CN110135628A - A kind of monetary device automatic generation method, device, system and recording medium - Google Patents
A kind of monetary device automatic generation method, device, system and recording medium Download PDFInfo
- Publication number
- CN110135628A CN110135628A CN201910330994.6A CN201910330994A CN110135628A CN 110135628 A CN110135628 A CN 110135628A CN 201910330994 A CN201910330994 A CN 201910330994A CN 110135628 A CN110135628 A CN 110135628A
- Authority
- CN
- China
- Prior art keywords
- configuration
- financial
- user data
- monetary
- data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 47
- 238000012549 training Methods 0.000 claims description 26
- 238000007418 data mining Methods 0.000 claims description 11
- 238000012800 visualization Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000003066 decision tree Methods 0.000 claims description 5
- 238000007637 random forest analysis Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 claims 1
- 239000010931 gold Substances 0.000 claims 1
- 229910052737 gold Inorganic materials 0.000 claims 1
- 238000004458 analytical method Methods 0.000 abstract description 29
- 238000007405 data analysis Methods 0.000 abstract description 4
- 230000010354 integration Effects 0.000 abstract description 2
- 238000012216 screening Methods 0.000 description 10
- 238000006243 chemical reaction Methods 0.000 description 8
- 238000009826 distribution Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 238000010835 comparative analysis Methods 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000009432 framing Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000000717 retained effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 239000012141 concentrate Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 239000000203 mixture Substances 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
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
Abstract
The invention discloses monetary device automatic generation method, device, system and computer-readable medium, this method includes obtaining financial user data, receives the configuration for financial user data, the financial user data is configured to sample data;Receive the configuration for monetary device target;Receive the configuration of the algorithm for financial modeling;According to the configuration for monetary device target, utilize the configuration of the algorithm of configuration and financial modeling to the financial user data, automatically calculate each label importance and each label for the monetary device target disturbance degree, to obtain best monetary device.The present invention can analysis method based on integration specification and a variety of AI algorithms, utilize automated decision-making analysis tool, realize intelligence, the automation of data analysis, generate and be conducive to the policy report that analysis personnel use, improve analysis person works' efficiency.
Description
Technical field
The invention belongs to technical field of data processing, and in particular to for business, finance the purpose of data processing system
And method, especially monetary device automatic generation method, device, system and computer-readable medium.
Background technique
Financial platform can obtain customer traffic from various channels, it is also desirable to the quality of each channel customer flow is assessed,
However, analysis difficulty is big and complicated, passes through to the business of analysis personnel in based on high-dimensional big data analysis of strategies work
It tests, program capability, knowledge of statistics etc. have very high request.
In the prior art, in the marketing process of financial product, for target customer, and the policy goals to be realized,
Ideal strategy protocol is obtained, analysis personnel need to have comprehensive ability, and in particular to professional ability, programming energy
Power, data analysis capabilities etc..So that analysis personnel is obtained optimal there is no complete set, intelligentized tool for the prior art
Or ideal strategy protocol, concentrate on analysis personnel more energy in business scenario analysis and inventive application.
Summary of the invention
The technical problem to be solved by the present invention is how to realize that automation generates optimal policy scheme.
In order to solve the above technical problems, the first aspect of the present invention proposes a kind of monetary device automatic generation method, comprising:
Financial user data is obtained, the financial user data includes multiple labels;The configuration for financial user data is received, it will
The financial user data is configured to sample data;The configuration for monetary device target is received, the target refers to using institute
State the financial product target component to be achieved of monetary device;Receive the configuration of the algorithm for financial modeling;According to described
Configuration for monetary device target, using the configuration of the algorithm of configuration and financial modeling to the financial user data, certainly
The importance for calculating each label and each label are moved for the disturbance degree of the monetary device target, to obtain best financial plan
Slightly.
A preferred embodiment of the invention, further includes: monetary device report is automatically generated, under this report includes
At least one of column content: the configuration of financial user data, monetary device target, the algorithm of financial modeling, each label it is important
The disturbance degree of property and each label for the monetary device target.
A preferred embodiment of the invention, the label included whether room, whether have vehicle, whether undergraduate course and
It is above, whether training, at least one of whether have consumptive loan, whether had overdue, amount of liabilities.
A preferred embodiment of the invention, the sample data include training sample data, verifying sample number
According to, at least one of the outer verifying sample data of packet, production assessment sample data.
A preferred embodiment of the invention, the target component include: the number of users after financial product is promoted
The touch amount of money and ROI conversion ratio after amount, financial product popularization.
A preferred embodiment of the invention, the algorithm include: regression algorithm, text analyzing, time series,
Random forest, XgBoost, Tree-NET | GBDT, decision tree, bayesian algorithm.
