consumption category and total amount of consumption Calculating consumption diversity indicators , the formula based on is:

[0063] It should be noted that the operating principle of this formula is: In an individual's total consumption, The proportion of a consumption category reflects the resource allocation of consumers in this consumption category. The logarithmic function The role of A nonlinear transformation is performed to make the consumption diversity index It is more sensitive to the uneven distribution of consumption categories. By summing all consumption categories and adding a negative sign, we get the consumption diversity index. .

[0064] in, For the The amount of consumption in each consumption category; is the serial number corresponding to different consumption categories, and its value is ; is the total number of different consumption categories, which is a positive integer.

[0065] According to the consumption diversity index Calculating consumption diversity scores , based on the following criteria:

[0066] It should be noted that in actual consumption scenarios, the number of consumption categories is limited, generally speaking, consumption diversity indicators The value of .

[0067] Score based on consumption ratio and consumption diversity score Calculate consumption index , the formula based on is:

[0068] It should be noted that this formula calculates the consumption ratio score and consumption diversity score The average value of consumption index Consumption indicators Used to measure the rationality of personal consumption, consumption indicators The higher it is, the more rational the consumption is.

[0069] Step 203: Calculate credit indicators The method is: Credit history data includes the total number of personal credit repayments , Number of overdue payments and repayment amount .

[0070] It should be noted that the total number of personal loan repayments Refers to the number of times a borrower repays a loan to a lending institution in accordance with the contract in a personal loan business, and the number of overdue repayments. It refers to the number of times that the borrower fails to repay the principal and interest of the loan in full as agreed in the contract within the prescribed repayment period. It refers to the total amount of funds repaid by the borrower to the lending institution in the credit business; Total number of credit repayments , Number of overdue payments and repayment amount Such data can be obtained through bank statements, credit reports or records of lending institutions. Among them, the credit services of lending institutions include the credit services of many third-party online networks. For example, the credit services provided by common third-party online institutions such as Huabei, Jiebei and JD Baitiao are also part of personal credit business.

[0071] Based on the total number of personal loan repayments and number of overdue payments Calculate repayment stability , the formula based on is:

[0072] It should be noted that this formula calculates the number of overdue repayments. Percentage of total personal loan repayments The ratio of the loan repayment period to the loan repayment period is used to measure the stability of the borrower in the credit business. The higher the ratio, the greater the repayment stability. The lower the ratio, the more stable the repayment. The higher.

[0073] According to the repayment amount , Monthly fixed job income and monthly part-time job income Calculating solvency index , the formula based on is:

[0074] It should be noted that this formula calculates the repayment amount The higher the ratio, the higher the repayment ability index. The lower the ratio, the higher the repayment capacity. The higher.

[0075] Based on repayment stability and solvency indicators Calculating credit indicators , the formula based on is:

[0076] It should be noted that this formula takes into account the repayment stability in a weighted manner. and solvency indicators Credit Indicators Impact on credit indicators Used to measure the degree of personal credit risk. Repayment stability The higher the credit risk, the lower the personal credit risk. The higher the solvency index The higher the credit risk, the lower the personal credit risk. The higher.

[0077] in, For repayment stability The weight coefficient is 0.4 to 0.6, and the repayment stability is Credit Indicators Determine the extent of impact; The solvency indicator The weight coefficient is 0.4 to 0.6, and the repayment capacity index is Credit Indicators The extent of the impact is determined; and =1.

[0078] Step 204: Calculate utility indicators The method is: Utility bill payment data including number of days late for payment .

[0079] It should be noted that the number of days for delayed payment It refers to the total number of days that have passed from the due date of each utility fee to the actual payment date. It reflects the delay caused by the payer's failure to pay the relevant fees in time as required. Public utility fees include water fees, electricity fees, gas fees, social security fees, etc.

[0080] Calculation of public utility indicators based on public utility payment data , the formula based on is:

[0081] It should be noted that this formula obtains the public utility index by calculating the inverse ratio of the average number of days of delayed payment per month. . Public Utilities Indicators It is used to measure the reliability of individuals in public utilities. The longer the average delay in payment, the lower the individual's reliability in public utilities. The lower.

