CN116777597A - Financial risk assessment method, device, storage medium and computer equipment - Google Patents
Financial risk assessment method, device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN116777597A CN116777597A CN202310728351.3A CN202310728351A CN116777597A CN 116777597 A CN116777597 A CN 116777597A CN 202310728351 A CN202310728351 A CN 202310728351A CN 116777597 A CN116777597 A CN 116777597A
- Authority
- CN
- China
- Prior art keywords
- data
- risk assessment
- model
- service data
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012502 risk assessment Methods 0.000 title claims abstract description 209
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000011156 evaluation Methods 0.000 claims abstract description 65
- 238000012545 processing Methods 0.000 claims abstract description 60
- 238000012216 screening Methods 0.000 claims abstract description 14
- 230000006399 behavior Effects 0.000 claims description 33
- 238000013210 evaluation model Methods 0.000 claims description 29
- 238000012549 training Methods 0.000 claims description 15
- 238000010801 machine learning Methods 0.000 claims description 12
- 238000012360 testing method Methods 0.000 claims description 9
- 238000012795 verification Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 239000006185 dispersion Substances 0.000 claims description 7
- 238000007619 statistical method Methods 0.000 claims description 7
- 238000010219 correlation analysis Methods 0.000 claims description 6
- 238000012821 model calculation Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 abstract description 21
- 230000008569 process Effects 0.000 description 14
- 238000004891 communication Methods 0.000 description 7
- 238000003066 decision tree Methods 0.000 description 4
- 238000012163 sequencing technique Methods 0.000 description 4
- 239000000243 solution Substances 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 238000000556 factor analysis Methods 0.000 description 3
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000012089 stop solution Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Software Systems (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of financial risk prediction evaluation, and provides a financial risk evaluation method, a device, a storage medium and computer equipment, wherein the method comprises the following steps: the risk assessment method comprises the steps of receiving a risk assessment request of a business object, wherein the risk assessment request carries basic information and behavior data of the business object, combining the basic information and the behavior data to obtain business data of the business object, performing redundancy processing on the business data, extracting feature data of the business data after the redundancy processing, respectively inputting the feature data into a plurality of preset risk assessment models to obtain corresponding assessment results, and finally screening out a target risk assessment model from the plurality of risk assessment models based on the assessment results, and outputting the assessment results corresponding to the target risk assessment model as business object risk assessment results. The method can improve the effectiveness and the singleness of the input data, and improve the accuracy of the risk assessment result while improving the calculation efficiency.
Description
Technical Field
The application relates to the technical field of financial risk prediction evaluation, in particular to a financial risk evaluation method, a financial risk evaluation device, a financial risk prediction evaluation storage medium and a financial risk prediction evaluation computer device.
Background
Along with the rapid development of the current financial field, related financial data also grows exponentially, and related industries such as banks, insurance and the like need to timely predict and evaluate financial risks so as to achieve the purpose of risk reduction.
In the existing process of predicting and evaluating financial risks, different tools are required to be continuously switched to perform data processing, statistical analysis, result output and other related works on financial data, the output of the predicted and evaluated results cannot be completed in one step, meanwhile, the existing tools calculate the data based on the traditional statistical method, and the accuracy of the outputted predicted and evaluated results is low.
Disclosure of Invention
In view of the above, the present application provides a financial risk assessment method, a device, a storage medium and a computer apparatus, which are mainly aimed at solving the technical problems that the existing financial risk assessment method needs to use different tools to complete the data processing work of each stage, cannot output results in one step and the accuracy of the output results is low.
According to a first aspect of the present invention there is provided a financial risk assessment method comprising:
receiving a risk assessment request of a business object, wherein the risk assessment request carries basic information and behavior data of the business object;
combining the basic information and the behavior data to obtain service data of the service object, and performing redundancy processing on the service data;
extracting feature data of the service data after the redundancy processing, and respectively inputting the feature data into a plurality of preset risk assessment models to obtain an assessment result corresponding to each risk assessment model;
and screening a target risk assessment model from a plurality of risk assessment models based on the assessment results, and outputting an assessment result corresponding to the target risk assessment model as a risk assessment result of the business object.
According to a second aspect of the present invention, there is provided a financial risk assessment apparatus comprising:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for receiving a risk assessment request of a business object, and the risk assessment request carries basic information and behavior data of the business object;
The data processing module is used for merging the basic information and the behavior data to obtain service data of the service object and carrying out redundancy processing on the service data;
the model calculation module is used for extracting the characteristic data of the service data after the redundancy processing, and respectively inputting the characteristic data into a plurality of preset risk assessment models to obtain an assessment result corresponding to each risk assessment model;
and the result output module is used for screening out a target risk assessment model from the multiple risk assessment models based on the assessment results, and outputting an assessment result corresponding to the target risk assessment model as a risk assessment result of the business object.
According to a third aspect of the present invention, there is provided a storage medium having stored thereon a computer program which when executed by a processor implements the financial risk assessment method described above.
According to a fourth aspect of the present invention there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the financial risk assessment method as described above when executing the program.
