CN112508723B - Financial risk prediction method and device based on automatic preferential modeling and electronic equipment - Google Patents
Financial risk prediction method and device based on automatic preferential modeling and electronic equipment Download PDFInfo
- Publication number
- CN112508723B CN112508723B CN202110166439.1A CN202110166439A CN112508723B CN 112508723 B CN112508723 B CN 112508723B CN 202110166439 A CN202110166439 A CN 202110166439A CN 112508723 B CN112508723 B CN 112508723B
- Authority
- CN
- China
- Prior art keywords
- model
- data
- parameters
- financial
- user
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 113
- 238000011156 evaluation Methods 0.000 claims abstract description 30
- 238000012545 processing Methods 0.000 claims abstract description 27
- 230000000694 effects Effects 0.000 claims abstract description 23
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000012360 testing method Methods 0.000 claims abstract description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 39
- 230000008569 process Effects 0.000 claims description 24
- 238000012216 screening Methods 0.000 claims description 23
- 238000000605 extraction Methods 0.000 claims description 14
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000013468 resource allocation Methods 0.000 claims description 8
- 238000013209 evaluation strategy Methods 0.000 claims description 6
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 238000007726 management method Methods 0.000 description 4
- 230000003287 optical effect Effects 0.000 description 4
- 230000006399 behavior Effects 0.000 description 3
- 230000006872 improvement Effects 0.000 description 3
- 238000007792 addition Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013075 data extraction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000012821 model calculation Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 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
- G06Q40/08—Insurance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Finance (AREA)
- Accounting & Taxation (AREA)
- Entrepreneurship & Innovation (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- General Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Biomedical Technology (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Technology Law (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a financial risk prediction method and device based on automatic preferential modeling and electronic equipment. The method comprises the following steps: presetting a model configuration file, wherein the model configuration file comprises a model generation file for automatically generating each model; receiving user input, the user input comprising financial product time nodes and model generation parameters; performing matching processing, and determining a model generation file matched with the user input; generating a financial risk model set according to the matched model generation file, and automatically training each financial risk model; selecting a corresponding test data set, performing effect evaluation on each model in the financial risk model set, and automatically selecting an optimal financial risk model according to evaluation indexes; and predicting the financial risk of the new user by using the optimal financial risk model. The invention can automatically generate the model, improve the working efficiency of service personnel and optimize the modeling system.
Description
Technical Field
The invention relates to the field of computer information processing, in particular to a financial risk prediction method and device based on automatic preferential modeling and electronic equipment.
Background
Risk prediction is a quantification of risk and is a key technology for risk management. At present, risk prediction is generally carried out in a modeling mode, and the method mainly comprises the steps of data extraction, feature generation, feature selection, algorithm model generation, rationality evaluation and the like in the process of establishing a model.
In the prior art, the main purpose of financial risk prediction is how to distinguish good customers from bad customers, evaluate the risk situation of users, reduce the credit risk, and realize profit maximization. In addition, as the source channel of data becomes more and more abundant, so too is the data that can be used as a risk feature variable. However, many data such as user data and other related data are not considered to be changed due to time factors when in use, and thus, when model calculation is performed using the above data, the model calculation value is not accurate enough, and even the accuracy of risk assessment for some users is low. In addition, related business personnel are performing business analysis, and performing business tasks such as feature engineering, model development, evaluation, online, monitoring and the like, usually require a great deal of time for the related business personnel to realize. Therefore, there is still a great room for improvement in terms of automatic model generation, model precision improvement or model optimization, data extraction and the like.
Accordingly, there is a need to provide a more automated financial risk prediction method.
Disclosure of Invention
In order to automatically generate a model, further improve the working efficiency of business personnel and further optimize a modeling system, the invention provides a financial risk prediction method based on automatic preferential modeling, which comprises the following steps: presetting a model configuration file, wherein the model configuration file comprises a model generation file for automatically generating each model; receiving user input, the user input comprising financial product time nodes and model generation parameters; performing matching processing on the received user input and the model configuration file, and determining a model generation file matched with the user input; generating a financial risk model set according to the matched model generation file, and automatically training each financial risk model; selecting a corresponding test data set, performing effect evaluation on each model in the financial risk model set, and automatically selecting an optimal financial risk model according to evaluation indexes; and predicting the financial risk of the new user by using the optimal financial risk model.
Preferably, said determining a model generation file matching said user input comprises: identifying identification parameters in the user input, carrying out matching processing on the identification parameters and an identification information set, and determining a model generation file matched with the user input according to a first matching rule and a second matching rule, wherein the identification parameters comprise financial product time nodes, selection parameters and model generation parameters; the identification information set comprises a time node for representing the life cycle of the financial product, whether a model algorithm is selected, whether model parameter adjustment is performed, and whether model parameters are selected.
Preferably, the method further comprises: the first matching rule comprises judging whether the identification parameter in the user input has a resource request node, a resource grant node, a resource allocation node, a resource use node, a resource quota increasing node or a resource return node in a financial time node; the second matching rule comprises judging whether sample screening, a model algorithm, model parameters and parameter adjustment methods exist in page submission data of the user-editable page.
Preferably, the method further comprises: in the matching process, a user-editable page is provided for a user, wherein the user-editable page comprises a plurality of parameter selectable items, and the plurality of parameter selectable items comprise a sample screening method item, a model algorithm item, a model parameter input or increase and decrease item, a model parameter adjustment item and a corresponding adjustment method item.
Preferably, the method further comprises: and monitoring the user editable page, and updating the corresponding model generation file according to the monitored page submission data.
Preferably, the preset model configuration file includes: configuring a plurality of model generation files according to historical service data, wherein each model generation file comprises a sample screening and classifying strategy, and the sample screening and classifying strategy comprises a feature extraction rule and a pre-classified data set corresponding to a financial product time node; the feature extraction rule comprises time parameters, event parameters, risk parameters and financial performance data extracted according to the time parameters and/or the event parameters, wherein the time parameters comprise financial performance data between two adjacent financial time nodes, in a specific time period from each financial time node, in a specific time period before each financial product time node, in a specific selected time period, and in a specific time period, and the financial performance data comprises movable branch data, overdue data, default data and return data; the event parameters include whether a new user is judged, whether overdue data is present, whether default data is present, whether collect urging data is present, and whether a multi-head user is judged.