A preferred embodiment of the invention, each label are for the disturbance degree of the monetary device target
Refer to concentration of the label data relative to monetary device target component.
A preferred embodiment of the invention receives the configuration by visualization interface.
A preferred embodiment of the invention, further includes: the automatic number for the financial user data is provided
According to the display of exploration.
A preferred embodiment of the invention, the Data Mining include: that data statistics amount summarizes.
A preferred embodiment of the invention, the statistical method that the data statistics amount summarizes include: missing system
Meter, mean value, most value, variance.
The second aspect of the present invention proposes a kind of monetary device automatically generating device, comprising: user data obtains module, uses
In obtaining financial user data, the financial user data includes multiple labels;User data configuration module, for receive for
The financial user data is configured to sample data by the configuration of financial user data;Policy goals configuration module, for connecing
The configuration for monetary device target is received, the target refers to the financial product target to be achieved using the monetary device
Parameter;Model algorithm configuration module receives the configuration of the algorithm for financial modeling;Policy generation module, for according to
Configuration for monetary device target, using the configuration of the algorithm of configuration and financial modeling to the financial user data, certainly
The importance for calculating each label and each label are moved for the disturbance degree of the monetary device target, to obtain best financial plan
Slightly.
A preferred embodiment of the invention, further includes: monetary device report is automatically generated, under this report includes
At least one of column content: the configuration of financial user data, monetary device target, the algorithm of financial modeling, each label it is important
The disturbance degree of property and each label for the monetary device target.
A preferred embodiment of the invention, the label included whether room, whether have vehicle, whether undergraduate course and
It is above, whether training, at least one of whether have consumptive loan, whether had overdue, amount of liabilities.
A preferred embodiment of the invention, the sample data include training sample data, verifying sample number
According to, at least one of the outer verifying sample data of packet, production assessment sample data.
A preferred embodiment of the invention, the target component include: the number of users after financial product is promoted
The touch amount of money and ROI conversion ratio after amount, financial product popularization.
A preferred embodiment of the invention, the algorithm include: regression algorithm, text analyzing, time series,
Random forest, XgBoost, Tree-NET | GBDT, decision tree, bayesian algorithm.
A preferred embodiment of the invention, each label are for the disturbance degree of the monetary device target
Refer to concentration of the label data relative to monetary device target component.
A preferred embodiment of the invention receives the configuration by visualization interface.
A preferred embodiment of the invention, further includes: the automatic number for the financial user data is provided
According to the display of exploration.
A preferred embodiment of the invention, the Data Mining include: that data statistics amount summarizes.
A preferred embodiment of the invention, the statistical method that the data statistics amount summarizes include: missing system
Meter, mean value, most value, variance.
The third aspect of the present invention proposes a kind of monetary device automatic creation system, comprising: memory is calculated for storing
Machine executable program;Data processing equipment, for reading the computer executable program in the memory, described with execution
Monetary device automatic generation method.
The fourth aspect of the present invention proposes a kind of computer-readable medium, for storing computer-readable program, the meter
Calculation machine readable program is used to execute the monetary device automatic generation method.
Technical solution of the present invention has the following beneficial effects:
The present invention can analysis method based on integration specification and a variety of AI algorithms, using automated decision-making analysis tool,
Intelligence, the automation for realizing data analysis generate and are conducive to the optimal policy report that analysis personnel use, improve analysis personnel work
Make efficiency.
Detailed description of the invention
Fig. 1 is the flow diagram of monetary device automatic generation method of the invention;
Fig. 2 is the histogram of each labeled targets variable concentration of monetary device automatic generation method of the invention;
Fig. 3 is the module architectures schematic diagram of monetary device automatically generating device of the invention;
Fig. 4 is the structural framing schematic diagram of monetary device automatic creation system of the invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, below in conjunction with specific embodiment, and reference
Attached drawing, the present invention is described in further detail.
It should be noted that monetary device automatic generation method, device, system and computer-readable medium of the invention,
It needs using automated decision-making analysis tool, when tool is selected, discrimination wants high.
As an example, the present invention is for screening high risk target visitor group.By sample configuration, policy goals setting is calculated
Method selects the configuration of three steps, automatically generates the optimal policy scheme based on business objective, i.e. the present invention can provide screening high risk
Label importance ranking and specific strategy protocol when objective group, and then it is conducive to the strategy that analysis personnel provide according to this method
Accurately screen High risk group.
The strategy that provides according to the method for the present invention or rule can be stable find out it is more much higher than normal clients risk
Client again.
Also, method of the invention can also automatically generate complete analysis report, and this report includes specific strategy, strategy
Effect, stability, impact evaluation etc..
Method application scenarios of the invention are also very rich, for example, can be used for new strategy formulation, policy optimization, outside
Standing accesses the scenes such as assessment, migration efficiency, collection.
Fig. 1 is the flow diagram of monetary device automatic generation method of the invention, as shown in Figure 1, this method comprises:
S1: financial user data is obtained, the financial user data includes multiple labels.
Further, the label included whether room, whether have vehicle, whether undergraduate course and its more than, whether training, whether have
Whether consumptive loan at least one of had overdue, amount of liabilities.
Wherein, the source of financial user data includes the data generated online, the data for pre-generating and storing, by defeated
Enter device or transmission medium and from least one of external received data.
External data includes external standing data and web search data, and the data generated online include that APP uses data.
As an example, financial user data of the invention is externally introduced data by input unit.
Further, monetary device automatic generation method of the invention further include: provide for the financial user data
The display that automaticdata is explored.
Further, the Data Mining includes: that data statistics amount summarizes.
Further, the statistical method that the data statistics amount summarizes includes: miss statistics, mean value, most value, variance.
As an example, the data being externally introduced, need to carry out Data Mining, Data Mining can make financial user data
It more intuitively shows, convenient for analysis, personnel check data, and the information of basic understanding finance user.
Data Mining includes: that data statistics amount summarizes, and the data statistics amount that analysis personnel can obtain includes lacking for data
Lose statistics, mean value, most value and variance etc..
The statistical chart of data statistics amount, is automated decision-making tool automatic mapping, analysis personnel according to check it is convenient can be with
Select the figures such as histogram or line chart.
S2: the configuration for financial user data is received, the financial user data is configured to sample data.
Further, the sample data includes training sample data, verifying sample data, the outer verifying sample data, life of packet
Produce at least one of assessment sample data.
It as shown in table 1, is the detailed configuration situation of the sample data in monetary device automatic generation method of the invention.Sample
The target variable of notebook data is divided into bad and good.
The quantity that target variable is bad in training sample data is 376, ratio 5.20%, and target variable is the number of good
Amount is 7520, and ratio 103.94%, training sample amounts to 7235, ratio 100.00%.
Verifying the quantity that target variable is bad in sample data is 380, ratio 5.22%, and target variable is the number of good
Amount is 7170, and ratio 98.42%, training sample amounts to 7285, ratio 100.00%.
Wrapping the quantity that target variable is bad in outer sample data is 400, ratio 5.35%, and target variable is the number of good
Amount is 7364, and ratio 98.46%, training sample amounts to 7479, ratio 100.00%.
Production assessment sample adds up to 5000.
Table 1
Further, it can be configured by visualization interface by the configuration of sample data, it is visual to be conducive to analysis personnel
Change operation.
S3: receiving the configuration for monetary device target, and the target refers to the financial product using the monetary device
Target component to be achieved.
Further, the target component includes: the number of users after financial product is promoted, the touch after financial product popularization
The amount of money and ROI conversion ratio.When passing through short message promotion, ROI conversion ratio example is the ROI conversion ratio of short message marketing.
Further, it for the configuration of policy goals, can equally be configured by visualization interface.
S4: the configuration of the algorithm for financial modeling is received.
Further, the algorithm includes: regression algorithm, text analyzing, time series, random forest, XgBoost, Tree-
NET | GBDT, decision tree, bayesian algorithm.
Further, it for the configuration of financial modeling algorithm, can equally be configured by visualization interface.
It should be noted that needing to be adjusted the design parameter being related to when using different algorithms, difference is calculated
In method, the design parameter for being related to the same label is different.
S5: according to the configuration for monetary device target, the configuration and finance to the financial user data are utilized
The configuration of the algorithm of model, calculate automatically each label importance and each label for the monetary device target disturbance degree,
To obtain best monetary device.
Further, each label refers to label data relative to financial plan the disturbance degree of the monetary device target
The slightly concentration of target component.
Further, further includes: automatically generate monetary device report, this report includes at least one of following content: finance
Configuration, monetary device target, the algorithm of financial modeling, the importance of each label and each label of user data are for the finance
The disturbance degree of policy goals.
As shown in table 2, it is monetary device automatic generation method of the invention according to the configuration for policy goals, utilizes
Matching for the algorithm of configuration and model to user data postpones, the importance of automatic calculated each label.
As shown in table 2, when screening original text risk visitor group, the importance of label by whether have room, whether have vehicle, whether undergraduate course
And its above, whether training, whether have consumptive loan, whether there is overdue, amount of liabilities to gradually decrease.Also, whether having
Room and whether have vehicle become important measurement standard.