The application provides a financial risk assessment method, a device, a storage medium and computer equipment, which firstly receive a risk assessment request of a business object, wherein the risk assessment request carries basic information and behavior data of the business object, secondly merge the basic information and the behavior data to obtain business data of the business object, carry out redundancy processing on the business data, then extract characteristic data of the business data after the redundancy processing, respectively input the characteristic data into a plurality of preset risk assessment models to obtain an assessment result corresponding to each risk assessment model, and finally screen out a target risk assessment model from the plurality of risk assessment models based on the assessment result, and output the assessment result corresponding to the target risk assessment model as the risk assessment result of the business object. The method provides a complete flow solution from data acquisition, data processing, modeling calculation and result output for financial risk assessment, does not need to frequently switch tools in each link, improves calculation efficiency, performs redundant processing on service data in the data processing process, ensures validity and singleness of input service data, inputs characteristic data into a plurality of risk assessment models, and performs screening and output based on assessment results output by each risk assessment model, thereby improving accuracy of risk assessment results. The method improves the effectiveness and the singleness of the input business data, and further improves the accuracy of the final output result on the basis of improving the overall calculation efficiency of risk prediction.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the application and do not constitute a limitation on the application. In the drawings:
FIG. 1 is a schematic flow chart of a financial risk assessment provided by an embodiment of the present application;
FIG. 2 is a schematic flow chart of a financial risk assessment provided by an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating a financial risk assessment apparatus according to an embodiment of the present application;
FIG. 4 is a schematic diagram illustrating a structure of a financial risk assessment apparatus according to an embodiment of the present application;
fig. 5 shows a schematic device structure of a computer device according to an embodiment of the present application.
Detailed Description
Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the application to those skilled in the art.
The embodiment of the application provides a financial risk assessment method, as shown in fig. 1, which comprises the following steps:
101. and receiving a risk assessment request of the business object, wherein the risk assessment request carries basic information and behavior data of the business object.
The financial risk is a risk related to the financial field, whether a financial market, a financial institution, a financial product or a financial customer generates a risk, and the consequences caused by the risk can cause a series of chain reactions in the industry, even threaten the overall stable operation of the financial system, and disturb the social and economic order. The technical field of the application is to predict and evaluate financial risks, discover possible risks of business objects in time and avoid serious consequences.
Specifically, the application is based on different kinds or forms of data input by different business objects, can be applied to various financial field industries such as classified pricing prediction of insurance products, anti-fraud prediction of insurance claims, bank credit risk prediction and the like, has wide application scenes, needs to conduct data import after receiving a risk assessment request, and particularly exists in the form of a data table.
In this embodiment, the data is imported in various implementation forms, for example, the client basic information table is directly imported, and the items such as the tag name, the field type, the field length and the like in the client basic information table can be edited and can be manually modified; the name of the data table and the data in the data table can be directly input through newly creating the data table, and then the contents in the data table are edited through manually adding or deleting the data rows in the data table, so that a complete customer basic information table is finally formed. Meanwhile, before data is imported, a database can be newly built and named so as to permanently store the data file generated in the risk assessment process, so that the data file can be conveniently and retrospectively checked later; the generated data files can be directly stored in the temporary database according to the requirements, and when the whole risk assessment flow is ended or restarted, the data files in the temporary database can be directly deleted, so that the occupation of storage space is reduced.
102. And combining the basic information and the behavior data to obtain service data of the service object, and performing redundancy processing on the service data.
Specifically, the basic information and the behavior data carried in the risk assessment request are relatively independent data information, so that after the process of importing the data is completed, the basic information and the behavior data are required to be combined to obtain the behavior data corresponding to each item of data in the basic information, the data obtained after the data combination is completed are the business data of the business object, and the business data can accurately express the behavior data contained in the basic information of each item of data in the business object.
In this embodiment, since the initial data is derived from the risk assessment request of the service object in the initial data importing process, the data cannot be screened and processed before or during the data importing process, after the data matching is completed to obtain the service data of the service object, the service data is first subjected to redundancy processing, and the unreasonable, non-applicable range and repeated data existing in the service data are deleted, so as to ensure the singleness and validity of the service data, and lay a foundation for the accurate result output in the subsequent data processing.
103. And extracting feature data of the service data after the redundancy processing, and respectively inputting the feature data into a plurality of preset risk assessment models to obtain an assessment result corresponding to each risk assessment model.
Specifically, the risk assessment model is a mathematical structure expressed in a mathematical language, generally or approximately, for characteristics or quantity dependencies of a system of things. In the application, the risk assessment model is used for carrying out assessment prediction on risks by calculating the input characteristic data, and a conventional risk assessment model is selected.
In this embodiment, after redundancy processing is performed on service data to ensure the singleness and accuracy of the service data, feature data of the service data is obtained, where the feature data is used to represent diversity, variability, distribution and relevance of all data in the service data, the feature data is input into a plurality of different preset risk assessment models, and assessment results in the different risk assessment models are obtained, so that the risk assessment models to be selected are determined by comparing subsequent assessment results. The multiple risk assessment models are adopted for calculation, so that multiple different assessment results can be obtained, errors caused by calculation by adopting a single risk assessment model are effectively avoided, and accuracy of result output can be improved.
104. Based on the evaluation results, a target risk evaluation model is screened out from the multiple risk evaluation models, and the evaluation result corresponding to the target risk evaluation model is output as the risk evaluation result of the business object.
In this embodiment, the screening process of the target risk assessment model is specifically performed by judging and screening the obtained assessment results of all the risk assessment models. The specific judgment standard can be used for selecting a risk assessment model corresponding to an assessment result which is in a preset range as a target risk assessment model by setting the preset range, and outputting the assessment result obtained by calculation as a risk assessment result of a business object; similarly, the target risk assessment model can be screened by comparing the assessment results output among all the risk assessment models according to a preset judgment standard. According to the application, after calculation is performed by utilizing a plurality of risk assessment models, the assessment results are further judged to obtain the most accurate risk assessment model, so that the assessment result which is the most approximate to the actual situation is obtained as the risk assessment result, and the accuracy of overall prediction assessment is improved.