Preferably, the preset model configuration file includes: configuring a model algorithm and a parameter determination strategy, wherein the determination strategy comprises a model algorithm, parameter adjustment suggestions and parameter adjustment methods corresponding to the number of positive and negative samples of financial time nodes and historical data, so that a user can select whether to perform model parameter adjustment or not, and a parameter adjustment method is selected from a parameter adjustment method set; and/or configuring a model evaluation strategy, drawing an effect curve for each financial risk model according to evaluation indexes, and comparing model effects to automatically select an optimal financial risk model, wherein the evaluation indexes comprise accuracy, ROC indexes and AUC indexes.
Preferably, the model configuration file further includes an update file for updating each model generation file.
In addition, the invention also provides a financial risk prediction device based on automatic preferential modeling, which comprises: the setting module is used for presetting a model configuration file, wherein the model configuration file comprises a model generation file used for automatically generating each model; the receiving module is used for receiving user input, and the user input comprises a financial product time node and model generation parameters; the matching processing module is used for performing matching processing on the received user input and the model configuration file and determining a model generation file matched with the user input; the generation module generates a file according to the matched model, generates a financial risk model set and automatically trains each financial risk model; the evaluation module is used for selecting a corresponding test data set, evaluating the effect of each model in the financial risk model set and automatically selecting an optimal financial risk model according to an evaluation index; and the prediction module is used for predicting the financial risk of the new user by using the optimal financial risk model.
Preferably, the system further comprises an identification module, wherein the identification module is used for identifying identification parameters in the user input, carrying out matching processing on the identification parameters and an identification information set, and determining a model generation file matched with the user input according to a first matching rule and a second matching rule, wherein the identification parameters comprise financial product time nodes, selection parameters and model generation parameters; the identification information set comprises a time node for representing the life cycle of the financial product, whether a model algorithm is selected, whether model parameter adjustment is performed, and whether model parameters are selected.
Preferably, the method further comprises: the first matching rule comprises judging whether the identification parameter in the user input has a resource request node, a resource grant node, a resource allocation node, a resource use node, a resource quota increasing node or a resource return node in a financial time node; the second matching rule comprises judging whether sample screening, a model algorithm, model parameters and parameter adjustment methods exist in page submission data of the user-editable page.
Preferably, the method further comprises: in the matching process, a user-editable page is provided for a user, wherein the user-editable page comprises a plurality of parameter selectable items, and the plurality of parameter selectable items comprise a sample screening method item, a model algorithm item, a model parameter input or increase and decrease item, a model parameter adjustment item and a corresponding adjustment method item.
Preferably, the system further comprises a monitoring module, wherein the monitoring module is used for monitoring the user-editable page and updating the corresponding model generation file according to the monitored page submission data.
Preferably, the method further comprises: configuring a plurality of model generation files according to historical service data, wherein each model generation file comprises a sample screening and classifying strategy, and the sample screening and classifying strategy comprises a feature extraction rule and a pre-classified data set corresponding to a financial product time node; the feature extraction rule comprises time parameters, event parameters, risk parameters and financial performance data extracted according to the time parameters and/or the event parameters, wherein the time parameters comprise financial performance data between two adjacent financial time nodes, in a specific time period from each financial time node, in a specific time period before each financial product time node, in a specific selected time period, and in a specific time period, and the financial performance data comprises movable branch data, overdue data, default data and return data; the event parameters include whether a new user is judged, whether overdue data is present, whether default data is present, whether collect urging data is present, and whether a multi-head user is judged.
Preferably, the method further comprises: configuring a model algorithm and a parameter determination strategy, wherein the determination strategy comprises a model algorithm, parameter adjustment suggestions and parameter adjustment methods corresponding to the number of positive and negative samples of financial time nodes and historical data, so that a user can select whether to perform model parameter adjustment or not, and a parameter adjustment method is selected from a parameter adjustment method set; and/or configuring a model evaluation strategy, drawing an effect curve for each financial risk model according to evaluation indexes, and comparing model effects to automatically select an optimal financial risk model, wherein the evaluation indexes comprise accuracy, ROC indexes and AUC indexes.
Preferably, the model configuration file further includes an update file for updating each model generation file.
In addition, the invention also provides electronic equipment, wherein the electronic equipment comprises: a processor; and a memory storing computer executable instructions that, when executed, cause the processor to perform the financial risk prediction method of the present invention based on automated preferential modeling.
Furthermore, the invention also provides a computer readable storage medium, wherein the computer readable storage medium stores one or more programs, and the one or more programs, when executed by a processor, implement the financial risk prediction method based on automatic preferential modeling.
Advantageous effects
Compared with the prior art, the method can enable the modeling process to be more automatic and standardized, can efficiently produce the optimal model, can further simplify the modeling process, and can further optimize the modeling system; the corresponding data set is automatically selected, and an automatic training model is realized; the optimal financial risk model is automatically selected through the user input of the related business personnel, so that the time for the related business personnel to complete the related business tasks is greatly reduced, and the working efficiency of the business personnel is improved; the optimal financial risk model can be provided for different users, and the risk situation of the users can be predicted more accurately and automatically.
Drawings
In order to make the technical problems solved by the present invention, the technical means adopted and the technical effects achieved more clear, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted, however, that the drawings described below are merely illustrative of exemplary embodiments of the present invention and that other embodiments of the present invention may be derived from these drawings by those skilled in the art without undue effort.
FIG. 1 is a flowchart of an example of a financial risk prediction method based on automatic preferential modeling of embodiment 1 of the present invention.
Fig. 2 is a flowchart of another example of the financial risk prediction method based on automatic preferential modeling of embodiment 1 of the present invention.
Fig. 3 is a flowchart of still another example of the financial risk prediction method based on automatic preferential modeling of embodiment 1 of the present invention.