Table 2
Serial number | Variable name | |
1 | Whether room is had | |
2 | Whether vehicle is had | |
3 | Whether undergraduate course and its more than | |
4 | Whether training | |
5 | It is whether married | |
6 | Whether consumptive loan is had | |
7 | Whether had overdue | |
8 | Amount of liabilities | |
9 | …… |
As shown in table 3, it is monetary device automatic generation method of the invention according to the configuration for policy goals, utilizes
Matching for the algorithm of configuration and model to user data postpones, automatic influence of the calculated each label for monetary device target
Degree, that is, refer to concentration of the label data relative to monetary device target component.
As shown in table 3, when screening original text risk visitor group, method of the invention also provides in addition to the importance of outgoing label
The target variable concentration of some specific label.
As an example, using whether undergraduate course and its more than label target variable concentration as example.Educational background be undergraduate course and
In client more than it, the quantity at hospitable family is 2600, and the quantity of bad client is 56, using bad client as the concentration of target variable
It is 2.11%.Educational background be not undergraduate course and its more than client in, the quantity at hospitable family is 4635, and the quantity of bad client is 320, with
Bad client is 6.46% as the concentration of target variable.Hospitable family total quantity is 7235, and bad client's total quantity is 376, bad client
Total target variable concentration is 4.94%.
Table 3
Fig. 2 is the histogram of each labeled targets variable concentration of monetary device automatic generation method of the invention.The number of Fig. 2
According to corresponding with the data in table 3.
By histogram, can more can be clearly seen that, educational background be undergraduate course and its more than user in, High risk group is wanted
Than educational background be not undergraduate course and its more than it is few.Educational background be not undergraduate course and its more than client in, High risk group is more.
Table 4 be using monetary device automatic generation method of the invention provide screening High risk group specific strategy or
Rule utilizes the algorithm of configuration and financial modeling to financial user data that is, according to configuration for monetary device target
Configuration, obtained optimal policy.
Table 4
Two kinds of rules of screening high risk visitor group are provided as shown in table 4.The first rule are as follows: whether there is room=no and to be
It is no had it is overdue=be and whether married=no.Second rule are as follows: whether had it is overdue=be amount of liabilities > 50000 and
Member.
Table 5
It as shown in table 5, is the rule provided by monetary device automatic generation method of the invention, the high risk visitor filtered out
Group and the aimed concn comparative analysis table for retaining client.Wherein, in the training sample of high risk visitor group, target variable concentration is
20.20%;It retains in client, target variable concentration is 4.89%.In the verifying sample of high risk visitor group, target variable concentration is
21.00%;It retains in client, target variable concentration is 4.84%.In the outer sample of the packet of high risk visitor group, target variable concentration is
22.00%;It retains in client, target variable concentration is 4.99%.
It is in table 5 statistics indicate that, what 1. rules estimated by means of the present invention can be stable finds out and compares normal clients
High 4 times of the client of risk;2. the high risk visitor group that the Rules Filtering estimated by means of the present invention goes out, on different samples
Distribution proportion is similar, i.e., the ability that the rule of method presumption of the invention distinguishes risk is stablized.
Table 6
Table 6 is the rule provided by monetary device automatic generation method of the invention, the high risk visitor group filtered out with stay
Deposit the distributed number comparative analysis table of client.As shown in table 6, high risk visitor group training sample, verifying sample, the outer sample of packet,
Distribution proportion in production verifying sample is close to 2.0%.Client is retained in training sample, verifying sample, the outer sample of packet, production
The distribution proportion in sample is verified close to 98.0%.
It is in table 6 statistics indicate that, the high risk visitor group that the Rules Filtering estimated by means of the present invention goes out is not same
Distribution is stable in sheet.
Table 1 is the content of policy report, the weight of configuration, specific strategy, each label including financial user data to table 6
The property wanted and each label are for the disturbance degree of the monetary device target and tactful effect analysis etc..
Policy report of the invention can be by output device, convenient for the use of business personnel.
By above method process, a complete analysis of strategies report can be covered substantially.Business personnel confirms report
It, can be according to report publishing policy under the premise of data source is correct.
Fig. 3 is the module architectures schematic diagram of monetary device automatically generating device of the invention, as shown in figure 3, the device packet
Include: user data obtains module, user data configuration module, policy goals configuration module, policy goals configuration module, strategy life
At module.
User data obtains module, and for obtaining financial user data, the financial user data includes multiple labels.
Further, the label included whether room, whether have vehicle, whether undergraduate course and its more than, whether training, whether have
Whether consumptive loan at least one of had overdue, amount of liabilities.
Wherein, the source of financial user data includes the data generated online, the data for pre-generating and storing, by defeated
Enter device or transmission medium and from least one of external received data.
External data includes external standing data and web search data, and the data generated online include that APP uses data.
As an example, financial user data of the invention is externally introduced data by input unit.
Further, monetary device automatically generating device of the invention also provides the automatic number for the financial user data
According to the display of exploration.
Further, the Data Mining includes: that data statistics amount summarizes.
Further, the statistical method that the data statistics amount summarizes includes: miss statistics, mean value, most value, variance.
As an example, the data being externally introduced, need to carry out Data Mining, Data Mining can make financial user data
It more intuitively shows, convenient for analysis, personnel check data, and the information of basic understanding finance user.
Data Mining includes: that data statistics amount summarizes, and the data statistics amount that analysis personnel can obtain includes lacking for data
Lose statistics, mean value, most value and variance etc..
The statistical chart of data statistics amount, is automated decision-making tool automatic mapping, analysis personnel according to check it is convenient can be with
Select the figures such as histogram or line chart.
User data configuration module, for receiving the configuration for financial user data, by the financial user data
It is configured to sample data.
Further, the sample data includes training sample data, verifying sample data, the outer verifying sample data, life of packet
Produce at least one of assessment sample data.
As shown in table 1, the details of sample data configuration is carried out for monetary device automatically generating device of the invention.Sample
The target variable of notebook data is divided into bad and good.
The quantity that target variable is bad in training sample data is 376, ratio 5.20%, and target variable is the number of good
Amount is 7520, and ratio 103.94%, training sample amounts to 7235, ratio 100.00%.
Verifying the quantity that target variable is bad in sample data is 380, ratio 5.22%, and target variable is the number of good
Amount is 7170, and ratio 98.42%, training sample amounts to 7285, ratio 100.00%.
Wrapping the quantity that target variable is bad in outer sample data is 400, ratio 5.35%, and target variable is the number of good
Amount is 7364, and ratio 98.46%, training sample amounts to 7479, ratio 100.00%.
Production assessment sample adds up to 5000.
Further, it can be configured by visualization interface by the configuration of sample data, it is visual to be conducive to analysis personnel
Change operation.
Policy goals configuration module, for receiving the configuration for monetary device target, the target refers to described in use
The financial product of monetary device target component to be achieved.
Further, the target component includes: the number of users after financial product is promoted, the touch after financial product popularization
The amount of money and ROI conversion ratio.When passing through short message promotion, ROI conversion ratio example is the ROI conversion ratio of short message marketing.
Further, it for the configuration of policy goals, can equally be configured by visualization interface.
Model algorithm configuration module receives the configuration of the algorithm for financial modeling.
Further, the algorithm includes: regression algorithm, text analyzing, time series, random forest, XgBoost, Tree-
NET | GBDT, decision tree, bayesian algorithm.
Further, it for the configuration of financial modeling algorithm, can equally be configured by visualization interface.
It should be noted that needing to be adjusted the design parameter being related to when using different algorithms, difference is calculated
In method, the design parameter for being related to the same label is different.
Policy generation module, for the configuration according to for monetary device target, using to the financial number of users
According to configuration and financial modeling algorithm configuration, the importance for calculating each label automatically and each label are for the monetary device
The disturbance degree of target, to obtain best monetary device.
Further, each label refers to label data relative to financial plan the disturbance degree of the monetary device target
The slightly concentration of target component.
Further, further includes: automatically generate monetary device report, this report includes at least one of following content: finance
Configuration, monetary device target, the algorithm of financial modeling, the importance of each label and each label of user data are for the finance
The disturbance degree of policy goals.
As shown in table 2, it is monetary device automatically generating device of the invention according to the configuration for policy goals, utilizes
Matching for the algorithm of configuration and model to user data postpones, the importance of automatic calculated each label.
As shown in table 2, when screening original text risk visitor group, the importance of label by whether have room, whether have vehicle, whether undergraduate course
And its above, whether training, whether have consumptive loan, whether there is overdue, amount of liabilities to gradually decrease.Also, whether having
Room and whether have vehicle become important measurement standard.
As shown in table 3, it is monetary device automatically generating device of the invention according to the configuration for policy goals, utilizes
Matching for the algorithm of configuration and model to user data postpones, automatic influence of the calculated each label for monetary device target
Degree, that is, refer to concentration of the label data relative to monetary device target component.
As shown in table 3, when screening original text risk visitor group, the device of the invention also provides in addition to the importance of outgoing label
The target variable concentration of some specific label.
As an example, using whether undergraduate course and its more than label target variable concentration as example.Educational background be undergraduate course and
In client more than it, the quantity at hospitable family is 2600, and the quantity of bad client is 56, using bad client as the concentration of target variable
It is 2.11%.Educational background be not undergraduate course and its more than client in, the quantity at hospitable family is 4635, and the quantity of bad client is 320, with
Bad client is 6.46% as the concentration of target variable.Hospitable family total quantity is 7235, and bad client's total quantity is 376, bad client
Total target variable concentration is 4.94%.
Fig. 2 is the histogram of each labeled targets variable concentration of monetary device automatic generation method of the invention.The number of Fig. 2
According to corresponding with the data in table 3.
By histogram, can more can be clearly seen that, educational background be undergraduate course and its more than user in, High risk group is wanted
Than educational background be not undergraduate course and its more than it is few.Educational background be not undergraduate course and its more than client in, High risk group is more.
Table 4 be using monetary device automatically generating device of the invention provide screening High risk group specific strategy or
Rule utilizes the algorithm of configuration and financial modeling to financial user data that is, according to configuration for monetary device target
Configuration, obtained optimal policy.
Two kinds of rules of screening high risk visitor group are provided as shown in table 4.The first rule are as follows: whether there is room=no and to be
It is no had it is overdue=be and whether married=no.Second rule are as follows: whether had it is overdue=be amount of liabilities > 50000 and
Member.
It as shown in table 5, is the rule provided by monetary device automatically generating device of the invention, the high risk visitor filtered out
Group and the aimed concn comparative analysis table for retaining client.Wherein, in the training sample of high risk visitor group, target variable concentration is
20.20%;It retains in client, target variable concentration is 4.89%.In the verifying sample of high risk visitor group, target variable concentration is
21.00%;It retains in client, target variable concentration is 4.84%.In the outer sample of the packet of high risk visitor group, target variable concentration is
22.00%;It retains in client, target variable concentration is 4.99%.
It is in table 5 statistics indicate that, what 1. rules estimated by means of the present invention can be stable finds out and compares normal clients
High 4 times of the client of risk;2. the high risk visitor group that the Rules Filtering estimated by means of the present invention goes out, on different samples
Distribution proportion is similar, i.e., the ability that the rule of method presumption of the invention distinguishes risk is stablized.
Table 6 is the rule provided by monetary device automatically generating device of the invention, the high risk visitor group filtered out with stay
Deposit the distributed number comparative analysis table of client.As shown in table 6, high risk visitor group training sample, verifying sample, the outer sample of packet,
Distribution proportion in production verifying sample is close to 2.0%.Client is retained in training sample, verifying sample, the outer sample of packet, production
The distribution proportion in sample is verified close to 98.0%.
It is in table 6 statistics indicate that, the high risk visitor group that the Rules Filtering estimated by means of the present invention goes out is not same
Distribution is stable in sheet.
Table 1 is the content of policy report, the weight of configuration, specific strategy, each label including financial user data to table 6
The property wanted and each label are for the disturbance degree of the monetary device target and tactful effect analysis etc..
Policy report of the invention can be by output device, convenient for the use of business personnel.
By above method process, a complete analysis of strategies report can be covered substantially.Business personnel confirms report
It, can be according to report publishing policy under the premise of data source is correct.
In addition, the present invention also proposes monetary device automatic creation system.Fig. 4 be monetary device of the invention of the invention from
The structural framing schematic diagram of dynamic generation system, as shown in figure 4, monetary device automatic creation system of the invention include memory and
Data processing equipment, memory is for storing computer executable program, data processing equipment, for reading in the memory
Computer executable program, to execute the monetary device automatic generation method.System can be local system in the present invention
System, is also possible to distributed system.Memory of the invention can be local storage, be also possible to distributed memory system,
Such as cloud storage system.And data processor then include at least one tool number word information processing capability device, such as CPU,
GPU, multicomputer system or cloud processor.
Furthermore the present invention also proposes computer-readable medium, described computer-readable for storing computer-readable program
Program is used to execute the monetary device automatic generation method of the invention.
It should be appreciated that in order to simplify the present invention and help it will be understood by those skilled in the art that various aspects of the invention,
Above in the description of exemplary embodiment of the present invention, each feature of the invention is retouched in a single embodiment sometimes
It states, or is described referring to single figure.But should not be by the feature that the present invention is construed to include in exemplary embodiment
The essential features of patent claims.
It should be appreciated that can be to progress such as module, unit, the components for including in the equipment of one embodiment of the present of invention certainly
It adaptively changes so that they are arranged in equipment unlike this embodiment.The difference that can include the equipment of embodiment
Module, unit or assembly are combined into module, a unit or assembly, also they can be divided into multiple submodule, subelement or
Sub-component.Module, unit or assembly in the embodiment of the present invention can realize in hardware, can also be with one or more
The software mode run on a processor is realized, or is implemented in a combination thereof.
Particular embodiments described above has carried out further in detail the purpose of the present invention, technical scheme and beneficial effects
Describe in detail bright, it should be understood that the above is only a specific embodiment of the present invention, is not intended to restrict the invention, it is all
Within the spirit and principles in the present invention, any modification, equivalent substitution, improvement and etc. done should be included in protection of the invention
Within the scope of.
Claims (10)
1. a kind of monetary device automatic generation method, comprising:
Financial user data is obtained, the financial user data includes multiple labels;
The configuration for financial user data is received, the financial user data is configured to sample data;
The configuration for monetary device target is received, the target refers to be reached using the financial product of the monetary device
Target component;
Receive the configuration of the algorithm for financial modeling;
According to the configuration for monetary device target, the calculation of configuration and financial modeling to the financial user data is utilized
The configuration of method, calculate automatically each label importance and each label for the monetary device target disturbance degree, to obtain
Best monetary device.
2. monetary device automatic generation method as described in claim 1, which is characterized in that the label included whether room,
Whether have vehicle, whether undergraduate course and its more than, whether training, whether have consumptive loan, whether had in overdue, amount of liabilities extremely
Few one kind.
3. monetary device automatic generation method as described in claim 1, which is characterized in that the algorithm include: regression algorithm,
Text analyzing, time series, random forest, XgBoost, Tree-NET | GBDT, decision tree, bayesian algorithm.
4. monetary device automatic generation method as described in claim 1, which is characterized in that described in being received by visualization interface
Configuration.
5. monetary device automatic generation method as described in claim 1, which is characterized in that further include: it provides for the gold
Melt the display that the automaticdata of user data is explored.
6. monetary device automatic generation method as claimed in claim 5, which is characterized in that the Data Mining includes: data
Statistic summarizes.
7. monetary device automatic generation method as claimed in claim 6, which is characterized in that the system that the data statistics amount summarizes
Meter method includes: miss statistics, mean value, most value, variance.
8. a kind of monetary device automatically generating device, comprising:
User data obtains module, and for obtaining financial user data, the financial user data includes multiple labels;
User data configuration module configures the financial user data for receiving the configuration for financial user data
At sample data;
Policy goals configuration module, for receiving the configuration for monetary device target, the target refers to using the finance
The financial product target component to be achieved of strategy;
Model algorithm configuration module receives the configuration of the algorithm for financial modeling;
Policy generation module, for the configuration according to for monetary device target, using to the financial user data
The configuration of the algorithm of configuration and financial modeling, the importance for calculating each label automatically and each label are for the monetary device target
Disturbance degree, to obtain best monetary device.
9. a kind of monetary device automatic creation system characterized by comprising
Memory, for storing computer executable program;
Data processing equipment is required in 1 to 7 for reading the computer executable program in the memory with perform claim
Described in any item monetary device automatic generation methods.
10. a kind of computer-readable medium, for storing computer-readable program, which is characterized in that the computer-readable journey
Sequence is for monetary device automatic generation method described in any one of perform claim requirement 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910330994.6A CN110135628A (en) | 2019-04-23 | 2019-04-23 | A kind of monetary device automatic generation method, device, system and recording medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910330994.6A CN110135628A (en) | 2019-04-23 | 2019-04-23 | A kind of monetary device automatic generation method, device, system and recording medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110135628A true CN110135628A (en) | 2019-08-16 |
Family
ID=67570816
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910330994.6A Pending CN110135628A (en) | 2019-04-23 | 2019-04-23 | A kind of monetary device automatic generation method, device, system and recording medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110135628A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110769385A (en) * | 2019-09-26 | 2020-02-07 | 北京淇瑀信息科技有限公司 | Short message sending method and device using strategy optimization model and electronic equipment |
CN112801611A (en) * | 2021-01-22 | 2021-05-14 | 平安消费金融有限公司 | Wind control method and system based on big data |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106779087A (en) * | 2016-11-30 | 2017-05-31 | 福建亿榕信息技术有限公司 | A kind of general-purpose machinery learning data analysis platform |
CN107122863A (en) * | 2017-04-28 | 2017-09-01 | 厦门大学 | Overstock inquiry and the Forecasting Methodology of material correlative attribute |
CN107993139A (en) * | 2017-11-15 | 2018-05-04 | 华融融通(北京)科技有限公司 | A kind of anti-fake system of consumer finance based on dynamic regulation database and method |
CN109034658A (en) * | 2018-08-22 | 2018-12-18 | 重庆邮电大学 | A kind of promise breaking consumer's risk prediction technique based on big data finance |
CN109344998A (en) * | 2018-09-06 | 2019-02-15 | 盈盈(杭州)网络技术有限公司 | A kind of customer default probability forecasting method based on medical and beauty treatment scene |
CN109635010A (en) * | 2018-12-26 | 2019-04-16 | 深圳市梦网百科信息技术有限公司 | A kind of user characteristics and characterization factor extract, querying method and system |
-
2019
- 2019-04-23 CN CN201910330994.6A patent/CN110135628A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106779087A (en) * | 2016-11-30 | 2017-05-31 | 福建亿榕信息技术有限公司 | A kind of general-purpose machinery learning data analysis platform |
CN107122863A (en) * | 2017-04-28 | 2017-09-01 | 厦门大学 | Overstock inquiry and the Forecasting Methodology of material correlative attribute |
CN107993139A (en) * | 2017-11-15 | 2018-05-04 | 华融融通(北京)科技有限公司 | A kind of anti-fake system of consumer finance based on dynamic regulation database and method |
CN109034658A (en) * | 2018-08-22 | 2018-12-18 | 重庆邮电大学 | A kind of promise breaking consumer's risk prediction technique based on big data finance |
CN109344998A (en) * | 2018-09-06 | 2019-02-15 | 盈盈(杭州)网络技术有限公司 | A kind of customer default probability forecasting method based on medical and beauty treatment scene |
CN109635010A (en) * | 2018-12-26 | 2019-04-16 | 深圳市梦网百科信息技术有限公司 | A kind of user characteristics and characterization factor extract, querying method and system |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110769385A (en) * | 2019-09-26 | 2020-02-07 | 北京淇瑀信息科技有限公司 | Short message sending method and device using strategy optimization model and electronic equipment |
CN112801611A (en) * | 2021-01-22 | 2021-05-14 | 平安消费金融有限公司 | Wind control method and system based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20200193312A1 (en) | Method and system for composite scoring, classification, and decision making based on machine learning | |
Chen et al. | A fuzzy credit-rating approach for commercial loans: a Taiwan case | |
Persson et al. | Equity and efficiency in adaptation finance: Initial experiences of the Adaptation Fund | |
JP5605819B2 (en) | Credit scoring and reporting | |
Hu et al. | User influence analysis for github developer social networks | |
KR101772803B1 (en) | Method for management consulting of company | |
EP2329447A1 (en) | Evaluating loan access using online business transaction data | |
CN107194743A (en) | A kind of network surveying questionnaire generation method and device | |
US20150026083A1 (en) | Generating Connection Map for Intelligent Connections in Enterprises | |
KR20110081060A (en) | Analyzing anticipated value and effort in using cloud computing to process a specified workload | |
Hasenpusch et al. | Strategic media venturing: Corporate venture capital approaches of TIME incumbents | |
Nicholson et al. | Conceptual frameworks linking agriculture and food security | |
CN112634056A (en) | Method, equipment and storage medium for rapidly calculating and updating enterprise share right structure | |
Bateman et al. | Risk information and retirement investment choice mistakes under prospect theory | |
CN110135628A (en) | A kind of monetary device automatic generation method, device, system and recording medium | |
Veselinović et al. | The interplay of entrepreneurial orientation, total quality management, and financial performance | |
Seth et al. | Consensus and conflict: Exploring moderating effects of knowledge workers on industry environment and entrepreneurial entry relationship | |
Lyu et al. | Income-increasing effect of e-commerce of agricultural products based on IT absorptive theory | |
CN108805603A (en) | Marketing activity method for evaluating quality, server and computer readable storage medium | |
US20220122181A1 (en) | Processes and procedures for managing and characterizing liquidity risk of a portfolio over time using data analytics methods in a cloud computing environment | |
Biswas et al. | A Proposed q-Rung Orthopair Fuzzy-Based Decision Support System for Comparing Marketing Automation Modules for Higher Education Admission | |
CN113407827A (en) | Information recommendation method, device, equipment and medium based on user value classification | |
CN113469696A (en) | User abnormality degree evaluation method and device and computer readable storage medium | |
CN106301880A (en) | One determines that cyberrelationship degree of stability, Internet service recommend method and apparatus | |
CN113869973A (en) | Product recommendation method, product recommendation system, and computer-readable storage medium |
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 | ||
CB02 | Change of applicant information |
Country or region after: China Address after: Room 1109, No. 4, Lane 800, Tongpu Road, Putuo District, Shanghai, 200062 Applicant after: Shanghai Qiyue Information Technology Co.,Ltd. Address before: Room a2-8914, 58 Fumin Branch Road, Hengsha Township, Chongming District, Shanghai, 201500 Applicant before: Shanghai Qiyue Information Technology Co.,Ltd. Country or region before: China |
|
CB02 | Change of applicant information |