The application provides a financial risk assessment method, a device, a storage medium and computer equipment, which are characterized in that firstly, a risk assessment request of a business object is received, the risk assessment request carries basic information and behavior data of the business object, secondly, the basic information and the behavior data are combined to obtain business data of the business object, the business data are subjected to redundancy processing, then, feature data of the business data subjected to the redundancy processing are acquired, the feature data are respectively input into a plurality of preset risk assessment models to obtain an assessment result corresponding to each risk assessment model, finally, a target risk assessment model is selected from the plurality of risk assessment models based on the assessment result, and the assessment result corresponding to the target risk assessment model is output as the risk assessment result of the business object. The method provides a complete flow solution from data acquisition, data processing, modeling calculation and result output for financial risk assessment, does not need to frequently switch tools in each link, improves calculation efficiency, performs redundant processing on service data in the data processing process, ensures validity and singleness of input service data, inputs feature data into a plurality of preset risk assessment models for calculation, screens and outputs based on assessment results output by each risk assessment model, and improves accuracy of risk assessment results. The method improves the effectiveness of the input business data, and further improves the accuracy of the final output result on the basis of improving the overall calculation efficiency of risk prediction.
The embodiment of the application also provides a financial risk assessment method, as shown in fig. 2, which comprises the following steps:
201. and receiving a risk assessment request of the business object, wherein the risk assessment request carries basic information and behavior data of the business object.
In the embodiment of the application, firstly, based on the application scene in the financial industry where the application is located, the risk assessment request of the business object in the application scene is received, the application scene and the business scene range where the application is applicable are wide, then the data is imported based on the risk assessment request, the specific process of data import is consistent with the step 101, and redundant description is omitted here.
202. And combining the basic information and the behavior data to obtain the business data of the business object.
Specifically, all primary key fields in basic information and a plurality of parameter items associated with each primary key field are firstly obtained, then each parameter item is combined with each variable item in behavior data one by one to obtain service data corresponding to the primary key fields, and finally all primary key fields in the basic information and the service data corresponding to each primary key field are integrated to obtain service data of a service object.
In the embodiment of the application, the basic information comprises a plurality of main key fields, each main key field is correspondingly associated with a plurality of parameter items, the behavior data comprises variable items, and the parameter items corresponding to each main key field and the variable items are combined one by one, so that the business data of the business object can be finally obtained. Taking bank credit risk prediction as an example, behavior data is presented in the form of a violation record table, a customer ID is used as a primary key field in basic information, each customer ID is associated with parameters such as age, housing, month income, credit card number, working life, nationality and the like, each parameter is combined with whether the violation variable item in the violation record table, and finally service data of a service object is obtained and presented in the form of a credit service information table.
203. And carrying out redundancy processing on the service data.
Wherein the business data comprises at least one sub-data, and each sub-data comprises a plurality of data index items.
Specifically, a data index item is selected from a plurality of data index items as a sorting index, all sub-data in the service data are sorted based on a preset priority order of the sorting index, and finally all the sub-data are traversed.
In the embodiment of the application, because some unreasonable, unnecessary or repeated data exist in the service data, deletion is needed to ensure the singleness and the effectiveness of the data, the data in the service data are sequenced first for conveniently carrying out redundancy on the data, and the screening is convenient. Specifically, taking prediction of risk of a credit service of a bank as an example, the obtained service data is presented in a data table manner and comprises a plurality of pieces of sub-data, each piece of sub-data is used for recording a plurality of data index items such as a customer ID, an age, a service life, a month income and the like. The sorting index may be implemented by adding an additional data column, for example, adding a working age data index item in a data table of service data, where a specific value in the working age data index item is obtained by subtracting a working age from an age of a corresponding customer, and then sorting the data based on a preset priority order of the working ages, specifically, after sorting the data based on the working ages, deleting the data with the working ages less than 18 years directly to ensure the rationality of the data. The sequencing mode provided by the application has great flexibility.
In the embodiment of the application, after the service data is sequenced, redundant processing is required to be performed on the data, based on preset conditions, sub data can be identified to be repeated when the sub data has a plurality of identical data index items, deletion is required to be performed to ensure the singleness of the data, for example, when three variables of client ID, age and working age in the plurality of sub data are all identical, the plurality of sub data are identified to be repeated, and based on the sequencing result, only the sub data positioned in the first order is required to be reserved, and the rest repeated sub data are directly deleted, so that the whole process of the service data redundant processing is finally completed.
204. And extracting the characteristic data of the service data after the redundancy processing.
Specifically, firstly, carrying out statistical analysis on service data to obtain frequency, concentration, dispersion and distribution characteristics of the service data, and then carrying out correlation analysis on the service data based on preset parameters to obtain correlation among a plurality of data index items in the service data, wherein the preset parameters comprise: and finally integrating the frequency, concentration, dispersion, distribution characteristics of the service data and the correlation among a plurality of data index items in the service data to obtain the characteristic data of the service data.
In the embodiment of the application, the statistical analysis of the business data after the redundancy processing refers to describing the data characteristics by adopting modes such as a table or a numerical form summarization, and the like, in the process of predicting the credit risk of the bank, the credit business data with the age of less than 30 years old is processed, and the frequency, concentration, dispersion and distribution characteristic results of the business data are obtained by calculating and analyzing the data index items such as the age, month income, working age, default and the like in the business data, and the number, average value, standard deviation, minimum value, 25% fraction, median, 75% fraction, maximum value, mode, extremely poor, quartile interval, variation coefficient, deflection, kurtosis, null value rate and the like of each data index item.