Fig. 4 is a schematic diagram of an example of an automatic preferential modeling-based financial risk prediction apparatus of embodiment 2 of the present invention.
Fig. 5 is a schematic diagram of another example of an automated preferential modeling-based financial risk prediction device of embodiment 2 of the present invention.
Fig. 6 is a schematic diagram of still another example of the financial risk prediction apparatus based on automatic preferential modeling of embodiment 2 of the present invention.
Fig. 7 is a block diagram of an exemplary embodiment of an electronic device according to the present invention.
Fig. 8 is a block diagram of an exemplary embodiment of a computer readable medium according to the present invention.
Detailed Description
Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments can be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art. The same reference numerals in the drawings denote the same or similar elements, components or portions, and thus a repetitive description thereof will be omitted.
The features, structures, characteristics or other details described in a particular embodiment do not exclude that may be combined in one or more other embodiments in a suitable manner, without departing from the technical idea of the invention.
In the description of specific embodiments, features, structures, characteristics, or other details described in the present invention are provided to enable one skilled in the art to fully understand the embodiments. However, it is not excluded that one skilled in the art may practice the present invention without one or more of the specific features, structures, characteristics, or other details.
The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various devices, elements, components or portions, this should not be limited by these terms. These words are used to distinguish one from the other. For example, a first device may also be referred to as a second device without departing from the spirit of the invention.
The term "and/or" and/or "includes all combinations of any of the associated listed items and one or more.
In view of the above problems, the present invention proposes a financial risk prediction method based on automatic preferential modeling. The method can enable the modeling process to be more automatic and standardized, can efficiently produce an optimal model, and can further optimize the modeling system, so that the working efficiency of business personnel can be further improved. The specific procedure of the method of the present invention will be described in detail below.
In the present invention, the resource refers to any available substance, information, and time, and the information resource includes a computing resource and various types of data resources. The data resources include various dedicated data in various fields. The innovation of the invention is how to use the information interaction technology between the server and the client to make the resource allocation process more automatic, efficient and reduce the labor cost. Therefore, the invention can be applied to risk prediction during distribution and return of various resources, not only to financial resources, but also to physical goods, water, electricity, meaningful data and the like. However, for convenience, the implementation of resource allocation is described in the present invention by taking financial data resources as an example, but those skilled in the art will appreciate that the present invention may also be used for risk prediction of other resources.
Example 1
In the following, embodiments of the financial risk prediction method based on automatic preferential modeling of the present invention will be described with reference to fig. 1 to 3.
FIG. 1 is a flow chart of an example of an automated preferential modeling-based financial risk prediction method of the present invention. As shown in fig. 1, the method includes the following steps.
Step S101, a model configuration file is preset, where the model configuration file includes a model generation file for automatically generating each model.
Step S102, receiving user input, wherein the user input comprises a financial product time node and model generation parameters.
And step S103, performing matching processing on the received user input and the model configuration file, and determining a model generation file matched with the user input.
Step S104, generating a financial risk model set according to the matched model generation file, and automatically training each financial risk model.
Step S105, selecting a corresponding test data set, evaluating the effect of each model in the financial risk model set, and automatically selecting an optimal financial risk model according to the evaluation index.
And step S106, predicting the financial risk of the new user by using the optimal financial risk model.
In this example, in an application scenario where a user performs resource usage on a financial service product or a financial management product, a profile is configured in a preset model according to business person input, for example, through an automated wind-controlled modeling system.
Specifically, the automatic wind control modeling system is connected with a plurality of clients, and different types of business personnel use the automatic wind control modeling system to perform file configuration, updating, other management or data processing and the like according to authority or business tasks.
For example, the system comprises a plurality of types of business personnel, wherein the first type of business personnel is a user for configuring and managing files according to business requirements and the like; the second class of service personnel is users for generating application according to the preset file model. However, the above description is only illustrative and not to be construed as limiting the invention. The following will describe in more detail the specific steps.
First, in step S101, a model profile including a model generation file for automatically generating each model is preset.
Specifically, the first class business personnel sets a model configuration file according to the historical business data, wherein the model configuration file comprises a plurality of model generation files. For example, a plurality of model generation files are configured for automated generation of an optimal model based on a first class of business personnel on a visualization interface provided by an automated wind-controlled modeling system.
Further, each model generation file includes determining a sample screening and classification strategy including feature extraction rules, pre-classified data sets corresponding to the financial product time nodes.
Preferably, the feature extraction rule includes a time parameter, an event parameter, a risk parameter, and extraction of parameters according to the time parameter, the event parameter, the risk parameter, and the like.
For example, the time parameters include financial performance data between two adjacent financial time nodes, including dynamic count data, overdue data, default data, and return data, within a specific time period from each financial time node, within a specific time period before each financial product time node, within a specific time period from a selection of a specific time period; the event parameters include whether a new user is judged, whether overdue data is present, whether default data is present, whether collect urging data is present, and whether a multi-head user is judged.
Specifically, in performing the pre-classification of the data set, for example, time parameters of over three days, five days, seven days, fifteen days, thirty days, and the like are defined, and resource return times of three days, six days, nine days, and the like are defined.
In this example, the historical service data of different service lines are subjected to sample screening according to the feature extraction rule, sample labels are defined, and sample pre-classification is performed. Thus, sample screening and classification strategies can be determined.
Further, a training data set, a test data set and the like corresponding to each model are established according to the sample data after sample screening and the sample data after classification.
For training data sets, sample data is segmented, for example, sample data between resource quota-granting nodes and resource-using nodes, and sample data for which the number of resource uses is greater than a specific number and reaches a specific number of resource returns, based on such nodes as resource quota-granting nodes, resource-using nodes, and resource return nodes.
For example, positive samples and negative samples are defined according to sample data in each segment after the segmentation, and labels are 0 and 1, wherein 1 represents samples with the user being more than Y, and 0 represents samples with the user resource return probability being less than Y, and Y values in each segment are different. In general, the higher the probability of return of the user's resources, the better the loan is to recover principal, the better the efficiency of use of funds, the lower the risk level of the property, and vice versa.