[0082] in, For the Months of delayed payment.

[0083] Step 205: Calculate insurance index The method is: Insurance record data including the number of times premiums were paid on time , the number of premiums payable , Insurance Diversity Score and insurance purchase continuity score .

[0084] It should be noted that the number of premium payments on time It refers to the cumulative number of times the insured has successfully completed premium payments within the payment period specified in the insurance contract. It is the number of times the insured should theoretically pay premiums, calculated based on the payment cycle and insurance period of the insurance contract, and obtained through the insurance company's system records, insurance contracts or payment receipts.

[0085] Insurance Diversity Score It is used to measure the variety of insurance products purchased by the insured, which reflects the insured's diversification in risk management and comprehensive protection awareness. The method to obtain is: check all the insurance products purchased by the individual, determine the insurance category to which each product belongs, insurance categories include health insurance, property insurance and accidental injury insurance, etc., and then count the number of different insurance types. When the number of insurance types is 1, the insurance diversity score When the number of insurance types is 2 to 3, the insurance diversity score is When the number of insurance types is greater than 3, the insurance diversity score is is 10.

[0086] Insurance Purchase Continuity Score Used to assess the consistency of the insured's continued purchase of insurance over a period of time. It reflects the insured's long-term insurance planning awareness and continuous demand for insurance protection. Insurance Purchase Continuity Score The method of obtaining is: by consulting the insurance contract, determine the effective year of the insurance contract And the year of purchase , according to the effective year of the insurance contract And the year of purchase Calculating Insurance Purchase Continuity Score : 1 0。

[0087] Calculate insurance indicators based on insurance record data , the formula based on is:

[0088] It should be noted that this formula calculates the insurance diversity score and insurance diversity score The sum of the premiums and multiply it by the number of premiums paid on time Number of premiums payable The ratio of Insurance Indicators Used to measure personal insurance risk and the number of times premiums are paid on time Number of premiums payable The higher the proportion, the lower the personal insurance risk. The higher the insurance diversity score The higher it is, the lower the personal insurance risk is. The higher the insurance diversity score The higher it is, the lower the personal insurance risk is. The higher.

[0089] Step 206: Calculate judicial indicators The method is: Judicial records data includes the number of cases involving individuals involved in financial disputes , Number of successful cases involving economic disputes , Economic Crime Severity Score and the crime decay time coefficient .

[0090] It should be noted that the number of cases involving individuals in economic disputes It refers to the total number of economic-related dispute cases in which an individual is a party. It reflects the individual's situation in handling economic affairs and the legal risks he faces. It is obtained through the China Judgments Online or the court litigation service hall.

[0091] Number of successful cases involving economic disputes It refers to the number of cases in which the court ultimately ruled in favor of all or part of the individual's litigation requests among all economic dispute cases in which the individual was involved. It reflects the individual's success rate in legal proceedings and is obtained through the China Judgments Online or the court litigation service hall.

[0092] Economic Crime Severity Score The method of obtaining is: collecting the penalty period corresponding to the individual crime type ,when At 1 year, the economic crime severity score for 10. When When the economic crime severity score for 20. When When the economic crime severity score for 30. When When the economic crime severity score for 40.

[0093] Crime decay time coefficient The method of obtaining is: collecting the time since the individual crime .when The crime decay time coefficient is 0.5. When the economic crime severity score is 0.7. When the economic crime severity score is 0.9.

[0094] According to the number of cases involving economic disputes and the number of cases involving economic disputes won Calculating case indicators , the formula based on is:

[0095] It should be noted that this formula is based on the number of successful cases involving economic disputes. The number of cases involving economic disputes The proportion of cases obtained . Case indicators Used to measure the risk level of an individual in economic cases. Number of successful cases involving economic disputes The number of cases involving economic disputes The higher the proportion, the lower the risk level of the individual in economic cases. The higher.

[0096] Score based on severity of economic crime and the crime decay time coefficient Calculating crime indicators , the formula based on is:

[0097] It should be noted that the economic crime severity score of this formula and the crime decay time coefficient Multiply to get the crime index Crime Indicators Used to measure an individual's risk of committing economic crime. Economic Crime Severity Score and the crime decay time coefficient The higher the value, the lower the risk of personal economic crime. The higher.