And the correlation analysis is to analyze two or more data index items with correlation in the data so as to measure the correlation degree of the two data index items, wherein the preset coefficients adopted by the application comprise at least one parameter of Pearson coefficient, spearman coefficient, KMO test parameter, bartlett sphere test parameter and P-value parameter. Specifically, in the process of processing credit service data with the age of less than 30 years, aiming at data index items such as age, month income, service life, default or the like in the service data, the correlation between the data is displayed through a Pearson coefficient and a Spearman coefficient, wherein the Pearson coefficient is the ratio of the product of covariance and standard deviation between every two data, the Spearman coefficient is the Pearson coefficient between every two ordered data, the coefficient value is between-1 and 1, the value is close to-1 and represents negative correlation, the value is close to-1 and represents positive correlation, and the value is close to 0 and represents no correlation. And when the square sum of the simple correlation coefficients among all the data is far greater than the square sum of the partial correlation coefficients, the KMO value is more suitable for factor analysis, and when the square sum of the simple correlation coefficients among all the data is close to 0, the KMO value is more suitable for factor analysis, which means that the weaker the correlation among the data, and the original variable is less suitable for factor analysis. The Bartlett sphere test is also a test method for verifying whether the data are independent; p-value is a significance test, meaning that the result is more significant when the calculated P value is < 0.05. The user can adopt different calculation and analysis means to obtain a correlation analysis result according to the requirements, and integrate the correlation analysis result with the result after statistical analysis to obtain characteristic data of service data, so as to lay a foundation for subsequent modeling and screen out fields capable of being used for modeling.
205. And carrying out grouping processing and visual display on the service data.
Specifically, firstly, selecting a data index item from a plurality of data index items in service data as a grouping index, secondly, grouping the service data based on a preset grouping rule corresponding to the grouping index to obtain a plurality of service data groups, and then, responding to a chart generation instruction, displaying a chart generation page, wherein the chart generation page comprises a plurality of chart templates, responding to the selection instruction of the chart templates, displaying the selected chart templates in the chart generation page, and finally, responding to the dragging operation of the data index item, adding the dragged data index item in each service data group to each coordinate axis of the selected chart template, generating a target chart and displaying.
In the embodiment of the application, the data volume of the service data is huge, so that the service data is classified, on one hand, the processing volume of the data can be reduced, and on the other hand, a user can acquire the data processing results under different conditions according to the requirements. The application classifies the service data according to certain rules and logic, namely, carries out factor classification processing on the service data, specifically selects data index items from the service data as grouping indexes, and groups the service data based on the preset grouping rules of the grouping indexes. The grouping mode supported by the application is divided into three types, namely manual grouping, namely grouping is carried out completely according to rules preset by a user, original grouping is carried out, namely factors before classification are copied to the classified factors according to enumeration classification, automatic grouping is carried out, and classified factors are automatically generated according to a classification regression tree model. Still take bank credit risk prediction as an example, age data index items in business data are grouped by an automatic grouping mode to generate a plurality of grouping results of 20 years old or less, 21-25 years old, 26-30 years old, 31-35 years old, 35-40 years old and the like, a user is dissatisfied with the automatic grouping results, can switch to manual grouping to carry out merging or splitting adjustment, and can also take variables such as month income, credit card number, working life and the like as grouping indexes to carry out grouping, and finally new variables such as month income grouping, credit card number grouping, working life grouping and the like are generated.
In the embodiment of the application, the visualized chart generated by grouped business data can be displayed, a plurality of chart templates with different types are arranged in an icon generation page, the chart templates comprise a combination of a histogram and a line graph, the histogram, a pie chart, a scatter chart, a Q-Q chart and the like, after responding to a chart generation instruction and a selection instruction of the chart template, the chart templates are displayed, then responding to a dragging instruction of a data index item, respectively dragging a plurality of data index items in a business data group to an X axis, a Y axis or other coordinate axes according to the attribute of the chart template, and finally generating the visualized chart. The method is particularly applied to bank credit risk prediction, and can be used for dragging an age data index item into an X-axis, dragging an average value of month income and an average value of default quantity into a Y-axis to generate a combination of a histogram and a line graph, and dragging an month income index item into the X-axis and dragging an average value of default quantity into the Y-axis to generate a pie chart. The business data is converted into the visual chart, so that the works such as bank credit business monitoring, strategic decision and the like can be intuitively served in a multi-dimensional manner, the function of a data monitoring large screen is realized, the chart generation process can be automatically generated by staff through operations such as clicking, dragging and the like, the meaning of each coordinate axis of the chart is automatically determined, and finally, the generated chart meets the requirements of users and has stronger flexibility and compatibility.
206. Training risk assessment models, and respectively inputting characteristic data into a plurality of risk assessment models to obtain an assessment result corresponding to each risk assessment model.
Specifically, the training method of the risk assessment model comprises the following steps: firstly, collecting a plurality of sample service data, constructing an initial risk assessment model, dividing the plurality of sample service data into a training set and a verification set according to a preset proportion, then training the initial risk assessment model based on the sample service data in the training set to obtain model parameters of the initial risk assessment model, wherein the input parameters of the initial risk assessment model are characteristic data of the sample service data, the output parameters of the initial risk assessment model are assessment result labels of the sample service data, and finally, based on the sample service data in the verification set, the model parameters of the initial risk assessment model are adjusted to obtain the risk assessment model, wherein the risk assessment model comprises a generalized linear model and a machine learning model.
In the embodiment of the application, the feature data are input into the risk assessment model to calculate to obtain the assessment results corresponding to different risk assessment models, and the risk assessment model is required to be trained before the calculation, so that the feature data of the business data are randomly sampled to generate a training set and a verification set, specifically, the sampling ratio is 8:2, then an initial risk assessment model is built, the training set is utilized to train the initial risk assessment model, model parameters are determined, and the verification set is utilized to verify the initial model to adjust the model parameters, so that the preset risk assessment model is finally obtained.