It should be noted that the foregoing is merely illustrative, and is not to be construed as limiting the invention, and in other examples, the overdue probability (or default probability) may be used to define positive and negative samples.
As another example, taking a resource usage node as an example, the training data set includes time characteristic data, event characteristic data, user resource usage behavior data, overdue probability (default probability or resource return probability) of a history user associated with the resource usage node within a specific time period including a time period from the resource quota granting node, a time period from the resource quota granting node to an occurrence time of a first resource usage behavior, a time period from the occurrence time of the first resource usage behavior, and the like.
Preferably, a determination strategy for configuring model algorithms and parameters is also included.
Specifically, the determining strategy includes a model algorithm, a parameter adjustment suggestion and a parameter adjustment method corresponding to the financial time node and the positive and negative sample number of the historical data, so that a user can select whether to perform model parameter adjustment or not, and a parameter adjustment method is selected from a parameter adjustment method set.
In another example, the corresponding model algorithm is selected based on the number of positive and negative samples of the sample data, the number of tagged sample data, the sample data density, and the like. For example, for sample data having a number of tagged sample data less than a minimum specific number, modeling calculations are performed using a characterization learning algorithm, such as CNN, RNN, or the like. For another example, an unsupervised self-learning algorithm is used for sample data without tags. For another example, for the case where the number of data for positive or negative samples is greater than a minimum specific number and less than a specific number, oversampling is performed to create a data set for model training. In other examples, one or a combination of two or more of logistic regression, random forest, GBDT, XGBoost algorithms may also be used.
In yet another example, the method further comprises configuring a model evaluation strategy, drawing an effect curve for each financial risk model according to evaluation indexes, and comparing model effects to automatically select an optimal financial risk model, wherein the evaluation indexes comprise accuracy, ROC indexes and AUC indexes.
Preferably, the model parameters of the multiple dimensions are input, for example using Cartesian product calculations, to generate the multiple models. Thus, a large variety of configuration files are obtained.
In yet another example, the model configuration file further includes an update file for updating each model generation file. For example, the model generation files are updated periodically according to the parameter change or the data volume change in the specific application and the evaluation result.
Therefore, through presetting the configuration file, a plurality of automatic processes can be realized to automatically select the optimized financial risk model, the modeling flow can be simplified, the time for modeling by the business personnel can be reduced, and the working efficiency of the business personnel can be improved.
The foregoing description is only illustrative of the preferred embodiments and is not to be construed as limiting the invention.
Next, in step S102, user input is received, the user input including a financial product time node, model generation parameters.
In this example, user input is received from a user, wherein the user is a second type of business person.
For example, during use of the automated wind-controlled modeling system by user a (i.e., a second class of business personnel), user input may be made on the use interface to complete the modeled business tasks.
In this example, the user input for user a includes a financial product time node, model generation parameters, and the like.
Specifically, further, the financial product time node includes a resource request node, a resource grant node, a resource allocation node, a resource use node, a resource increase/decrease limit node, a resource return node, and the like related to a financial service product or a financial management product.
In this example, a financial time node is used as an identification parameter for the matching process of the model profile.
Further, the model generation parameters include necessary influencing factors or index parameters for generating each model, such as minimum variance loss, sample data distribution parameters and the like.
The foregoing description is only illustrative of the preferred embodiments and is not to be construed as limiting the invention.
Next, in step S103, a matching process is performed with the model configuration file using the received user input, and a model generation file matching the user input is determined.
As shown in fig. 2, step S201 of identifying an identification parameter in the user input is also included.
In step S201, identification parameters in the user input are identified.
Specifically, identifying an identification parameter in user input of a current user, and performing matching processing on the identification parameter and an identification information set, wherein the identification information set comprises a time node used for representing a life cycle of a financial product, whether a model algorithm is selected, whether model parameter adjustment is performed, and whether model parameters are selected.
Preferably, determining a matching rule for the matching process is also included.
For example, the first matching rule and the second matching rule are automatically determined based on the identification parameters and the optional parameters generated by the model. However, the above description is only illustrative and not to be construed as limiting the invention.
Specifically, the first matching rule includes determining whether the identification parameter in the user input has a resource request node, a resource grant node, a resource allocation node, a resource usage node, a resource quota increasing node, or a resource return node in a financial time node. And the second matching rule comprises judging whether sample screening, a model algorithm, model parameters and parameter adjustment methods exist in page submission data of the user-editable page.
Further, according to the first matching rule and the second matching rule, determining a model generation file matched with the user input, wherein the identification parameters comprise financial product time nodes, selection parameters and model generation parameters.
Further, the identified identification parameters and the model configuration file are automatically subjected to matching processing, so that a corresponding model generation file can be obtained.
Therefore, according to the user input, the corresponding model generation file can be automatically matched, so that automation of the modeling process can be realized, and the modeling flow can be further simplified.
The foregoing description is only illustrative of the preferred embodiments and is not to be construed as limiting the invention.
Next, in step S104, a financial risk model set is generated from the matched model generation file, and each financial risk model is automatically trained.
For example, the model generation file 1 is matched, and a corresponding plurality of models (i.e., a financial risk model set) are generated from the model generation file 1.
Specifically, the training data set in step S101 is selected, and each financial risk model is automatically trained.
As shown in fig. 3, step S301 of providing the user with the user-editable page during the matching process is also included.
In step S301, during the matching process (i.e., during the matching process of the identification parameter of the user with the identification information set), the user (i.e., the second class service person) is provided with the user-editable page.
Specifically, the user-editable page includes a plurality of parameter selectable items including a sample screening method item, a model algorithm item, a model parameter input or increase/decrease item, a model parameter adjustment item, and a corresponding adjustment method item.
Further, user a may select one or more items of data from the plurality of parameter selectable items described above on the user-editable page and submit the page data by the ok button.
Preferably, the user-editable pages are monitored, and data is submitted according to the monitored pages to update the corresponding model generation files.
In an example, when it is monitored that the user selects the page data having the model parameter adjustment option, the model parameter adjustment is performed using the model evaluation policy configured in step S101.
Thereby, an automatic selection of the corresponding data set is achieved, and an automatic training model is achieved.