[0098] According to case indicators and crime indicators Calculating judicial indicators , the formula based on is: +

[0099] It should be noted that this formula takes into account the case indicators and crime indicators Judicial Indicators Judicial indicators Used to measure the level of risk an individual poses to the judicial system. The higher the value, the lower the individual's judicial risk. The higher the crime index The higher the value, the lower the individual's judicial risk. The higher.

[0100] Combined with the contents of step 201 to step 207: By income stability score , job stability score and occupation type score Calculating the income stability index , which helps to understand the individual's economic foundation; score based on consumption ratio and consumption diversity score Calculate consumption index , can measure whether an individual's consumption habits are reasonable; according to the repayment stability ratio and solvency indicators Calculating credit indicators , which can reflect the individual's credit risk level and help financial institutions to reasonably allocate credit resources; calculate public utility indicators based on public utility payment data , which can improve the comprehensiveness of credit assessment and help improve the credit system; calculate insurance indicators based on insurance record data , which can quantify individual insurance risk situations; calculate judicial indicators based on judicial record data , can complement other indicators to make the credit evaluation dimension more complete.

[0101] Step 3: Income stability indicator , consumption indicators , credit indicators , public utility indicators , Insurance Indicators and judicial indicators Perform standardization preprocessing and calculate the probability of good credit ; Preset credit probability threshold set and credit score threshold; Based on good credit probability , credit probability threshold set and credit score threshold set to calculate personal credit score ; Preset credit rating threshold set, based on personal credit score The credit rating is divided into credit ratings according to a set of credit rating thresholds.

[0102] Step 301: Calculate the probability of good credit The method is: The income stability index , consumption indicators , credit indicators , public utility indicators , Insurance Indicators and judicial indicators Input the logistic regression model for preprocessing, and calculate the probability of good credit based on the preprocessed indicators , the formula based on is:

[0103] It should be noted that the preprocessing is a preprocessing method for data standardization, which obtains the standardized data by calculating the difference between the original data indicator and the mean value of the indicator data and dividing it by the variance of the indicator data.

[0104] in, is the intercept; Standard income stability indicator The characteristic coefficient of Standard consumption index The characteristic coefficient of Standard credit indicators The characteristic coefficient of Standard utility indicators The characteristic coefficient of Standard insurance index The characteristic coefficient of Standard judicial indicators Characteristic coefficient of; standard income stability index Income stability indicator Parameter values ​​after preprocessing; standard consumption indicators For consumption indicators Preprocessed parameter values; standard credit indicators Credit Indicator Preprocessed parameter values; standard utility indicators Public utility indicators Preprocessed parameter values; standard insurance indicators For insurance indicators Preprocessed parameter values; standard judicial indicators For judicial indicators The parameter value after preprocessing. , , , , , and Determined by maximum likelihood estimation method.

[0105] Step 302: The method of classifying credit ratings is: The credit probability threshold set includes the credit probability low threshold and credit probability high threshold .

[0106] It should be noted that the credit probability low threshold and credit probability high threshold The method for determining is: collect a large number of credit data samples, perform statistical analysis of the collected data, and calculate the mean and standard deviation of the data. Calculate the value of the mean minus two times the standard deviation as the credit probability low threshold Calculate the mean plus two times the standard deviation as the high credit probability threshold Reference data.

[0107] Credit score threshold set includes low credit score threshold and high credit score threshold .

[0108] It should be noted that the credit score low threshold and credit score thresholds The method of determining the credit score is to collect and analyze a large amount of historical data. When the data presents a normal distribution, the mean and standard deviation of the data are calculated. The reference value is the mean minus the standard deviation. Credit score high threshold The reference value is the mean plus the standard deviation. When the data is skewed, the median and the third quartile are calculated, and the credit score low threshold is Reference median setting, credit score high threshold Refer to the third quartile setting.

[0109] Based on the probability of good credit , credit probability threshold set and credit score threshold set to calculate personal credit score The method is: When 0 Calculate personal credit score The method is:

[0110] It should be noted that the operating principle of this formula is: when 0 When personal credit score Starting from 0, as the probability of good credit increases The increase in credit score increases in a linear manner .in The probability of good credit exist Normalize within the interval.

[0111] when Calculate personal credit score The method is:

[0112] It should be noted that the operating principle of this formula is: when When personal credit score from Start with good credit probability The increase in credit score in a new linear way , Indicates the growth range of credit score within this interval, The probability of good credit exist Normalize within the interval.

[0113] when Calculate personal credit score The method is:

[0114] It should be noted that the operating principle of this formula is: when When personal credit score from Start with good credit probability Increases in linear fashion to the highest credit score , Indicates the growth range of credit score within this interval, The probability of good credit exist Normalize within the interval.

[0115] The credit rating threshold set includes low credit rating Threshold and credit rating high threshold ; It should be noted that low credit rating Threshold and credit rating high threshold The determination method is as follows: financial institutions collect a large amount of customer information, use the solution of the present invention to evaluate personal credit scores, and draw a curve of default rate versus credit score based on the corresponding default records. Observe the default rate curve and find the point where the default rate changes significantly. When the credit score is lower than a certain value, the default rate begins to rise sharply, and the credit rating is low. The threshold can be set with reference to this value. When the credit score is higher than a certain value, the default rate remains at a very low level, and the credit rating high threshold You can refer to this value for setting.

[0116] Based on personal credit score The credit rating threshold set is divided into the following standards:

[0117] Among them, A-level credit is a high credit rating, B-level credit is a medium credit rating, and C-level credit is a low credit rating.

[0118] Combined with the contents of step 301 to step 302: The income stability index , consumption indicators , credit indicators , public utility indicators , Insurance Indicators and judicial indicators Perform standardization preprocessing and calculate the probability of good credit , which can more comprehensively reflect an individual's credit status. , credit probability threshold set and credit score threshold set to calculate personal credit score , which helps to quantify personal credit status and more carefully reflect the differences in personal credit, while solving the problem of the reduced effectiveness of personal credit scores over time. The division of credit ratings based on a set of credit rating thresholds is beneficial for financial institutions to conduct risk management and resource allocation.

[0119] On the other hand, the present invention also discloses a credit data management system for multi-source information, which is used to implement the above-mentioned credit data management method for multi-source information, including: Data collection module, used to collect personal income stability data, consumption behavior data, credit history data, public utility payment data, insurance record data and judicial record data; Indicator calculation module, used to calculate income stability scores based on personal income stability data , job stability score and occupation type score ; and further calculate the income stability index ; Calculate consumption ratio based on consumption behavior data and personal income stability data , according to the consumption ratio Calculate consumption ratio score ; Calculate consumption diversity indicators based on consumption behavior data , according to the consumption diversity index Calculating consumption diversity scores ; Score based on consumption ratio and consumption diversity score Calculate consumption index ; Calculate repayment stability based on credit history data ; Calculate repayment capacity indicators based on credit history data and personal income stability data ; Based on repayment stability and solvency indicators Calculating credit indicators ; Calculation of public utility indicators based on public utility payment data ; Calculate insurance indicators based on insurance record data ; Calculating case indicators based on judicial record data and crime indicators ; and further calculate judicial indicators ; Credit rating module, used to convert income stability indicators , consumption indicators , credit indicators , public utility indicators , Insurance Indicators and judicial indicators Perform preprocessing and calculate the probability of good credit ; Preset credit probability threshold set and credit score threshold; Based on good credit probability , credit probability threshold set and credit score threshold set to calculate personal credit score ; Preset credit rating threshold set, based on personal credit score Credit ratings are divided according to credit rating thresholds.

[0120] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. A person of ordinary skill in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented in electronic hardware or in combination with 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.

[0121] 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.

[0122] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the 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.

Claims

1. A credit data management method for multi-source information, characterized by: The following steps are involved: Collect personal income stability data, consumer behavior data, credit history data, utility payment data, insurance record data, and judicial record data; Calculate income stability score based on individual income stability data , job stability score and occupation type score ; and further calculate the income stability index ; Calculate consumption ratio based on consumption behavior data and personal income stability data , according to the consumption ratio Calculate consumption ratio score ; Calculate consumption diversity indicators based on consumption behavior data , according to the consumption diversity index Calculating consumption diversity scores ; Score based on consumption ratio and consumption diversity score Calculate consumption index ; Calculate repayment stability based on credit history data ; Calculate repayment capacity indicators based on credit history data and personal income stability data ; Based on repayment stability and solvency indicators Calculating credit indicators ; Calculation of public utility indicators based on public utility payment data ; Calculate insurance indicators based on insurance record data ; Calculating case indicators based on judicial record data and crime indicators ; And further calculate the judicial index ; The income stability index , consumption indicators , credit indicators , public utility indicators , Insurance Indicators and judicial indicators Perform preprocessing and calculate the probability of good credit ; Preset credit probability threshold set and credit score threshold; based on good credit probability , credit probability threshold set and credit score threshold set to calculate personal credit score ; A set of preset credit rating thresholds, based on personal credit scores Credit ratings are divided according to credit rating thresholds.

2. A credit data management method for multi-source information according to claim 1, characterized in that: Calculating the income stability index The method is: Income stability data includes monthly fixed job income value , Monthly part-time job income , Continuous working years , Number of career changes , Industry type stability score and occupational stability score ; Based on the monthly fixed income and monthly part-time job income Calculating income stability score , the formula based on is: ； in, For the Months of fixed job income; For the Months’ worth of part-time job income; It is the serial number corresponding to different months, and its value is ; is the total number of months in a unit of time, and the value is a positive integer; Based on continuous working years and number of career changes Calculating job stability scores , the formula based on is: ； Stability score by industry type and occupational stability score Calculating Occupational Type Score , the formula based on is: = ； Among them, the industry type stability score For the Stability scores for each industry type; is the serial number corresponding to different industry types, and the value is a positive integer; occupational stability score For the The stability score of the occupational nature; is the serial number corresponding to different occupational natures, and its value is a positive integer; Score stability for industry types The weight coefficient is between 0.4 and 0.6; Score for job stability The weight coefficient is between 0.4 and 0.6; and + =1; Based on income stability score , job stability score and occupation type score , calculate the income stability index , the formula based on is: ； in, Score income stability The weight coefficient is between 0.2 and 0.5; Score job stability The weight coefficient is 0.3 to 0.5; Score for career type The weight coefficient is between 0.2 and 0.5; and + + =1.

3. A credit data management method for multi-source information according to claim 2, characterized in that: Calculate consumption index The method is: Consumption behavior data includes personal monthly consumption amount , Consumption Category Amount and total amount of consumption ; Based on monthly consumption , Monthly fixed job income and monthly part-time job income Calculate consumption ratio , the formula based on is: ； According to consumption ratio Calculate consumption ratio score , based on the following criteria: ； Amount by consumption category and total amount of consumption Calculating consumption diversity indicators , the formula based on is: ； in, For the The amount of consumption in each consumption category; is the serial number corresponding to different consumption categories, and its value is ; is the total number of different consumption categories, which is a positive integer; According to the consumption diversity index Calculating consumption diversity scores , based on the following criteria: ； Score based on consumption ratio and consumption diversity score Calculate consumption index , the formula based on is: 。 4. The credit data management method for multi-source information according to claim 3, characterized in that: Calculating credit indicators The method is: Credit history data includes the total number of personal credit repayments , Number of overdue payments and repayment amount ; Based on the total number of personal loan repayments and number of overdue payments Calculate repayment stability , the formula based on is: ； According to the repayment amount , Monthly fixed job income and monthly part-time job income Calculating solvency index , the formula based on is: ； Based on repayment stability and solvency indicators Calculating credit indicators , the formula based on is: ； in, For repayment stability The weight coefficient is between 0.4 and 0.6; The solvency indicator The weight coefficient is between 0.4 and 0.6, and =1.

5. The credit data management method for multi-source information according to claim 4, characterized in that: Calculating utility indicators The method is: Utility bill payment data including number of days late for payment ; Calculation of public utility indicators based on public utility payment data , the formula based on is: ； in, For the Months of delayed payment.

6. A credit data management method for multi-source information according to claim 5, characterized in that: Calculating insurance indicators The method is: Insurance record data including the number of times premiums were paid on time , the number of premiums payable , Insurance Diversity Score and insurance purchase continuity score ; Calculate insurance indicators based on insurance record data , the formula based on is: 。 7. A credit data management method for multi-source information according to claim 6, characterized in that: Calculating judicial indicators The method is: Judicial records data includes the number of cases involving individuals involved in financial disputes , Number of successful cases involving economic disputes , Economic Crime Severity Score and the crime decay time coefficient ; According to the number of cases involving economic disputes and the number of cases involving economic disputes won Calculating case indicators , the formula based on is: ； Score based on severity of economic crime and the crime decay time coefficient Calculating crime indicators , the formula based on is: ； According to case indicators and crime indicators Calculating judicial indicators , the formula based on is: + 。 8. The credit data management method for multi-source information according to claim 7, characterized in that: Calculate the probability of good credit The method is: The income stability index , consumption indicators , credit indicators , public utility indicators , Insurance Indicators and judicial indicators Input the logistic regression model for preprocessing, and calculate the probability of good credit based on the preprocessed indicators , the formula based on is: ； in, is the intercept; Standard income stability indicator The characteristic coefficient of Standard consumption index The characteristic coefficient of Standard credit indicators The characteristic coefficient of Standard utility indicators The characteristic coefficient of Standard insurance index The characteristic coefficient of Standard judicial indicators Characteristic coefficient of; standard income stability index Income stability indicator Parameter values ​​after preprocessing; standard consumption indicators For consumption indicators Preprocessed parameter values; standard credit indicators Credit Indicator Preprocessed parameter values; standard utility indicators Public utility indicators Preprocessed parameter values; standard insurance indicators For insurance indicators Preprocessed parameter values; standard judicial indicators For judicial indicators The parameter value after preprocessing.

9. The credit data management method for multi-source information according to claim 8, characterized in that: The credit rating method is as follows: The credit probability threshold set includes the credit probability low threshold and credit probability high threshold ; Credit score threshold set includes low credit score threshold and high credit score threshold ; Based on the probability of good credit , credit probability threshold set and credit score threshold set to calculate personal credit score The method is: When 0 Calculate personal credit score The method is: ； when Calculate personal credit score The method is: ； when Calculate personal credit score The method is: ； The credit rating threshold set includes low credit rating Threshold and credit rating high threshold ; Based on personal credit score The credit rating threshold set is divided into the following standards: ； Among them, A-level credit is a high credit rating, B-level credit is a medium credit rating, and C-level credit is a low credit rating.

10. A credit data management system for multi-source information, characterized by: include: Data collection module, used to collect personal income stability data, consumption behavior data, credit history data, public utility payment data, insurance record data and judicial record data; Indicator calculation module, used to calculate income stability scores based on personal income stability data , job stability score and occupation type score ; and further calculate the income stability index ; Calculate consumption ratio based on consumption behavior data and personal income stability data , according to the consumption ratio Calculate consumption ratio score ; Calculate consumption diversity indicators based on consumption behavior data , according to the consumption diversity index Calculating consumption diversity scores ; Score based on consumption ratio and consumption diversity score Calculate consumption index ; Calculate repayment stability based on credit history data ; Calculate repayment capacity indicators based on credit history data and personal income stability data ; Based on repayment stability and solvency indicators Calculating credit indicators ; Calculation of public utility indicators based on public utility payment data ; Calculate insurance indicators based on insurance record data ; Calculating case indicators based on judicial record data and crime indicators ; And further calculate the judicial index ; Credit rating module, used to convert income stability indicators , consumption indicators , credit indicators , public utility indicators , Insurance Indicators and judicial indicators Perform preprocessing and calculate the probability of good credit ; Preset credit probability threshold set and credit score threshold; based on good credit probability , credit probability threshold set and credit score threshold set to calculate personal credit score ; A set of preset credit rating thresholds, based on personal credit scores Credit ratings are divided according to credit rating thresholds.

Images