The application adopts a risk assessment model specifically to comprise a generalized linear model and a machine learning model, wherein the generalized linear model establishes a relation between a mathematical expected value of a target variable and an independent variable of a linear combination through a link function, the relation is specifically applied to bank credit risk prediction, an assessment result is an expected value of the default probability, the higher the expected value is in a range of 0% -100%, the higher the expected value is, the higher the default probability is, and the evaluation value of the prediction model is, the lower the default probability is, the higher the evaluation value is, the input characteristic data is age, month income, credit card number, working life and the like, and the default probabilities of different types of users are calculated and predicted through binomial distribution, and meanwhile, the evaluation value of the risk assessment model is calculated; the machine learning model applies XGBoost machine learning algorithm, minimizes the residual error between the predicted result of the decision tree and the true value by constructing the decision tree, and iterates the model by repeating the steps, when the iteration number reaches the preset upper limit or the residual error is not reduced, a strong classifier with a plurality of decision trees can be obtained, so that the offence probability and the predicted model evaluation value are classified and predicted, the machine learning model is particularly applied to bank credit risk prediction, the age, month income, credit card number and working life in the input characteristic data are respectively 30-40 years old, 10000-20000 yuan, 1 and 5-10 years old clients are branches in the decision tree, and the machine learning model forms a group of offence probability and predicted model evaluation value evaluation results for the branches.
Meanwhile, model parameters, a model fitting information table, a variable grouping information table and a variable importance information table can be output through the risk assessment model, and key parameter and check value results set by the model, grouping results of the variables and contribution degrees of the respective variables to the model assessment results are respectively displayed.
207. Based on the evaluation results, a target risk evaluation model is screened out from the multiple risk evaluation models, and the evaluation result corresponding to the target risk evaluation model is output as the risk evaluation result of the business object.
Specifically, judging whether an evaluation result corresponding to each risk evaluation model meets a preset condition one by one, when a unique evaluation result meets the preset condition, selecting the risk evaluation model corresponding to the evaluation result as a target risk evaluation model, adjusting model parameters of the target risk evaluation model based on the evaluation result, and outputting the evaluation result as a risk evaluation result of a business object; when a plurality of evaluation results meet a preset condition, calculating an average value of the plurality of evaluation results as a risk evaluation result of the business object, and adjusting model parameters of a risk evaluation model corresponding to each evaluation result based on the evaluation result; when no evaluation result meets the preset condition, selecting a risk evaluation model corresponding to the evaluation result closest to the preset condition as a target risk evaluation model, adjusting model parameters of the target risk evaluation model based on the evaluation result, and outputting the evaluation result as a risk evaluation result of the business object.
In the embodiment of the application, after the evaluation results of a plurality of risk evaluation models are obtained, the target risk evaluation model needs to be screened based on the evaluation results. Still taking bank credit risk prediction as an example, the risk assessment model adopts a generalized linear model and a machine learning model, the probability of violating is calculated based on the generalized linear model to be 4%, the risk score is 59.97 points, the probability of violating is calculated based on the machine learning model to be 4%, the risk score is 60.87 points, after the assessment result is obtained, the result closest to the actual situation can be screened according to a preset condition, for example, when the preset condition is that the risk score is higher than 60 minutes, the assessment result of the machine learning model is selected as the risk assessment result of the business object; or when the risk score of the preset condition is not met, selecting a risk assessment model with higher risk score, namely still selecting an assessment result of the machine learning model as a risk assessment result of the business object; or when both meet the preset conditions, taking the average value between the two as a final evaluation result. Screening the target risk assessment model based on the assessment result, and adjusting model parameters of the target risk assessment model to ensure accuracy of the target risk assessment model, wherein the assessment result of the target risk assessment model is used as a risk assessment result of a final business object.
The method provided by the embodiment of the application comprises the steps of firstly receiving a risk assessment request of a business object, wherein the risk assessment request carries basic information and behavior data of the business object, then merging the basic information and the behavior data to obtain business data of the business object, performing redundancy processing on the business data, then extracting feature data of the business data after the redundancy processing, performing grouping processing on the business data, performing visual display, training a risk assessment model, respectively inputting the feature data into a plurality of risk assessment models for calculation to obtain an assessment result corresponding to each risk assessment model, and finally screening out a target risk assessment model from the plurality of risk assessment models based on the assessment result, and outputting the assessment result corresponding to the target risk assessment model as the risk assessment result of the business object.
According to the method, basic information and behavior data carried by a risk assessment request of a business object are combined to obtain the business data, redundancy processing is carried out to improve the accuracy of the business data, grouping processing is carried out on the business data to meet the use requirement of a user, visual display is carried out to intuitively monitor the data, characteristic data of a business data terminal are input into a plurality of risk assessment models to be calculated to obtain a plurality of assessment results, screening is carried out to obtain accurate assessment results, and the accuracy of the output risk assessment results is ensured. The method provides a one-stop solution for various business scenes in the financial industry, and improves the overall calculation efficiency of risk assessment.
Further, as a specific implementation of the method of fig. 1, an embodiment of the present application provides a financial risk assessment apparatus, as shown in fig. 3, where the apparatus includes: a data acquisition module 301, a data processing module 302, a model calculation module 303 and a result output module 304.
The data acquisition module 301 may be configured to receive a risk assessment request of a business object, where the risk assessment request carries basic information and behavior data of the business object;
the data processing module 302 is configured to combine the basic information and the behavior data to obtain service data of the service object, and perform redundancy processing on the service data;
the model calculation module 303 may be configured to obtain feature data of the service data after the redundancy processing, and input the feature data into a plurality of risk assessment models respectively to obtain an assessment result corresponding to each risk assessment model;
the result output module 304 may be configured to screen a target risk assessment model from the multiple risk assessment models based on the assessment results, and output an assessment result corresponding to the target risk assessment model as a risk assessment result of the business object.
In a specific application scenario, the data processing module 302 may be specifically configured to obtain all primary key fields in the basic information and a plurality of parameter items associated with each primary key field; combining each parameter item with each variable item in the behavior data one by one to obtain service data corresponding to each main key field; and integrating all the primary key fields in the basic information and the service data corresponding to each primary key field to obtain the service data of the service object.
In a specific application scenario, the data processing module 302 may be further configured to select a data index item from the plurality of data index items as the ranking index; sequencing all the sub-data in the service data based on a preset priority order of sequencing indexes; traversing all the sub-data, when a plurality of sub-data have at least two identical data index items, reserving the first order sub-data based on the ordering sequence of the sub-data, and removing all the sub-data except the first order sub-data.
In a specific application scenario, the model calculation module 303 may be configured to perform statistical analysis on the service data to obtain frequency, concentration, dispersion and distribution characteristics of the service data; carrying out correlation analysis on service data based on preset parameters to obtain the correlation degree among a plurality of data index items in the service data, wherein the preset parameters comprise: at least one of a Pearson coefficient, a Spearman coefficient, a KMO test parameter, a Bartlett sphere test parameter, or a P-value parameter; and integrating the frequency, the concentration, the dispersion, the distribution characteristics and the correlation among a plurality of data index items in the service data to obtain the characteristic data of the service data.
In a specific application scenario, as shown in fig. 4, the apparatus further includes a data display module 305, where the data display module 305 is specifically configured to select a data index item from a plurality of data index items in service data as a grouping index; grouping the service data based on a preset grouping rule corresponding to the grouping index to obtain a plurality of service data groups; displaying a chart generation page in response to the chart generation instruction, wherein the chart generation page comprises a plurality of chart templates, and displaying the selected chart templates in the icon generation page in response to the selection instruction of the chart templates; and responding to the dragging operation of the data index items, respectively and correspondingly adding the dragged data index items in each business data group to each coordinate axis of the selected chart template, and generating and displaying a target chart.
In a specific application scenario, the model calculation module 303 may be specifically configured to collect a plurality of sample service data, construct an initial risk assessment model, and divide the plurality of sample service data into a training set and a verification set according to a preset proportion; training an initial risk assessment model based on sample service data in a training set to obtain model parameters of the initial risk assessment model, wherein the input parameters of the initial risk assessment model are characteristic data of the sample service data, and the output parameters of the initial risk assessment model are assessment result labels of the sample service data; based on sample business data in the verification set, model parameters of the initial risk assessment model are adjusted to obtain a risk assessment model, wherein the risk assessment model comprises a generalized linear model and a machine learning model.
In a specific application scenario, the result output module 304 may be specifically configured to determine whether an evaluation result corresponding to each risk evaluation model meets a preset condition one by one; when the unique evaluation result meets the preset condition, selecting a risk evaluation model corresponding to the evaluation result as a target risk evaluation model, adjusting model parameters of the target risk evaluation model based on the evaluation result, and outputting the evaluation result as a risk evaluation result of the business object; when a plurality of evaluation results meet a preset condition, calculating an average value of the plurality of evaluation results as a risk evaluation result of the business object, and adjusting model parameters of a risk evaluation model corresponding to each evaluation result based on the evaluation result; when no evaluation result meets the preset condition, selecting a risk evaluation model corresponding to the evaluation result closest to the preset condition as a target risk evaluation model, adjusting model parameters of the target risk evaluation model based on the evaluation result, and outputting the evaluation result as a risk evaluation result of the business object.
It should be noted that, for other corresponding descriptions of each functional unit related to the financial risk assessment device provided in this embodiment, reference may be made to corresponding descriptions in fig. 1 and fig. 2, and details are not repeated here.
Based on the above method as shown in fig. 1, correspondingly, the present embodiment further provides a storage medium, on which a computer program is stored, which when executed by a processor, implements the above financial risk assessment method.
Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, where the software product to be identified may be stored in a non-volatile storage medium (may be a CD-ROM, a usb disk, a mobile hard disk, etc.), and includes several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to execute the method for evaluating financial risk of each implementation scenario of the present application.
Based on the methods shown in fig. 1 and fig. 2 and the embodiments of the financial risk assessment apparatus shown in fig. 3 and fig. 4, in order to achieve the above objects, referring to fig. 5, this embodiment further provides an entity apparatus for financial risk assessment, where the apparatus includes a communication bus, a processor, a memory, a communication interface, and may further include an input/output interface and a display device, where each functional unit may complete communication with each other through the bus. The memory stores a computer program, and the processor is configured to execute the program stored in the memory to perform the financial risk assessment method in the above embodiment.
Optionally, the physical device may further include a user interface, a network interface, a camera, radio Frequency (RF) circuitry, sensors, audio circuitry, WI-FI modules, and the like. The user interface may include a Display screen (Display), an input unit such as a Keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), etc.
It will be appreciated by those skilled in the art that the structure of the entity device for financial risk assessment provided in this embodiment is not limited to the entity device, and may include more or fewer components, or may be a combination of certain components, or may be a different arrangement of components.
The storage medium may also include an operating system, a network communication module. The operating system is a program for managing the entity equipment hardware and the software resources to be identified, and supports the operation of the information processing program and other software and/or programs to be identified. The network communication module is used for realizing communication among all components in the storage medium and communication with other hardware and software in the information processing entity equipment.
From the above description of the embodiments, it will be apparent to those skilled in the art that the present application may be implemented by means of software plus necessary general hardware platforms, or may be implemented by hardware. By applying the technical scheme of the application, firstly, a risk assessment request of a business object is received, the risk assessment request carries basic information and behavior data of the business object, secondly, the basic information and the behavior data are combined to obtain business data of the business object, redundancy processing is carried out on the business data, then, feature data of the business data after the redundancy processing are extracted, the feature data are respectively input into a plurality of preset risk assessment models for calculation, an assessment result corresponding to each risk assessment model is obtained, finally, a target risk assessment model is screened from the plurality of risk assessment models based on the assessment result, and the assessment result corresponding to the target risk assessment model is output as the risk assessment result of the business object. The method provides a complete flow solution from data acquisition, data processing, modeling calculation and result output for financial risk assessment, does not need to frequently switch tools in each link, improves calculation efficiency, performs redundant processing on service data in the data processing process, ensures validity and singleness of input service data, inputs feature data into a plurality of risk assessment models for calculation, and performs screening and output based on assessment results output by each risk assessment model, thereby improving accuracy of risk assessment results. The method improves the effectiveness and the singleness of the input business data, and further improves the accuracy of the final output result on the basis of improving the overall calculation efficiency of risk prediction.
Those skilled in the art will appreciate that the drawing is merely a schematic illustration of a preferred implementation scenario and that the modules or flows in the drawing are not necessarily required to practice the application. Those skilled in the art will appreciate that modules in an apparatus in an implementation scenario may be distributed in an apparatus in an implementation scenario according to an implementation scenario description, or that corresponding changes may be located in one or more apparatuses different from the implementation scenario. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above-mentioned inventive sequence numbers are merely for description and do not represent advantages or disadvantages of the implementation scenario. The foregoing disclosure is merely illustrative of some embodiments of the application, and the application is not limited thereto, as modifications may be made by those skilled in the art without departing from the scope of the application.
Claims (10)
1. A financial risk assessment method, the method comprising:
receiving a risk assessment request of a business object, wherein the risk assessment request carries basic information and behavior data of the business object;
combining the basic information and the behavior data to obtain service data of the service object, and performing redundancy processing on the service data;
Extracting feature data of the service data after redundancy processing, and respectively inputting the feature data into a plurality of preset risk assessment models to obtain an assessment result corresponding to each risk assessment model;
and screening a target risk assessment model from a plurality of risk assessment models based on the assessment results, and outputting an assessment result corresponding to the target risk assessment model as a risk assessment result of the business object.
2. The method of claim 1, wherein the merging the basic information and the behavior data to obtain the business data of the business object includes:
acquiring all main key fields in the basic information and a plurality of parameter items associated with each main key field;
combining each parameter item with each variable item in the behavior data one by one to obtain service data corresponding to each main key field;
and integrating all the primary key fields in the basic information and the service data corresponding to each primary key field to obtain the service data of the service object.
3. The method of claim 1, wherein the business data comprises at least one sub-data, each sub-data comprising a plurality of data index items; the redundant processing of the service data comprises the following steps:
Selecting one data index item from the plurality of data index items as a sorting index;
sorting all the sub-data in the service data based on a preset priority order of the sorting index;
traversing all the sub-data, when a plurality of the sub-data have at least two identical data index items, reserving first order sub-data based on the ordering sequence of the sub-data, and removing all other sub-data except the first order sub-data.
4. The method of claim 1, wherein the extracting feature data of the redundantly processed service data comprises:
carrying out statistical analysis on the service data to obtain the frequency, concentration, dispersion and distribution characteristics of the service data;
performing correlation analysis on the service data based on preset parameters to obtain correlation among a plurality of data index items in the service data, wherein the preset parameters comprise: at least one parameter selected from the group consisting of Pearson coefficient, spearman coefficient, KMO test parameter, bartlett sphere test parameter, and P-value test parameter;
and integrating the frequency, the concentration, the dispersion, the distribution characteristics and the correlation among a plurality of data index items in the service data to obtain the characteristic data of the service data.
5. The method according to claim 1, wherein after said extracting the feature data of the redundancy-processed service data, the method further comprises:
selecting a data index item from a plurality of data index items of the service data as a grouping index;
grouping the service data based on a preset grouping rule corresponding to the grouping index to obtain a plurality of service data groups;
responding to a chart generation instruction, and displaying a chart generation page, wherein a plurality of chart templates are displayed in the chart generation page;
responding to a selection instruction of the chart template, and displaying the selected chart template in the icon generating page;
and responding to the dragging operation of the data index items, respectively and correspondingly adding the dragged data index items in each business data set to each coordinate axis of the selected chart template, and generating and displaying a target chart.
6. The method of claim 1, wherein the training method of the risk assessment model comprises:
collecting a plurality of sample service data, constructing an initial risk assessment model, and dividing the plurality of sample service data into a training set and a verification set according to a preset proportion;
Training the initial risk assessment model based on sample service data in the training set to obtain model parameters of the initial risk assessment model, wherein the input parameters of the initial risk assessment model are characteristic data of the sample service data, and the output parameters of the initial risk assessment model are assessment result labels of the sample service data;
and adjusting model parameters of the initial risk assessment model based on the sample business data in the verification set to obtain the risk assessment model, wherein the risk assessment model comprises a generalized linear model and a machine learning model.
7. The method according to claim 1, wherein the step of screening a target risk assessment model from a plurality of risk assessment models based on the assessment results, and outputting an assessment result corresponding to the target risk assessment model as a risk assessment result of the business object includes:
judging whether the evaluation result corresponding to each risk evaluation model meets a preset condition one by one;
when only the evaluation result meets the preset condition, selecting the risk evaluation model corresponding to the evaluation result as a target risk evaluation model, adjusting model parameters of the target risk evaluation model based on the evaluation result, and outputting the evaluation result as a risk evaluation result of the business object;
When a plurality of evaluation results meet the preset conditions, calculating an average value of the plurality of evaluation results as a risk evaluation result of the business object, and adjusting model parameters of the risk evaluation model corresponding to each evaluation result based on the evaluation result;
when the assessment result does not exist and meets the preset condition, selecting the risk assessment model corresponding to the assessment result closest to the preset condition as a target risk assessment model, adjusting model parameters of the target risk assessment model based on the assessment result, and outputting the assessment result as a risk assessment result of the business object.
8. A financial risk assessment device, the device comprising:
the system comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for receiving a risk assessment request of a business object, and the risk assessment request carries basic information and behavior data of the business object;
the data processing module is used for merging the basic information and the behavior data to obtain service data of the service object and carrying out redundancy processing on the service data;
the model calculation module is used for extracting the characteristic data of the service data after the redundancy processing, and respectively inputting the characteristic data into a plurality of preset risk assessment models to obtain an assessment result corresponding to each risk assessment model;
And the result output module is used for screening out a target risk assessment model from the multiple risk assessment models based on the assessment results, and outputting an assessment result corresponding to the target risk assessment model as a risk assessment result of the business object.