The foregoing description is only illustrative of the preferred embodiments and is not to be construed as limiting the invention. In other examples, the user (i.e., the second class of business people) may also be provided with user-editable pages at the time of the matching process or after determining the model generation file.
Next, in step S105, a corresponding test data set is selected, effect evaluation is performed on each model in the financial risk model set, and an optimal financial risk model is automatically selected according to the evaluation index.
In this example, automatically selecting an optimal model from a plurality of models is also included.
Specifically, a plurality of models are generated based on the matched model generation file, and corresponding test data sets are automatically selected according to each model.
Further, according to the model evaluation strategy configured in step S101, at least two evaluation indexes of the accuracy, ROC index, and AUC index are selected, an effect curve is drawn for each model, and model effects are compared to automatically select an optimal financial risk model.
In another example, the method further comprises recording a user input, an optimal financial risk model corresponding to the user input, and storing the user input, the optimal financial risk model corresponding to the user input, to a model database, wherein the model database uses financial product time nodes as indexes, and the model database is used for optimal model matching according to model input features.
Therefore, the optimal financial risk model is automatically selected through the user input of the relevant business personnel, so that the time for the relevant business personnel to complete the relevant business tasks is greatly reduced, and the working efficiency is improved.
The foregoing is illustrative only, and is not to be construed as limiting the present invention.
Next, in step S106, the financial risk of the new user is predicted using the optimal financial risk model.
Specifically, user data of a current user is acquired, and whether the user is a new user is judged.
Further, for example, the second class of service personnel extracts valid feature data from the user data of the new user.
In this example, the effective feature data is time feature data and risk feature data of the new user, and the effective feature data is used as an input feature of the model.
Since the extraction method of the effective feature data is the same as that of step S101, the description thereof is omitted.
In another example, the second business person, for example, enters the user data of the new user into the corresponding page, directly returning the optimal financial risk model corresponding to the user's characteristics and its calculated values.
In yet another example, for example, the first class business person inputs the user data of the new user into the effective feature extraction page, and automatically extracts the effective feature, and then performs optimal model matching with the effective feature as a model input feature, so as to automatically select an optimal financial risk model corresponding to the effective feature.
Further, the selected optimal financial risk model is used to calculate a financial predictor, which in this example is a predictor representing a quantified risk of the user, the predictor being a value between 0 and 1. For example, the financial risk prediction value is a default probability, a overdue probability, a resource return probability, or the like.
Therefore, the optimal financial risk model can be provided for different users, and the risk situation of the users can be predicted more accurately and automatically.
The foregoing description is only illustrative of the preferred embodiments and is not to be construed as limiting the invention.
Those skilled in the art will appreciate that all or part of the steps implementing the above-described embodiments are implemented as a program (computer program) executed by a computer data processing apparatus. The above-described method provided by the present invention can be implemented when the computer program is executed. Moreover, the computer program may be stored in a computer readable storage medium, which may be a readable storage medium such as a magnetic disk, an optical disk, a ROM, a RAM, or a storage array composed of a plurality of storage media, for example, a magnetic disk or a tape storage array. The storage medium is not limited to a centralized storage, but may be a distributed storage, such as cloud storage based on cloud computing.
Compared with the prior art, the method can enable the modeling process to be more automatic and standardized, can efficiently produce the optimal model, can further simplify the modeling process, and can further optimize the modeling system; the corresponding data set is automatically selected, and an automatic training model is realized; the optimal financial risk model is automatically selected through the user input of the related business personnel, so that the time for the related business personnel to complete the related business tasks is greatly reduced, and the working efficiency of the business personnel is improved; the optimal financial risk model can be provided for different users, and the risk situation of the users can be predicted more accurately and automatically.
Example 2
The following describes apparatus embodiments of the invention that may be used to perform method embodiments of the invention. Details described in the embodiments of the device according to the invention should be regarded as additions to the embodiments of the method described above; for details not disclosed in the embodiments of the device according to the invention, reference may be made to the above-described method embodiments.
Referring to fig. 4, 5 and 6, the present invention also provides a financial risk prediction apparatus 400 based on automatic preferential modeling, the financial risk prediction apparatus 400 comprising: a setting module 401, configured to preset a model configuration file, where the model configuration file includes a model generation file for automatically generating each model; a receiving module 402 for receiving user input, the user input comprising a financial product time node, model generation parameters; a matching processing module 403, configured to perform matching processing with the model configuration file using the received user input, and determine a model generation file that matches the user input; the generating module 404 generates a financial risk model set according to the matched model generating file, and automatically trains each financial risk model; the evaluation module 405 is configured to select a corresponding test data set, evaluate effects of each model in the financial risk model set, and automatically select an optimal financial risk model according to an evaluation index; a prediction module 406, configured to predict a financial risk of the new user using the optimal financial risk model.
As shown in fig. 5, the device further includes a recognition module 501, where the recognition module 501 is configured to recognize an identification parameter in the user input, perform matching processing on the identification parameter and an identification information set, and determine a model generation file matched with the user input according to a first matching rule and a second matching rule, where the identification parameter includes a financial product time node, a selection parameter, and a model generation parameter; the identification information set comprises a time node for representing the life cycle of the financial product, whether a model algorithm is selected, whether model parameter adjustment is performed, and whether model parameters are selected.
Preferably, the method further comprises: the first matching rule comprises judging whether the identification parameter in the user input has a resource request node, a resource grant node, a resource allocation node, a resource use node, a resource quota increasing node or a resource return node in a financial time node; the second matching rule comprises judging whether sample screening, a model algorithm, model parameters and parameter adjustment methods exist in page submission data of the user-editable page.
Preferably, the method further comprises: in the matching process, a user-editable page is provided for a user, wherein the user-editable page comprises a plurality of parameter selectable items, and the plurality of parameter selectable items comprise a sample screening method item, a model algorithm item, a model parameter input or increase and decrease item, a model parameter adjustment item and a corresponding adjustment method item.
As shown in fig. 6, the system further includes a monitoring module 601, where the monitoring module 601 is configured to monitor the user-editable page, and update a corresponding model generation file according to the monitored page submission data.
Preferably, the method further comprises: configuring a plurality of model generation files according to historical service data, wherein each model generation file comprises a sample screening and classifying strategy, and the sample screening and classifying strategy comprises a feature extraction rule and a pre-classified data set corresponding to a financial product time node; the feature extraction rule comprises time parameters, event parameters, risk parameters and financial performance data extracted according to the time parameters and/or the event parameters, wherein the time parameters comprise financial performance data between two adjacent financial time nodes, in a specific time period from each financial time node, in a specific time period before each financial product time node, in a specific selected time period, and in a specific time period, and the financial performance data comprises movable branch data, overdue data, default data and return data; the event parameters include whether a new user is judged, whether overdue data is present, whether default data is present, whether collect urging data is present, and whether a multi-head user is judged.
Preferably, the method further comprises: configuring a model algorithm and a parameter determination strategy, wherein the determination strategy comprises a model algorithm, parameter adjustment suggestions and parameter adjustment methods corresponding to the number of positive and negative samples of financial time nodes and historical data, so that a user can select whether to perform model parameter adjustment or not, and a parameter adjustment method is selected from a parameter adjustment method set; and/or configuring a model evaluation strategy, drawing an effect curve for each financial risk model according to evaluation indexes, and comparing model effects to automatically select an optimal financial risk model, wherein the evaluation indexes comprise accuracy, ROC indexes and AUC indexes.
Preferably, the model configuration file further includes an update file for updating each model generation file.
In example 2, the same parts as those in example 1 are omitted.
It will be appreciated by those skilled in the art that the modules in the embodiments of the apparatus described above may be distributed in an apparatus as described, or may be distributed in one or more apparatuses different from the embodiments described above with corresponding changes. The modules of the above embodiments may be combined into one module, or may be further split into a plurality of sub-modules.
Compared with the prior art, the method can enable the modeling process to be more automatic and standardized, can efficiently produce the optimal model, can further simplify the modeling process, and can further optimize the modeling system; the corresponding data set is automatically selected, and an automatic training model is realized; the optimal financial risk model is automatically selected through the user input of the related business personnel, so that the time for the related business personnel to complete the related business tasks is greatly reduced, and the working efficiency of the business personnel is improved; the optimal financial risk model can be provided for different users, and the risk situation of the users can be predicted more accurately and automatically.
Example 3
The following describes an embodiment of an electronic device according to the present invention, which may be regarded as a specific physical implementation of the above-described embodiment of the method and apparatus according to the present invention. Details described in relation to the embodiments of the electronic device of the present invention should be considered as additions to the embodiments of the method or apparatus described above; for details not disclosed in the embodiments of the electronic device of the present invention, reference may be made to the above-described method or apparatus embodiments.
Fig. 7 is a block diagram of an exemplary embodiment of an electronic device according to the present invention. An electronic apparatus 200 according to the embodiment of the present invention is described below with reference to fig. 7. The electronic device 200 shown in fig. 7 is only an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 7, the electronic device 200 is in the form of a general purpose computing device. The components of the electronic device 200 may include, but are not limited to: at least one processing unit 210, at least one memory unit 220, a bus 230 connecting the different system components (including the memory unit 220 and the processing unit 210), a display unit 240, and the like.
Wherein the storage unit stores program code that is executable by the processing unit 210 such that the processing unit 210 performs the steps according to various exemplary embodiments of the present invention described in the processing method section of the electronic device described above in the present specification. For example, the processing unit 210 may perform the steps shown in fig. 1.
The memory unit 220 may include readable media in the form of volatile memory units, such as Random Access Memory (RAM) 2201 and/or cache memory 2202, and may further include Read Only Memory (ROM) 2203.
The storage unit 220 may also include a program/utility 2204 having a set (at least one) of program modules 2205, such program modules 2205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment.
Bus 230 may be a bus representing one or more of several types of bus structures including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.
The electronic device 200 may also communicate with one or more external devices 300 (e.g., keyboard, pointing device, bluetooth device, etc.), one or more devices that enable a user to interact with the electronic device 200, and/or any device (e.g., router, modem, etc.) that enables the electronic device 200 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 250. Also, the electronic device 200 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through a network adapter 260. Network adapter 260 may communicate with other modules of electronic device 200 via bus 230. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with electronic device 200, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
From the above description of embodiments, those skilled in the art will readily appreciate that the exemplary embodiments described herein may be implemented in software, or may be implemented in software in combination with necessary hardware. Thus, the technical solution according to the embodiments of the present invention may be embodied in the form of a software product, which may be stored in a computer readable storage medium (may be a CD-ROM, a usb disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, or a network device, etc.) to perform the above-mentioned method according to the present invention. The computer program, when executed by a data processing device, enables the computer readable medium to carry out the above-described method of the present invention.
As shown in fig. 8, the computer program may be stored on one or more computer readable media. The computer readable medium may be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, with readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A readable storage medium may also be any readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).
In summary, the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components in accordance with embodiments of the present invention may be implemented in practice using a general purpose data processing device such as a microprocessor or Digital Signal Processor (DSP). The present invention can also be implemented as an apparatus or device program (e.g., a computer program and a computer program product) for performing a portion or all of the methods described herein. Such a program embodying the present invention may be stored on a computer readable medium, or may have the form of one or more signals. Such signals may be downloaded from an internet website, provided on a carrier signal, or provided in any other form.
The above-described specific embodiments further describe the objects, technical solutions and advantageous effects of the present invention in detail, and it should be understood that the present invention is not inherently related to any particular computer, virtual device or electronic apparatus, and various general-purpose devices may also implement the present invention. The foregoing description of the embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (9)
1. A new user risk prediction method based on automatic preferential modeling, comprising:
the method comprises the steps that input is carried out by different business personnel according to authorities or business tasks, model configuration files are preset, the model configuration files comprise model generation files used for automatically generating models and determination strategies for configuring model algorithms and parameters, a plurality of model generation files are configured according to historical business data corresponding to different types of business personnel, and each model generation file comprises a classification strategy for determining sample screening and a data set; the determination strategy of the configuration model algorithm and the parameters comprises a model algorithm, parameter adjustment suggestions and parameter adjustment methods corresponding to the financial time node and the positive and negative sample number of the historical data, so that a user can select whether to perform model parameter adjustment or not, and a parameter adjustment method is selected from a parameter adjustment method set;
receiving user input, wherein the user input comprises a financial product time node, model generation parameters, whether a model algorithm is selected, whether model parameter adjustment is performed or not, and whether model parameters are selected or not, the model generation parameters comprise necessary influencing factors or index parameters for generating each model, and the user is a business person for completing a modeled business task;
Selecting a corresponding model algorithm according to the number of positive and negative samples of the sample data, the number of labeled sample data and the sample data density;
using the received user input to carry out matching processing with the model configuration file, in the matching process, providing a user-editable page, enabling the user to independently select one or more items of data, further identifying identification parameters in the user input according to page submission data of the user-editable page, carrying out matching processing on the identification parameters and an identification information set, and determining a model generation file matched with the user input according to a first matching rule and a second matching rule, wherein the identification parameters comprise financial product time nodes, selection parameters and model generation parameters; the identification information set comprises a time node used for representing the life cycle of the financial product, whether a model algorithm is selected, whether model parameter adjustment is carried out, and whether model parameters are selected;
generating a financial risk model set according to the matched model generation file, and automatically training each financial risk model;
selecting a corresponding test data set, performing effect evaluation on each model in the financial risk model set, and automatically selecting an optimal financial risk model according to evaluation indexes;
And predicting the financial risk of the new user by using the optimal financial risk model.
2. The automatic preferential modeling-based new user risk prediction method according to claim 1, further comprising:
the first matching rule comprises judging whether the identification parameter in the user input has a resource request node, a resource grant node, a resource allocation node, a resource use node, a resource quota increasing node or a resource return node in a financial time node;
the second matching rule comprises judging whether sample screening, a model algorithm, model parameters and parameter adjustment methods exist in page submission data of the user-editable page.
3. The new user risk prediction method based on automatic preferential modeling according to claim 1 or 2, further comprising:
in the matching process, a user-editable page is provided for a user, wherein the user-editable page comprises a plurality of parameter selectable items, and the plurality of parameter selectable items comprise a sample screening method item, a model algorithm item, a model parameter input or increase and decrease item, a model parameter adjustment item and a corresponding adjustment method item.
4. A new user risk prediction method based on automatic preferential modeling according to claim 3, further comprising:
And monitoring the user editable page, and updating the corresponding model generation file according to the monitored page submission data.
5. The method for predicting risk of new users based on automatic preferential modeling according to claim 1, comprising:
the sample screening and classifying strategy comprises a feature extraction rule and a pre-classified data set corresponding to the financial product time node;
the feature extraction rule comprises time parameters, event parameters, risk parameters and financial performance data extracted according to the time parameters and/or the event parameters, wherein the time parameters comprise financial performance data between two adjacent financial time nodes, in a specific time period from each financial time node, in a specific time period before each financial product time node, in a specific selected time period, and in a specific time period, and the financial performance data comprises movable branch data, overdue data, default data and return data; the event parameters include whether a new user is judged, whether overdue data is present, whether default data is present, whether collect urging data is present, and whether a multi-head user is judged.
6. The automatic preferential modeling-based new user risk prediction method according to claim 1 or 5, wherein the preset model profile includes:
And configuring a model evaluation strategy, drawing an effect curve for each financial risk model according to evaluation indexes, and comparing model effects to automatically select an optimal financial risk model, wherein the evaluation indexes comprise accuracy, ROC indexes and AUC indexes.
7. A new user risk prediction apparatus based on automatic preferential modeling, comprising:
the setting module is used for presetting model configuration files according to the input of different service personnel, wherein the model configuration files comprise model generation files for automatically generating models and determining strategies for configuring model algorithms and parameters, and configuring a plurality of model generation files according to historical service data corresponding to different types of service personnel, and each model generation file comprises a classifying strategy for determining sample screening and a data set; the determination strategy of the configuration model algorithm and the parameters comprises a model algorithm, parameter adjustment suggestions and parameter adjustment methods corresponding to the financial time node and the positive and negative sample number of the historical data, so that a user can select whether to perform model parameter adjustment or not, and a parameter adjustment method is selected from a parameter adjustment method set;
the receiving module is used for receiving user input, wherein the user input comprises a financial product time node, model generation parameters, whether a model algorithm is selected, whether model parameter adjustment is performed, and whether model parameters are selected, and the model generation parameters comprise necessary influence factors or index parameters for generating each model; selecting a corresponding model algorithm according to the number of positive and negative samples of the sample data, the number of labeled sample data and the sample data density;
The matching processing module is used for carrying out matching processing on the received user input and the model configuration file, and in the matching process, a user-editable page is provided, so that the user can independently select one or more items of data, identification parameters in the user input are identified according to page submission data of the user-editable page, the identification parameters are matched with an identification information set, and a model generation file matched with the user input is determined according to a first matching rule and a second matching rule, wherein the identification parameters comprise financial product time nodes, selection parameters and model generation parameters; the identification information set comprises a time node used for representing the life cycle of the financial product, whether a model algorithm is selected, whether model parameter adjustment is carried out, and whether model parameters are selected;
the generation module generates a file according to the matched model, generates a financial risk model set and automatically trains each financial risk model;
the evaluation module is used for selecting a corresponding test data set, evaluating the effect of each model in the financial risk model set and automatically selecting an optimal financial risk model according to an evaluation index;
And the prediction module is used for predicting the financial risk of the new user by using the optimal financial risk model.
8. An electronic device, wherein the electronic device comprises:
a processor; the method comprises the steps of,
a memory storing computer executable instructions that when executed cause the processor to perform the new user risk prediction method based on automated preferential modeling according to any one of claims 1-6.
9. A computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement the automated preferential modeling-based new user risk prediction method of any one of claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110166439.1A CN112508723B (en) | 2021-02-05 | 2021-02-05 | Financial risk prediction method and device based on automatic preferential modeling and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110166439.1A CN112508723B (en) | 2021-02-05 | 2021-02-05 | Financial risk prediction method and device based on automatic preferential modeling and electronic equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112508723A CN112508723A (en) | 2021-03-16 |
| CN112508723B true CN112508723B (en) | 2024-02-02 |
Family
ID=74952746
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110166439.1A Active CN112508723B (en) | 2021-02-05 | 2021-02-05 | Financial risk prediction method and device based on automatic preferential modeling and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112508723B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113487427B (en) * | 2021-04-20 | 2024-06-25 | 微梦创科网络科技（中国）有限公司 | Transaction risk identification method, device and system |
| CN112884092B (en) * | 2021-04-28 | 2021-11-02 | 深圳索信达数据技术有限公司 | AI model generation method, electronic device, and storage medium |
| CN113297480B (en) * | 2021-04-29 | 2023-03-14 | 上海淇玥信息技术有限公司 | Customized information sending method and device and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106663224A (en) * | 2014-06-30 | 2017-05-10 | 亚马逊科技公司 | Interactive interfaces for machine learning model evaluations |
| CN110046706A (en) * | 2019-04-18 | 2019-07-23 | 腾讯科技（深圳）有限公司 | Model generating method, device and server |
| CN110210624A (en) * | 2018-07-05 | 2019-09-06 | 第四范式（北京）技术有限公司 | Execute method, apparatus, equipment and the storage medium of machine-learning process |
| CN111639798A (en) * | 2020-05-26 | 2020-09-08 | 华青融天(北京)软件股份有限公司 | Intelligent prediction model selection method and device |
| WO2020249125A1 (en) * | 2019-06-14 | 2020-12-17 | 第四范式（北京）技术有限公司 | Method and system for automatically training machine learning model |
| CN112270545A (en) * | 2020-10-27 | 2021-01-26 | 上海淇馥信息技术有限公司 | Financial risk prediction method and device based on migration sample screening and electronic equipment |
| CN112270547A (en) * | 2020-10-27 | 2021-01-26 | 上海淇馥信息技术有限公司 | Financial risk assessment method and device based on feature construction and electronic equipment |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8731983B2 (en) * | 2005-02-24 | 2014-05-20 | Sap Ag | System and method for designing effective business policies via business rules analysis |
| US20190295011A1 (en) * | 2018-03-20 | 2019-09-26 | Xingjian Duan | Distributed computer framework for data analysis, risk management, and automated compliance |
-
2021
- 2021-02-05 CN CN202110166439.1A patent/CN112508723B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106663224A (en) * | 2014-06-30 | 2017-05-10 | 亚马逊科技公司 | Interactive interfaces for machine learning model evaluations |
| CN110210624A (en) * | 2018-07-05 | 2019-09-06 | 第四范式（北京）技术有限公司 | Execute method, apparatus, equipment and the storage medium of machine-learning process |
| CN110046706A (en) * | 2019-04-18 | 2019-07-23 | 腾讯科技（深圳）有限公司 | Model generating method, device and server |
| WO2020249125A1 (en) * | 2019-06-14 | 2020-12-17 | 第四范式（北京）技术有限公司 | Method and system for automatically training machine learning model |
| CN111639798A (en) * | 2020-05-26 | 2020-09-08 | 华青融天(北京)软件股份有限公司 | Intelligent prediction model selection method and device |
| CN112270545A (en) * | 2020-10-27 | 2021-01-26 | 上海淇馥信息技术有限公司 | Financial risk prediction method and device based on migration sample screening and electronic equipment |
| CN112270547A (en) * | 2020-10-27 | 2021-01-26 | 上海淇馥信息技术有限公司 | Financial risk assessment method and device based on feature construction and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112508723A (en) | 2021-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112508723B (en) | Financial risk prediction method and device based on automatic preferential modeling and electronic equipment | |
| KR101966557B1 (en) | Repairing-part-demand forecasting system and method using big data and machine learning | |
| CN112270545A (en) | Financial risk prediction method and device based on migration sample screening and electronic equipment | |
| US20130024173A1 (en) | Computer-Implemented Systems and Methods for Testing Large Scale Automatic Forecast Combinations | |
| US20110161263A1 (en) | Computer-Implemented Systems And Methods For Constructing A Reduced Input Space Utilizing The Rejected Variable Space | |
| CN112508580A (en) | Model construction method and device based on rejection inference method and electronic equipment | |
| CN112270546A (en) | Risk prediction method and device based on stacking algorithm and electronic equipment | |
| CN111738331A (en) | User classification method and device, computer-readable storage medium and electronic device | |
| CN112508695A (en) | Financial risk prediction method and device based on market risk and electronic equipment | |
| CN111199469A (en) | User payment model generation method and device and electronic equipment | |
| US20230117225A1 (en) | Automated workflow analysis and solution implementation | |
| CN114127803A (en) | Multi-method system for optimal prediction model selection | |
| CN111179055B (en) | Credit line adjusting method and device and electronic equipment | |
| CN111209930B (en) | Method and device for generating trust policy and electronic equipment | |
| Sharko et al. | Methodological basis of causal forecasting of the economic systems development management processes under the uncertainty | |
| CN112348662A (en) | Risk assessment method and device based on user occupation prediction and electronic equipment | |
| CN111210332A (en) | Method and device for generating post-loan management strategy and electronic equipment | |
| CN116757650B (en) | Project management and resource scheduling method based on machine learning | |
| CN112488865A (en) | Financial risk prediction method and device based on financial time nodes and electronic equipment | |
| Raphael et al. | Incremental development of CBR strategies for computing project cost probabilities | |
| CN113298120B (en) | Fusion model-based user risk prediction method, system and computer equipment | |
| CN113570114B (en) | Resource service intelligent matching method, system and computer equipment | |
| WO2022064894A1 (en) | Information processing device, information processing method, and program | |
| US20220309391A1 (en) | Interactive machine learning optimization | |
| Saif | Software Effort Estimation for Successful Software Application Development |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |