CN107358360A - The abnormal traffic data screening method of anti money washing system - Google Patents
The abnormal traffic data screening method of anti money washing system Download PDFInfo
- Publication number
- CN107358360A CN107358360A CN201710576257.5A CN201710576257A CN107358360A CN 107358360 A CN107358360 A CN 107358360A CN 201710576257 A CN201710576257 A CN 201710576257A CN 107358360 A CN107358360 A CN 107358360A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- exception model
- triggered
- data
- abnormal index
- 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
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Accounting & Taxation (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Technology Law (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present embodiments relate to data screening method, a kind of abnormal traffic data screening method of anti money washing system is specifically disclosed.This method includes receiving business datum；Sift out the abnormal index of business datum triggering；Calculate the Exception Model for the abnormal index triggering being triggered；The business datum included under each abnormal index being triggered included under each Exception Model being triggered is exported, obtains abnormal traffic data.This method is by taking the method that abnormal index, Exception Model screen, i.e. screening technique is combined with business scenario, multiple abnormal indexes meeting the Exception Model trigger condition are screened by way of being triggered, the business datum for making to be sifted out is that the possibility merchandised extremely greatly increases, so as to more effectively sift out abnormal traffic data, this method configuration is flexible, portable strong, can be applied to different data analysis class systems.
Description
Technical field
The present invention relates to data screening method, and in particular to a kind of abnormal traffic data screening method of anti money washing system.
Background technology
In financial industry, the emphasis of Anti-Money Laundering is that client trading behavior is analyzed, and extracts all kinds of wholesales and hands over
Easily, the information such as suspicious transaction, to be further tracked, investigate and to examine.We often choose some abnormal index and go to sieve
Abnormal traffic is selected, but in practical situations both, meet that transaction/client/account of some abnormal index does not represent the transaction row
To certainly exist exception, in order to further strengthen the precision of anti money washing monitoring, it is different that urgent need proposes that one kind is more effectively sifted out
The method often merchandised.
The content of the invention
In view of this, the application provides a kind of abnormal traffic data screening method of anti money washing system, and the application is by adopting
Abnormal index, the mode of Exception Model combined sorting are taken, so that more effectively more accurately screening mode filters out abnormal traffic data.
To solve above technical problem, technical scheme provided by the invention is a kind of abnormal traffic data of anti money washing system
Screening technique, including：
Receive business datum；
According to the trigger condition of default each abnormal index, the abnormal index that business datum triggers is sifted out；
According to the trigger condition of the default each Exception Model being made up of several abnormal indexes, calculate be triggered it is different
The Exception Model of Chang Zhibiao triggerings；
The business datum included under each abnormal index being triggered included under each Exception Model being triggered is exported,
Obtain abnormal traffic data.
Preferably, the trigger condition according to the default each Exception Model being made up of several abnormal indexes, meter
The method of the Exception Model for the abnormal index triggering being triggered, including：
Obtain the score value of each abnormal index included in each Exception Model；
Calculate the total score for the abnormal index being triggered in each Exception Model；
According to the triggering score value of default each Exception Model, the Exception Model being triggered is sifted out.
Preferably, the method for the score value for obtaining each abnormal index included in each Exception Model, including obtain
The score value of each abnormal index included in default each Exception Model.
Preferably, the method for the score value for obtaining each abnormal index included in each Exception Model, including calculate
The score value of each abnormal index included in each Exception Model.
Preferably, the method for the score value for calculating each abnormal index included in each Exception Model, including：
If the total score of Exception Model is X points, and contains N number of abnormal index, then the score value of each abnormal index is X/
N, X and N are the positive integer more than 1.
Preferably, the method for the total score for calculating the abnormal index being triggered in each Exception Model, including：To different
The score value summation for each abnormal index being triggered in norm type.
Preferably, the triggering score value according to default each Exception Model, the side for the Exception Model being triggered is sifted out
Method, including：When the total score for the abnormal index being triggered in Exception Model is more than or equal to the default triggering of the Exception Model
Score value, then the Exception Model be triggered.
Preferably, the business datum that data obtain through integration based on the business datum.
Preferably, method of the basic data through integrating acquisition business datum, including：
Receive the basic data of separate sources and be uniformly converted into txt file storage and arrive specified location；
By data loading tasks, all txt files of specified location are loaded；
By database store process, the txt file layer assembly of loading is turned into business datum.
Preferably, the business datum include business occur frequency data, whereabouts data, time data, count
According to, value data, receipt and payment than data and the abnormal behaviour data of business handling.
Compared with prior art, its advantage describes in detail as follows the application：The abnormal traffic data that the application provides
Screening technique, the method by taking abnormal index, Exception Model combined sorting, i.e. screening technique are combined with business scenario,
Multiple abnormal indexes meeting the Exception Model trigger condition are screened by way of being triggered, and make the business sifted out
Data are that the possibility merchandised extremely greatly increases, and so as to more effectively sift out abnormal traffic data, this method configuration is flexible, can
Transplantability is strong, can be applied to different data analysis class systems.
Brief description of the drawings
Fig. 1 is method flow schematic diagram provided in an embodiment of the present invention；
Fig. 2 is the method flow schematic diagram that another embodiment of the present invention provides.
Embodiment
In order that those skilled in the art more fully understands technical scheme, it is below in conjunction with the accompanying drawings and specific real
Applying example, the present invention is described in further detail.
As shown in figure 1, the embodiment of the present invention provides a kind of abnormal traffic data screening method of anti money washing system, specific bag
Include：
S1：Receive business datum.
Here business datum includes frequency data, whereabouts ground data, time data, locality data, the gold that business occurs
Specified number evidence, receipt and payment are than data and the abnormal behaviour data of business handling etc..The abnormal behaviour of business handling includes：More people handle
Commanded during business by same people on side.Then same commander people is then the abnormal behaviour data of business handling.The business of reception
Data are through integrating the business datum obtained based on data.Method of the basic data through integrating acquisition business datum, including：
Receive the basic data of separate sources and be uniformly converted into txt file storage and arrive specified location；
By data loading tasks, all txt files of specified location are loaded；
By database store process, the txt file layer assembly of loading is turned into business datum.
S2：According to the trigger condition of default each abnormal index, the abnormal index that business datum triggers is sifted out.
Here, according to abnormal index detail list, the abnormal index that business datum meets is sifted out, i.e. these abnormal indexes are touched
Hair.Abnormal index is defined by bank oneself, and the possibility that the abnormal transaction or bank oneself that source behaviour row is announced are analyzed is washed
The merchandising of money risk, situation analysis of external money laundering case etc..The customization of abnormal index is mainly by dividing abnormal traffic
Analysis, split into the rule of system detectio.It is the business feelings for meeting a feature for one single abnormal index is simple
Condition, as day trade transaction accumulating sum reaches 100,000, such as client's daylight trading is more than or equal to 100,000, then meets that the exception refers to
Mark.Such as less than 100,000, then it is unsatisfactory for.
S3：According to the trigger condition of the default each Exception Model being made up of several abnormal indexes, calculating is triggered
Abnormal index triggering Exception Model.
Here, Exception Model is made up of abnormal index, and a model includes multiple abnormal indexes.Here Exception Model is
Defined by bank oneself, the possibility that the abnormal transaction or bank oneself that source behaviour row is announced are analyzed has the friendship of money laundering risks
Easily, situation analysis of external money laundering case etc., case modelling and indexing are decomposed, becomes Exception Model and form abnormal
Each abnormal index of model.
According to the abnormal index and the trigger condition of Exception Model that default Exception Model includes in Exception Model detail list,
Calculate the Exception Model being triggered.Such as when the trigger condition of some Exception Model is triggered for its 5 abnormal index included
I.e. the model is triggered, then when there is 5 abnormal indexes to be triggered in the abnormal index that the Exception Model includes, the Exception Model
Just it is triggered.
S4：Export the business number included under each abnormal index being triggered included under each Exception Model being triggered
According to acquisition abnormal traffic data.
Here, the business datum gone out by abnormal index and Exception Model combined sorting is exported, that is, obtains abnormal traffic
Data, bank can carry out further tracking, investigate and examining according to abnormal traffic data.
As shown in Fig. 2 the embodiment of the present invention provides another more preferably abnormal traffic data screening method, according to default
The trigger condition for each Exception Model being made up of several abnormal indexes, calculate the abnormal mould for the abnormal index triggering being triggered
The method of type, including：
S31：Obtain the score value of each abnormal index included in each Exception Model.
Here, the method for obtaining the score value of each abnormal index included in each Exception Model, can be to be preset
Each Exception Model in the score value of each abnormal index that includes.
Here, the method for obtaining the score value of each abnormal index included in each Exception Model, or calculate every
The score value of each abnormal index included in individual Exception Model.Exception Model is made up of abnormal index, and an Exception Model includes
Multiple abnormal indexes, such as an Exception Model A, include a1, a2, a3, tetra- abnormal indexes of a4, each abnormal index score value 25
Point, the score value of Exception Model triggering sets 50 points, such as triggers any two abnormal index, then this Exception Model triggers.
Here the method for calculating the score value of each abnormal index included in each Exception Model, including：
If the total score of Exception Model is X points, and contains N number of abnormal index, then the score value of each abnormal index is X/
N, X and N are the positive integer more than 1.
S32：Calculate the total score for the abnormal index being triggered in each Exception Model.
Here, the method for calculating the total score for the abnormal index being triggered in each Exception Model, including：To Exception Model
In be triggered each abnormal index score value summation.
S33：According to the triggering score value of default each Exception Model, the Exception Model being triggered is sifted out.
Here, according to the triggering score value of default each Exception Model in Exception Model detail list, sift out be triggered it is different
The method of norm type, including：When the total score for the abnormal index being triggered in Exception Model is more than or equal to the Exception Model
Default triggering score value, then the Exception Model be triggered.
It the above is only the preferred embodiment of the present invention, it is noted that above-mentioned preferred embodiment is not construed as pair
The limitation of the present invention, protection scope of the present invention should be defined by claim limited range.For the art
For those of ordinary skill, without departing from the spirit and scope of the present invention, some improvements and modifications can also be made, these change
Enter and retouch and also should be regarded as protection scope of the present invention.
Claims (10)
1. a kind of abnormal traffic data screening method of anti money washing system, it is characterised in that including：
Receive business datum；
According to the trigger condition of default each abnormal index, the abnormal index that business datum triggers is sifted out；
According to the trigger condition of the default each Exception Model being made up of several abnormal indexes, calculate the exception being triggered and refer to
Mark the Exception Model of triggering；
The business datum included under each abnormal index being triggered included under each Exception Model being triggered is exported, is obtained
Abnormal traffic data.
2. the abnormal traffic data screening method of anti money washing system according to claim 1, it is characterised in that the basis
The trigger condition of the default each Exception Model being made up of several abnormal indexes, calculate what the abnormal index being triggered triggered
The method of Exception Model, including：
Obtain the score value of each abnormal index included in each Exception Model；
Calculate the total score for the abnormal index being triggered in each Exception Model；
According to the triggering score value of default each Exception Model, the Exception Model being triggered is sifted out.
3. the abnormal traffic data screening method of anti money washing system according to claim 2, it is characterised in that the acquisition
The method of the score value of each abnormal index included in each Exception Model, including obtain and included in default each Exception Model
Each abnormal index score value.
4. the abnormal traffic data screening method of anti money washing system according to claim 2, it is characterised in that the acquisition
Included in the method for the score value of each abnormal index included in each Exception Model, including each Exception Model of calculating each
The score value of abnormal index.
5. the abnormal traffic data screening method of anti money washing system according to claim 4, it is characterised in that the calculating
The method of the score value of each abnormal index included in each Exception Model, including：
If the total score of Exception Model is X point, and contain N number of abnormal index, then the score value of each abnormal index be X/N, X with
N is the positive integer more than 1.
6. the abnormal traffic data screening method of anti money washing system according to claim 2, it is characterised in that the calculating
The method of the total score for the abnormal index being triggered in each Exception Model, including：It is each different to what is be triggered in Exception Model
Chang Zhibiao score value summation.
7. the abnormal traffic data screening method of anti money washing system according to claim 2, it is characterised in that the basis
The triggering score value of default each Exception Model, the method for sifting out the Exception Model being triggered, including：Touched when in Exception Model
The total score of the abnormal index of hair is more than or equal to the default triggering score value of the Exception Model, then the Exception Model is triggered.
8. the abnormal traffic data screening method of anti money washing system according to claim 1, it is characterised in that the business
Data are through integrating the business datum obtained based on data.
9. the abnormal traffic data screening method of anti money washing system according to claim 8, it is characterised in that the basis
Method of the data through integrating acquisition business datum, including：
Receive the basic data of separate sources and be uniformly converted into txt file storage and arrive specified location；
By data loading tasks, all txt files of specified location are loaded；
By database store process, the txt file layer assembly of loading is turned into business datum.
10. the abnormal traffic data screening method of anti money washing system according to claim 1, it is characterised in that the industry
Data are compared in data, time data, locality data, value data, receipt and payment to business data with including the frequency data of business generation, whereabouts
With the abnormal behaviour data of business handling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710576257.5A CN107358360A (en) | 2017-07-14 | 2017-07-14 | The abnormal traffic data screening method of anti money washing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710576257.5A CN107358360A (en) | 2017-07-14 | 2017-07-14 | The abnormal traffic data screening method of anti money washing system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107358360A true CN107358360A (en) | 2017-11-17 |
Family
ID=60292644
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710576257.5A Pending CN107358360A (en) | 2017-07-14 | 2017-07-14 | The abnormal traffic data screening method of anti money washing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107358360A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520318A (en) * | 2018-04-02 | 2018-09-11 | 深圳前海桔子信息技术有限公司 | A kind of method for safety monitoring, device, server and storage medium |
| CN109583729A (en) * | 2018-11-19 | 2019-04-05 | 阿里巴巴集团控股有限公司 | Data processing method and device for platform on-time model |
| CN109949149A (en) * | 2019-03-18 | 2019-06-28 | 上海古鳌电子科技股份有限公司 | A kind of fund transfer risk monitoring method |
| CN110659989A (en) * | 2019-09-10 | 2020-01-07 | 马洪富 | Active exploration type compliance anti-money laundering method, device, system and storage medium |
| CN110852884A (en) * | 2019-11-15 | 2020-02-28 | 成都数联铭品科技有限公司 | Data processing system and method for anti-money laundering recognition |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106547838A (en) * | 2016-10-14 | 2017-03-29 | 北京银丰新融科技开发有限公司 | Method based on the suspicious funds transaction of fund network monitor |
| CN106803168A (en) * | 2016-12-30 | 2017-06-06 | 中国银联股份有限公司 | A kind of abnormal transfer accounts method for detecting and device |
| CN106897931A (en) * | 2016-06-12 | 2017-06-27 | 阿里巴巴集团控股有限公司 | A kind of recognition methods of abnormal transaction data and device |
-
2017
- 2017-07-14 CN CN201710576257.5A patent/CN107358360A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106897931A (en) * | 2016-06-12 | 2017-06-27 | 阿里巴巴集团控股有限公司 | A kind of recognition methods of abnormal transaction data and device |
| CN106547838A (en) * | 2016-10-14 | 2017-03-29 | 北京银丰新融科技开发有限公司 | Method based on the suspicious funds transaction of fund network monitor |
| CN106803168A (en) * | 2016-12-30 | 2017-06-06 | 中国银联股份有限公司 | A kind of abnormal transfer accounts method for detecting and device |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108520318A (en) * | 2018-04-02 | 2018-09-11 | 深圳前海桔子信息技术有限公司 | A kind of method for safety monitoring, device, server and storage medium |
| CN109583729A (en) * | 2018-11-19 | 2019-04-05 | 阿里巴巴集团控股有限公司 | Data processing method and device for platform on-time model |
| CN109949149A (en) * | 2019-03-18 | 2019-06-28 | 上海古鳌电子科技股份有限公司 | A kind of fund transfer risk monitoring method |
| CN110659989A (en) * | 2019-09-10 | 2020-01-07 | 马洪富 | Active exploration type compliance anti-money laundering method, device, system and storage medium |
| CN110852884A (en) * | 2019-11-15 | 2020-02-28 | 成都数联铭品科技有限公司 | Data processing system and method for anti-money laundering recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107358360A (en) | The abnormal traffic data screening method of anti money washing system | |
| US9373144B1 (en) | Diversity analysis with actionable feedback methodologies | |
| CN109784934A (en) | A kind of transaction risk control method, apparatus and relevant device and medium | |
| WO2017078986A1 (en) | Diversity analysis with actionable feedback methodologies | |
| KR102412433B1 (en) | Automatic data analysis method and system using artificial intelligence | |
| US8984022B1 (en) | Automating growth and evaluation of segmentation trees | |
| CN110297855A (en) | Report Dynamic Display method, apparatus, computer equipment and storage medium | |
| CN110390584A (en) | A kind of recognition methods of abnormal user, identification device and readable storage medium storing program for executing | |
| CN107895311A (en) | A kind of method and apparatus of order matching distribution | |
| CN106649517A (en) | Data mining method, device and system | |
| TAN et al. | Evaluation and improvement of procurement process with data analytics | |
| CN113379530A (en) | User risk determination method and device and server | |
| CN110019774A (en) | Label distribution method, device, storage medium and electronic device | |
| Bhat | An analysis of crime data under apache pig on big data | |
| Mayaki et al. | Multiple inputs neural networks for fraud detection | |
| Wanchai | Customer churn analysis: A case study on the telecommunication industry of Thailand | |
| CN110276691A (en) | A kind of data processing method and device based on big data platform | |
| US20160148318A1 (en) | Policy System | |
| US11182818B1 (en) | Computer system for identifying aberrant activity on a reward card platform | |
| KR20120023423A (en) | System for integrated trading and providing method thereof | |
| Bagde et al. | Analysis of fraud detection mechanism in health insurance using statistical data mining techniques | |
| CN109213979A (en) | Method, apparatus, electronic equipment and the storage medium that electrical form is screened | |
| JP2013178669A (en) | Tabulation device and tabulation program | |
| Adiputra et al. | Customer Churn Prediction Using Weight Average Ensemble Machine Learning Model | |
| CN109559139A (en) | A kind of processing method of item object, device, medium and electronic equipment |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171117 |