9. A storage medium having stored thereon a computer program, which when executed by a processor, implements the steps of the method of any of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the computer program when executed by the processor implements the steps of the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310728351.3A CN116777597A (en) | 2023-06-19 | 2023-06-19 | Financial risk assessment method, device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310728351.3A CN116777597A (en) | 2023-06-19 | 2023-06-19 | Financial risk assessment method, device, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116777597A true CN116777597A (en) | 2023-09-19 |
Family
ID=87990793
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310728351.3A Pending CN116777597A (en) | 2023-06-19 | 2023-06-19 | Financial risk assessment method, device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116777597A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090112649A1 (en) * | 2007-10-30 | 2009-04-30 | Intuit Inc. | Method and system for assessing financial risk associated with a business entity |
| CN109993412A (en) * | 2019-03-01 | 2019-07-09 | 百融金融信息服务股份有限公司 | The construction method and device of risk evaluation model, storage medium, computer equipment |
| CN110599335A (en) * | 2019-09-27 | 2019-12-20 | 北京淇瑀信息科技有限公司 | User financial risk assessment method and device based on multiple models |
| CN111507822A (en) * | 2020-04-13 | 2020-08-07 | 深圳微众信用科技股份有限公司 | Enterprise risk assessment method based on feature engineering |
| CN113298373A (en) * | 2021-05-20 | 2021-08-24 | 中国建设银行股份有限公司 | Financial risk assessment method, device, storage medium and equipment |
| CN114092216A (en) * | 2021-09-22 | 2022-02-25 | 金蝶征信有限公司 | Enterprise credit rating method, apparatus, computer device and storage medium |
| CN115794833A (en) * | 2022-12-19 | 2023-03-14 | 深圳前海微众银行股份有限公司 | Data processing method, server and computer storage medium |
| CN116128627A (en) * | 2022-12-21 | 2023-05-16 | 中信银行股份有限公司 | Risk prediction method, risk prediction device, electronic equipment and storage medium |
-
2023
- 2023-06-19 CN CN202310728351.3A patent/CN116777597A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090112649A1 (en) * | 2007-10-30 | 2009-04-30 | Intuit Inc. | Method and system for assessing financial risk associated with a business entity |
| CN109993412A (en) * | 2019-03-01 | 2019-07-09 | 百融金融信息服务股份有限公司 | The construction method and device of risk evaluation model, storage medium, computer equipment |
| CN110599335A (en) * | 2019-09-27 | 2019-12-20 | 北京淇瑀信息科技有限公司 | User financial risk assessment method and device based on multiple models |
| CN111507822A (en) * | 2020-04-13 | 2020-08-07 | 深圳微众信用科技股份有限公司 | Enterprise risk assessment method based on feature engineering |
| CN113298373A (en) * | 2021-05-20 | 2021-08-24 | 中国建设银行股份有限公司 | Financial risk assessment method, device, storage medium and equipment |
| CN114092216A (en) * | 2021-09-22 | 2022-02-25 | 金蝶征信有限公司 | Enterprise credit rating method, apparatus, computer device and storage medium |
| CN115794833A (en) * | 2022-12-19 | 2023-03-14 | 深圳前海微众银行股份有限公司 | Data processing method, server and computer storage medium |
| CN116128627A (en) * | 2022-12-21 | 2023-05-16 | 中信银行股份有限公司 | Risk prediction method, risk prediction device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108564286B (en) | Artificial intelligent financial wind-control credit assessment method and system based on big data credit investigation | |
| CN105718490A (en) | Method and device for updating classifying model | |
| CN110738527A (en) | feature importance ranking method, device, equipment and storage medium | |
| CN109711424B (en) | Behavior rule acquisition method, device and equipment based on decision tree | |
| CN110033284A (en) | Source of houses verification method, apparatus, equipment and storage medium | |
| CN114048436A (en) | Construction method and construction device for forecasting enterprise financial data model | |
| CN111738331A (en) | User classification method and device, computer-readable storage medium and electronic device | |
| CN112288455A (en) | Label generation method and device, computer readable storage medium and electronic equipment | |
| CN113919886A (en) | Data characteristic combination pricing method and system based on summer pril value and electronic equipment | |
| CN111199469A (en) | User payment model generation method and device and electronic equipment | |
| Deng | Towards objective benchmarking of electronic government: an inter‐country analysis | |
| CN111861521A (en) | Data processing method and device, computer readable medium and electronic equipment | |
| CN111210332A (en) | Method and device for generating post-loan management strategy and electronic equipment | |
| CN111582315A (en) | Sample data processing method and device and electronic equipment | |
| CN116911994B (en) | External trade risk early warning system | |
| CN114511022B (en) | Feature screening, behavior recognition model training and abnormal behavior recognition method and device | |
| CN116777597A (en) | Financial risk assessment method, device, storage medium and computer equipment | |
| CN112506930B (en) | Data insight system based on machine learning technology | |
| CN111489134B (en) | Method, device and equipment for constructing data model and computer readable storage medium | |
| CN114626940A (en) | Data analysis method and device and electronic equipment | |
| CN114092230A (en) | Data processing method and device, electronic equipment and computer readable medium | |
| CN114170000A (en) | Credit card user risk category identification method, device, computer equipment and medium | |
| CN113869973A (en) | Product recommendation method, product recommendation system, and computer-readable storage medium | |
| CN112529319A (en) | Grading method and device based on multi-dimensional features, computer equipment and storage medium | |
| US20200342302A1 (en) | Cognitive forecasting |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |