CN106682067A - Machine learning anti-fraud monitoring system based on transaction data - Google Patents
Machine learning anti-fraud monitoring system based on transaction data Download PDFInfo
- Publication number
- CN106682067A CN106682067A CN201610981804.3A CN201610981804A CN106682067A CN 106682067 A CN106682067 A CN 106682067A CN 201610981804 A CN201610981804 A CN 201610981804A CN 106682067 A CN106682067 A CN 106682067A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- engine
- algorithm
- sample
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/25—Integrating or interfacing systems involving database management systems
- G06F16/254—Extract, transform and load [ETL] procedures, e.g. ETL data flows in data warehouses
-
- 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
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Strategic Management (AREA)
- Marketing (AREA)
- Economics (AREA)
- Quality & Reliability (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a machine learning anti-fraud monitoring system based on transaction data. The system comprises a management platform, an ETL module, a sampling engine, a stream processing engine, a training engine, a prediction engine and a decision engine. The stream processing engine rapidly extracts and calculates characteristics of the huge original transaction data through streamed big data processing, the representative characteristics are obtained from the huge original transaction data, and information in the data is sufficiently extracted. In the model training module, various machine learning models and ensemble learning frameworks optimized for the capital loss ratio and the black sample recall ratio are used, and a composite model optimized for an indicator is obtained. The over-fitting and unstable defects due to a single model are overcome, and the stability and the generalization ability of the model are improved; according to a preset update time, the model training module automatically obtain the latest data and trains the model again, accordingly the model keeps the effectiveness all the time, and the problem of model inefficiency due to fraud variation is avoided.
Description
Technical field
The present invention relates to financial field, refers in particular to a kind of anti-fake monitoring system of machine learning based on transaction data.
Background technology
The booming financial revolution for creating a new round of Internet technology, but too fast growth also contains greatly
Blindness, what is be accompanied is the risk of fraud being on the rise.Fake monitoring pattern relatively conventional at present is included based on big number
According to risk policy, anti-fraud system and elite air control team etc..Although most of payment mechanisms have fake monitoring system,
But majority still relies on elite team and rule induction is carried out on the basis of analysis of cases.However, fraudulent mean emerge in an endless stream and
The inconsistent of trading activity brings difficulty to rule induction.Meanwhile, current algorithm is difficult to keep its robustness, performance
Expansion with rule system is declined, it is impossible to ensure there is high recall ratio while high precision ratio, so as to reduce Consumer's Experience.
Machine learning due to its non-linear with cost-sensitive scene advantage, while and be less dependent on manual analyses,
More excellent robustness and stability is shown, so being increasingly becoming a kind of new fraud detection scheme.
The content of the invention
Present invention aims to the problem that prior art is present, there is provided a set of transaction swindling towards financial field
Real-time monitoring system.Historical trading data after to cleaning is analyzed and models, and when New Transaction occurs, will currently hand over
Easy is to be compared with historical trading behavior, real-time judge is carried out to the transaction risk according to the scoring of output, so as to reach
To the target of real-time deal fraud detection.The system can reach higher precision and look into complete in the case of relatively low rate of false alarm
Rate, so as to ensure the transaction security of client.
The purpose of the present invention is achieved through the following technical solutions:A kind of machine learning based on transaction data is counter to take advantage of
Swindleness monitoring system, the system include management platform, ETL module, sample engine, stream process engine, training engine, prediction engine and
Decision engine;
The management platform provides the configuration information of each module, concurrent pattern drawing train request and predictions request, to mould
Type is managed and updates operation;The configuration information includes that the data time needed for ETL module is interval, needed for sample engine
Database field, the feature name and calculation needed for stream process engine trains the algorithm title and algorithm ginseng needed for engine
Number.
The ETL module extracts initial data database data according to the configuration information of management platform, carries out data pick-up, turns
Change, in-stockroom operation;The data transformation operations are mainly cleaned and standardization to data, including two parts:By initial data
The self-defining data in storehouse are converted into normal data;The field that machine learning model cannot be processed is converted;Data loading is grasped
The data being disposed are stored in any frequently-used data storehouse by work.
The sample engine is sampled according to the configuration information of management platform to initial data, is extracted from initial data
The Database field that stream process engine needs.
Feature name and calculation that the stream process engine is configured according to management platform, to sampled data feature is carried out
Extract and calculate.
The training engine includes data cleansing, model training, model evaluation;Data are lacked by the data cleansing
The normal data cleaning operations such as the process of mistake value, normalized;The model training, according to the model parameter of setting, using clear
Characteristic after washing is trained, specially:The algorithm title and algorithm parameter of management platform configuration are read, is called common
Machine learning algorithm, includes supervision algorithm and unsupervised algorithm is learnt;There is supervision algorithm to include logistic regression, linearly return
Return, support vector machine, decision Tree algorithms etc.;Unsupervised algorithm includes k-means clusters etc.;The model evaluation, using new
Data set is evaluated the model for training, according to indexs such as recall ratio, the precision ratio of output, KS values, ROC curves to model
Quality is evaluated, if satisfactory quality can carry out model deployment and use;The model training module is by advance
The renewal time of setting, latest data and again training pattern is obtained automatically, so that model remains effectiveness.
The prediction engine calls the model for training to flowing successively through the reality of ETL module, sample engine, stream process engine
Border transaction data is differentiated that output belongs to the probability of arm's length dealing and belongs to the probability of fraudulent trading, passes to predicting the outcome
Decision engine.
The decision engine carries out decision-making according to the output of prediction engine to the danger of the transaction.
Further, the machine learning algorithm in the training engine, is transformed, specifically for black sample recall ratio
For:The weight bigger than white sample is assigned to black sample losses function so as to be more likely to find out more black samples;Or, it is right
Black sample carries out over-sampling, and white sample carries out lack sampling;Or, regular terms is increased after loss function, model complexity is reduced,
Improve model generalized ability;Or, using integrated study framework, overcome the over-fitting of single model.
Transformed for monetary losses rate, the big weight of the low amount of money is assigned to high amount of money sample, be more likely to model
The high amount of money sample of few misclassification;Or, according to single dealing money dynamic adjustment probability threshold value, make to be more difficult to the transaction of the high amount of money by
It is determined as white sample;
Do for algorithm performance and optimize, using the function that can be performed with parallelization in GPU accelerating algorithms, substantially reduce training
And predicted time;Or, realize the calculating operation of algorithm bottom using linear algebra storehouse;Or, it is parallel using multithreading
Algorithm is realized in change.
Further, stream process engine carries out the fast of feature by the process of streaming big data to huge transaction initial data
Speed is extracted and calculated, can obtain in certain time interval accumulative certain user's history trading volume under certain dimension, accounting, variance,
The characteristic quantities such as average, summation, counting, minimum number statistics, standard deviation statistics calculating, the degree of bias, kurtosis, duplicate removal.
Whole system using can be divided in flow process training and predict two parts.
During training, the information of modules is configured using management platform, and initiate train request, ETL module root
According to configuration information, initial data database data is extracted, carry out data pick-up, conversion, in-stockroom operation.Sample engine is according to configuration to original
Beginning data are sampled, and obtain the Database field for needing.Stream process engine carries out feature extraction and calculating to sampled data, instruction
Practice engine first to clean data, according to the model parameter of setting, be trained using characteristic, then using new
Data the set pair analysis model is estimated, according to multiple indexes judgment models quality, if satisfactory quality can carry out mold portion
Administration and use, so far training part is terminated, otherwise repeatedly aforesaid operations process.
During prediction, ETL module obtains in real time transaction data, sample engine and Liu Chu according to the configuration of gathered data during training
Reason engine is calculated by sampling operation and streaming, obtains characteristic and input model, and prediction engine obtains model output, decision-making
Engine carries out Real-time Decision according to output probability.
The system contrasts prior art and system has obvious advantage, and system can maintain better stability/vigorousness
While, it is ensured that higher recall ratio and relatively low rate of false alarm.Above-mentioned characteristic is mainly by following several promises:Stream process engine leads to
The process of overflow-type big data carries out rapid extraction and the calculating of feature to huge transaction initial data, from magnanimity initial data
Representational feature is obtained, the information in data is fully extracted.Model training module using it is various for monetary losses rate, it is black
Machine learning model and integrated study framework that sample recall ratio optimized, what is obtained is the compound die for certain index optimization
Type, overcomes over-fitting, unstable defect that single model brings, improves the stability and generalization ability of model;Model
Training module obtains latest data and again training pattern, so that model is all the time automatically by the renewal time for pre-setting
Keep effectiveness, it is to avoid the model Problem of Failure that fraud variation brings.
Description of the drawings
Fig. 1 is the structured flowchart of the preferred embodiments of the invention.
Fig. 2 is exemplary timing diagram in the preferred embodiments of the invention.
Specific embodiment
More clearly to illustrate the architectural feature and effect of the present invention, come to this with specific embodiment below in conjunction with the accompanying drawings
It is bright to be described in detail.
As shown in Figure 1, 2, the anti-fake monitoring system of a kind of machine learning based on transaction data that the present invention is provided, including
Management platform, ETL module, sample engine, stream process engine, training engine, prediction engine and decision engine;
Management platform provides the visualization interface of system administration, and the information that user can need each module is flat in management
Configured on platform, each module will be obtained from management platform and configuration information and carries out respective operations automatically.Management platform may be used also
To initiate model training request and predictions request, operation is managed and updated to model.
After train request is received, ETL module obtains the trading activity data of financial sector front end triggering, carries out data and takes out
Take, change, in-stockroom operation.Specifically, the ETL module mainly obtains the data of financial sector trading activity, including during transaction
Between, loco, transaction IP, terminal type (movement, PC ends, operating system classification etc.), dealing money, Transaction Account number etc., this
A little data can be divided mainly into following big class:
1st, trading environment:Including exchange hour, transaction IP, transaction terminal etc..
2nd, transaction content:Including dealing money, transaction account number, trading password etc..
3rd, account number feature:Including regional features, space-time characteristic, sex characteristicss, age characteristicss etc..
4th, aggregated data:Refer to the polymerization amount of data, including transaction count etc. in 3 hours.
5th, other data:Refer to the data with the other side of the account relating.
Data transformation operations are mainly cleaned and standardization to data, mainly including two parts:By raw data base certainly
The data of definition are converted into normal data, such as the time will be converted into the standard time;The field that machine learning model cannot be processed
Converted, such as such as telephone number is converted to ownership place.
Data loading operation is exactly that the data being disposed are stored in into any frequently-used data storehouse, such as Oracle.
Sample engine takes the data of needs by the configuration file of management platform from above-mentioned data base, and configuration file includes
The information such as the time period of desired data, the title of required field, equivalent to a desired data inventory, the data got are stored in
In internal memory.
Stream process engine is calculated the data that sample engine is got, according to the characteristic information needed in management platform,
Initial data is converted into characteristic by engine, and such as certain is characterized in that the accumulative trade gold for calculating each user past 24 hours
Volume, stream process engine will search each user and go over the transaction record of 24 hours and dealing money is added up.Final meter
Good result is deposited hereof, and file can be arbitrary standards form, such as CSV, txt.
Training engine includes data cleansing, model training, model evaluation.First missing values process, normalizing are carried out to data
The normal data cleaning operations such as change process.Then algorithm title and the algorithm parameter configured on management platform interface is read, is called
Common machine learning algorithm, includes supervision algorithm and unsupervised algorithm is learnt.Have supervision algorithm include logistic regression,
Linear regression, support vector machine, decision Tree algorithms etc.;Unsupervised algorithm includes k-means clusters etc..
These algorithms are transformed for black sample recall ratio, specially:It is assigned to than white sample to black sample losses function
Big weight so as to be more likely to find out more black samples;Or, over-sampling is carried out to black sample, white sample carries out owing to adopt
Sample;Or, regular terms is increased after loss function, model complexity is reduced, improve model generalized ability;Or, using integrated
Learning framework, overcomes the over-fitting of single model.
Transformed for monetary losses rate, the big weight of the low amount of money is assigned to high amount of money sample, be more likely to model
The high amount of money sample of few misclassification;Or, according to single dealing money dynamic adjustment probability threshold value, make to be more difficult to the transaction of the high amount of money by
It is determined as white sample;
Do for algorithm performance and optimize, using the function that can be performed with parallelization in GPU accelerating algorithms, substantially reduce training
And predicted time;Or, realize the calculating operation of algorithm bottom using linear algebra storehouse;Or, it is parallel using multithreading
Algorithm is realized in change.
Parameter is adjusted, acquisition meets the model of the index requests such as accuracy rate, recall rate, and using test the set pair analysis model
It is estimated, whether observing and nursing can be with extensive to other data sets.Feedback of the information in training process is to management platform.Finally
The model write file that training is finished carries out persistence.For suitable model will carry out production environment deployment, true friendship is made
Easily data flow through whole system and carry out real-time blocking to possible risk.At the same time, model training module can also pass through
The renewal time for pre-setting, latest data and the suitable model of re -training is obtained automatically, so that model has been remained
Effect property.
Prediction engine and decision engine play a role after model actual deployment, real trade data in units of bar successively
Flow through ETL module, sample engine, stream process engine simultaneously carries out in above-mentioned training process after same operation, obtaining the friendship handled well
Easily data directly input prediction engine, and prediction engine calls the model for training to differentiate this data, and output belongs to just
Often the probability of transaction and the probability for belonging to fraudulent trading, by predicting the outcome decision engine is passed to.Decision engine is according to prediction engine
Output, to carrying out Real-time Decision when transaction.
The present invention design focal point be:Overall gui interface and managing configuration information are provided by management platform, is passed through
ETL module is quickly changed to data, put in storage, and using sampling module extensive raw data set is obtained, big by streaming
Data processing carries out rapid extraction and the calculating of feature to huge transaction initial data, and from magnanimity initial data generation has been obtained
The feature of table.Machine learning algorithm optimizes through various for monetary losses rate, black sample recall ratio, reasonable by arranging
Algorithm parameter, train outstanding model, and the assessment of multiple data sets is carried out to this model.Design by more than, this is
System can carry out accurate decision-making to transaction in real time.
The above, is only presently preferred embodiments of the present invention, and not the technical scope of the present invention is imposed any restrictions,
Therefore any trickle amendment, equivalent variations and the modification that every technical spirit according to the present invention is made to above example, still
Belong in the range of technical solution of the present invention.
Claims (3)
1. the anti-fake monitoring system of a kind of machine learning based on transaction data, it is characterised in that the system include management platform,
ETL module, sample engine, stream process engine, training engine, prediction engine and decision engine;
The management platform provides the configuration information of each module, concurrent pattern drawing train request and predictions request, and model is entered
Row management and renewal operation;The configuration information includes that the data time needed for ETL module is interval, the data needed for sample engine
Storehouse field, the feature name and calculation needed for stream process engine trains the algorithm title and algorithm parameter needed for engine.
The ETL module extracts initial data database data according to the configuration information of management platform, carries out data pick-up, changes, enters
Storehouse operates;The data transformation operations are mainly cleaned and standardization to data, including two parts:Raw data base is made by oneself
The data of justice are converted into normal data;The field that machine learning model cannot be processed is converted;Data loading operation will place
The data that reason is finished are stored in any frequently-used data storehouse.
The sample engine is sampled according to the configuration information of management platform to initial data, is extracted at stream from initial data
The Database field that reason engine needs.
Feature name and calculation that the stream process engine is configured according to management platform, to sampled data feature extraction is carried out
And calculating.
The training engine includes data cleansing, model training, model evaluation;Data are carried out missing values by the data cleansing
The normal data cleaning operation such as process, normalized;The model training, according to the model parameter of setting, after cleaning
Characteristic be trained, specially:The algorithm title and algorithm parameter of management platform configuration are read, common machine is called
Learning algorithm, includes supervision algorithm and unsupervised algorithm is learnt;Have supervision algorithm include logistic regression, linear regression,
Support vector machine, decision Tree algorithms etc.;Unsupervised algorithm includes k-means clusters etc.;The model evaluation, using new data
The model that set pair is trained is evaluated, according to indexs such as recall ratio, the precision ratio of output, KS values, ROC curves to model quality
Evaluated, if satisfactory quality can carry out model deployment and use;The model training module is by pre-setting
The renewal time, latest data and again training pattern are obtained automatically, so that model remains effectiveness.
The prediction engine calls the model for training to flowing successively through the actual friendship of ETL module, sample engine, stream process engine
Easily data are differentiated that output belongs to the probability of arm's length dealing and belongs to the probability of fraudulent trading, and by predicting the outcome decision-making is passed to
Engine.
The decision engine carries out decision-making according to the output of prediction engine to the danger of the transaction.
2. the anti-fake monitoring system of a kind of machine learning based on transaction data according to claim 1, it is characterised in that
Machine learning algorithm in the training engine, is transformed, specially for black sample recall ratio:To black sample losses function
It is assigned to the weight bigger than white sample so as to be more likely to find out more black samples;Or, over-sampling is carried out to black sample, in vain
Sample carries out lack sampling;Or, regular terms is increased after loss function, model complexity is reduced, improve model generalized ability;Or
Person, using integrated study framework, overcomes the over-fitting of single model.
Transformed for monetary losses rate, the big weight of the low amount of money is assigned to high amount of money sample, make model be more likely to few point
Wrong high amount of money sample;Or, according to single dealing money dynamic adjustment probability threshold value, make that the transaction of the high amount of money is more difficult to be differentiated
For white sample;
Do for algorithm performance and optimize, using the function that can be performed with parallelization in GPU accelerating algorithms, substantially reduce and train and pre-
The survey time;Or, realize the calculating operation of algorithm bottom using linear algebra storehouse;Or, using multithreading parallelization reality
Existing algorithm.
3. the anti-fake monitoring system of a kind of machine learning based on transaction data according to claim 1, it is characterised in that
Stream process engine carries out rapid extraction and the calculating of feature by the process of streaming big data to huge transaction initial data, can be with
Obtain in certain time interval accumulative certain user's history trading volume under certain dimension, accounting, variance, average, summation, counting, most
The characteristic quantities such as decimal statistics, standard deviation statistics calculating, the degree of bias, kurtosis, duplicate removal.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610981804.3A CN106682067B (en) | 2016-11-08 | 2016-11-08 | A kind of anti-fake monitoring system of machine learning based on transaction data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610981804.3A CN106682067B (en) | 2016-11-08 | 2016-11-08 | A kind of anti-fake monitoring system of machine learning based on transaction data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106682067A true CN106682067A (en) | 2017-05-17 |
CN106682067B CN106682067B (en) | 2018-05-01 |
Family
ID=58839430
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610981804.3A Active CN106682067B (en) | 2016-11-08 | 2016-11-08 | A kind of anti-fake monitoring system of machine learning based on transaction data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106682067B (en) |
Cited By (36)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107566358A (en) * | 2017-08-25 | 2018-01-09 | 腾讯科技(深圳)有限公司 | A kind of Risk-warning reminding method, device, medium and equipment |
CN107563884A (en) * | 2017-07-28 | 2018-01-09 | 浙江邦盛科技有限公司 | A kind of method for reducing loss of assets rate |
CN107785058A (en) * | 2017-07-24 | 2018-03-09 | 平安科技(深圳)有限公司 | Anti- fraud recognition methods, storage medium and the server for carrying safety brain |
CN108038701A (en) * | 2018-03-20 | 2018-05-15 | 杭州恩牛网络技术有限公司 | A kind of integrated study is counter to cheat test method and system |
CN108053318A (en) * | 2017-12-20 | 2018-05-18 | 北京奇安信科技有限公司 | It is a kind of to the method and device that is identified of merchandising extremely |
CN108122114A (en) * | 2017-12-25 | 2018-06-05 | 同济大学 | For abnormal repeat business fraud detection method, system, medium and equipment |
CN108446720A (en) * | 2018-02-27 | 2018-08-24 | 华青融天(北京)技术股份有限公司 | Abnormal deviation data examination method and system |
CN108446978A (en) * | 2018-02-12 | 2018-08-24 | 阿里巴巴集团控股有限公司 | Handle the method and device of transaction data |
CN108765135A (en) * | 2018-05-29 | 2018-11-06 | 佛山市金晶微阅信息科技有限公司 | A kind of credit is counter to cheat identifying system |
CN109086975A (en) * | 2018-07-10 | 2018-12-25 | 阿里巴巴集团控股有限公司 | A kind of recognition methods of transaction risk and device |
CN109299434A (en) * | 2018-09-04 | 2019-02-01 | 重庆公共运输职业学院 | Cargo customs clearance big data is intelligently graded and sampling observation rate computing system |
CN109308615A (en) * | 2018-08-02 | 2019-02-05 | 同济大学 | Real-time fraudulent trading detection method, system, storage medium and electric terminal based on statistical series feature |
CN109344394A (en) * | 2018-08-30 | 2019-02-15 | 广发证券股份有限公司 | A kind of text class data quality monitoring method and system |
CN109443419A (en) * | 2018-08-31 | 2019-03-08 | 广州市世科高新技术有限公司 | A kind of rectifier on-line monitoring method based on machine learning |
CN109447276A (en) * | 2018-09-17 | 2019-03-08 | 烽火通信科技股份有限公司 | A kind of machine learning method, system, equipment and application method |
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 |
CN109635948A (en) * | 2018-12-19 | 2019-04-16 | 北京达佳互联信息技术有限公司 | On-line training method, apparatus, system and computer readable storage medium |
CN109726239A (en) * | 2018-12-25 | 2019-05-07 | 厦门市美亚柏科信息股份有限公司 | The method, apparatus and readable storage medium storing program for executing that a kind of pair of forensic data is analyzed |
WO2019128514A1 (en) * | 2017-12-29 | 2019-07-04 | 阿里巴巴集团控股有限公司 | Method and device for pushing information and method and device for determining default input value |
CN110008984A (en) * | 2019-01-22 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of object module training method and device based on multitask sample |
CN110111106A (en) * | 2019-05-06 | 2019-08-09 | 无线生活(北京)信息技术有限公司 | Transaction risk monitoring method and device |
CN110334720A (en) * | 2018-03-30 | 2019-10-15 | 百度在线网络技术(北京)有限公司 | Feature extracting method, device, server and the storage medium of business datum |
WO2019233117A1 (en) * | 2018-06-06 | 2019-12-12 | 众安信息技术服务有限公司 | Routing method, device and equipment for on-line analytical processing engine |
CN110830515A (en) * | 2019-12-13 | 2020-02-21 | 支付宝(杭州)信息技术有限公司 | Flow detection method and device and electronic equipment |
CN110892442A (en) * | 2017-06-02 | 2020-03-17 | 维萨国际服务协会 | System, method and apparatus for adaptive scoring to detect misuse or abuse of business cards |
CN110888861A (en) * | 2019-11-12 | 2020-03-17 | 上海麦克风文化传媒有限公司 | Novel big data storage method |
CN110956278A (en) * | 2019-11-26 | 2020-04-03 | 支付宝(杭州)信息技术有限公司 | Method and system for retraining machine learning models |
CN111461216A (en) * | 2020-03-31 | 2020-07-28 | 浙江邦盛科技有限公司 | Case risk identification method based on machine learning |
TWI712981B (en) * | 2018-12-13 | 2020-12-11 | 開曼群島商創新先進技術有限公司 | Risk identification model training method, device and server |
CN112651785A (en) * | 2020-12-31 | 2021-04-13 | 中国农业银行股份有限公司 | Real-time monitoring method and system for transaction amount |
CN111861699B (en) * | 2020-07-02 | 2021-06-22 | 北京睿知图远科技有限公司 | Anti-fraud index generation method based on operator data |
CN113506109A (en) * | 2021-07-27 | 2021-10-15 | 中国工商银行股份有限公司 | Fraud transaction identification method and device |
TWI760254B (en) * | 2020-02-13 | 2022-04-01 | 華南商業銀行股份有限公司 | Automatic fund depositing method using neural network |
TWI764767B (en) * | 2019-02-13 | 2022-05-11 | 華南商業銀行股份有限公司 | Automatic fund depositing system for planning customized deposit transfer amount |
CN115082076A (en) * | 2022-07-04 | 2022-09-20 | 北京天德科技有限公司 | Three-stage financial violation multiple judgment method based on block chain |
CN116596532A (en) * | 2022-11-07 | 2023-08-15 | 北京天德科技有限公司 | Supervision method based on real-time suspicious transaction identification and supervision blockchain wallet |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103793484A (en) * | 2014-01-17 | 2014-05-14 | 五八同城信息技术有限公司 | Fraudulent conduct identification system based on machine learning in classified information website |
CN104679777A (en) * | 2013-12-02 | 2015-06-03 | 中国银联股份有限公司 | Method and system for detecting fraudulent trading |
CN106022508A (en) * | 2016-05-06 | 2016-10-12 | 陈丛威 | Method and apparatus for predicting user friend invitation behaviors of online financing platform |
-
2016
- 2016-11-08 CN CN201610981804.3A patent/CN106682067B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104679777A (en) * | 2013-12-02 | 2015-06-03 | 中国银联股份有限公司 | Method and system for detecting fraudulent trading |
CN103793484A (en) * | 2014-01-17 | 2014-05-14 | 五八同城信息技术有限公司 | Fraudulent conduct identification system based on machine learning in classified information website |
CN106022508A (en) * | 2016-05-06 | 2016-10-12 | 陈丛威 | Method and apparatus for predicting user friend invitation behaviors of online financing platform |
Cited By (45)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110892442A (en) * | 2017-06-02 | 2020-03-17 | 维萨国际服务协会 | System, method and apparatus for adaptive scoring to detect misuse or abuse of business cards |
CN107785058A (en) * | 2017-07-24 | 2018-03-09 | 平安科技(深圳)有限公司 | Anti- fraud recognition methods, storage medium and the server for carrying safety brain |
CN107563884A (en) * | 2017-07-28 | 2018-01-09 | 浙江邦盛科技有限公司 | A kind of method for reducing loss of assets rate |
CN107566358B (en) * | 2017-08-25 | 2020-10-30 | 腾讯科技(深圳)有限公司 | Risk early warning prompting method, device, medium and equipment |
CN107566358A (en) * | 2017-08-25 | 2018-01-09 | 腾讯科技(深圳)有限公司 | A kind of Risk-warning reminding method, device, medium and equipment |
CN108053318B (en) * | 2017-12-20 | 2021-09-03 | 奇安信科技集团股份有限公司 | Method and device for identifying abnormal transactions |
CN108053318A (en) * | 2017-12-20 | 2018-05-18 | 北京奇安信科技有限公司 | It is a kind of to the method and device that is identified of merchandising extremely |
CN108122114A (en) * | 2017-12-25 | 2018-06-05 | 同济大学 | For abnormal repeat business fraud detection method, system, medium and equipment |
US11087402B2 (en) | 2017-12-29 | 2021-08-10 | Advanced New Technologies Co., Ltd. | Method and device for pushing information and method and device for determining default input value |
WO2019128514A1 (en) * | 2017-12-29 | 2019-07-04 | 阿里巴巴集团控股有限公司 | Method and device for pushing information and method and device for determining default input value |
CN108446978A (en) * | 2018-02-12 | 2018-08-24 | 阿里巴巴集团控股有限公司 | Handle the method and device of transaction data |
CN108446720A (en) * | 2018-02-27 | 2018-08-24 | 华青融天(北京)技术股份有限公司 | Abnormal deviation data examination method and system |
CN108038701A (en) * | 2018-03-20 | 2018-05-15 | 杭州恩牛网络技术有限公司 | A kind of integrated study is counter to cheat test method and system |
CN110334720A (en) * | 2018-03-30 | 2019-10-15 | 百度在线网络技术(北京)有限公司 | Feature extracting method, device, server and the storage medium of business datum |
CN108765135A (en) * | 2018-05-29 | 2018-11-06 | 佛山市金晶微阅信息科技有限公司 | A kind of credit is counter to cheat identifying system |
WO2019233117A1 (en) * | 2018-06-06 | 2019-12-12 | 众安信息技术服务有限公司 | Routing method, device and equipment for on-line analytical processing engine |
CN109086975A (en) * | 2018-07-10 | 2018-12-25 | 阿里巴巴集团控股有限公司 | A kind of recognition methods of transaction risk and device |
CN109308615A (en) * | 2018-08-02 | 2019-02-05 | 同济大学 | Real-time fraudulent trading detection method, system, storage medium and electric terminal based on statistical series feature |
CN109308615B (en) * | 2018-08-02 | 2020-12-29 | 同济大学 | Real-time fraud transaction detection method, system, storage medium and electronic terminal based on statistical sequence characteristics |
CN109344394A (en) * | 2018-08-30 | 2019-02-15 | 广发证券股份有限公司 | A kind of text class data quality monitoring method and system |
CN109443419A (en) * | 2018-08-31 | 2019-03-08 | 广州市世科高新技术有限公司 | A kind of rectifier on-line monitoring method based on machine learning |
CN109443419B (en) * | 2018-08-31 | 2021-08-31 | 广州致新电力科技有限公司 | Machine learning-based rectifier online monitoring method |
CN109299434A (en) * | 2018-09-04 | 2019-02-01 | 重庆公共运输职业学院 | Cargo customs clearance big data is intelligently graded and sampling observation rate computing system |
CN109299434B (en) * | 2018-09-04 | 2019-06-14 | 重庆公共运输职业学院 | Cargo customs clearance big data is intelligently graded and sampling observation rate computing system |
CN109447276B (en) * | 2018-09-17 | 2021-11-02 | 烽火通信科技股份有限公司 | Machine learning system, equipment and application method |
CN109447276A (en) * | 2018-09-17 | 2019-03-08 | 烽火通信科技股份有限公司 | A kind of machine learning method, system, equipment and application method |
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 |
TWI712981B (en) * | 2018-12-13 | 2020-12-11 | 開曼群島商創新先進技術有限公司 | Risk identification model training method, device and server |
CN109635948A (en) * | 2018-12-19 | 2019-04-16 | 北京达佳互联信息技术有限公司 | On-line training method, apparatus, system and computer readable storage medium |
CN109726239A (en) * | 2018-12-25 | 2019-05-07 | 厦门市美亚柏科信息股份有限公司 | The method, apparatus and readable storage medium storing program for executing that a kind of pair of forensic data is analyzed |
CN110008984A (en) * | 2019-01-22 | 2019-07-12 | 阿里巴巴集团控股有限公司 | A kind of object module training method and device based on multitask sample |
TWI764767B (en) * | 2019-02-13 | 2022-05-11 | 華南商業銀行股份有限公司 | Automatic fund depositing system for planning customized deposit transfer amount |
CN110111106A (en) * | 2019-05-06 | 2019-08-09 | 无线生活(北京)信息技术有限公司 | Transaction risk monitoring method and device |
CN110888861A (en) * | 2019-11-12 | 2020-03-17 | 上海麦克风文化传媒有限公司 | Novel big data storage method |
CN110956278A (en) * | 2019-11-26 | 2020-04-03 | 支付宝(杭州)信息技术有限公司 | Method and system for retraining machine learning models |
CN110830515A (en) * | 2019-12-13 | 2020-02-21 | 支付宝(杭州)信息技术有限公司 | Flow detection method and device and electronic equipment |
TWI760254B (en) * | 2020-02-13 | 2022-04-01 | 華南商業銀行股份有限公司 | Automatic fund depositing method using neural network |
CN111461216A (en) * | 2020-03-31 | 2020-07-28 | 浙江邦盛科技有限公司 | Case risk identification method based on machine learning |
CN111461216B (en) * | 2020-03-31 | 2023-08-25 | 浙江邦盛科技股份有限公司 | Case risk identification method based on machine learning |
CN111861699B (en) * | 2020-07-02 | 2021-06-22 | 北京睿知图远科技有限公司 | Anti-fraud index generation method based on operator data |
CN112651785A (en) * | 2020-12-31 | 2021-04-13 | 中国农业银行股份有限公司 | Real-time monitoring method and system for transaction amount |
CN112651785B (en) * | 2020-12-31 | 2023-12-08 | 中国农业银行股份有限公司 | Transaction amount real-time monitoring method and system |
CN113506109A (en) * | 2021-07-27 | 2021-10-15 | 中国工商银行股份有限公司 | Fraud transaction identification method and device |
CN115082076A (en) * | 2022-07-04 | 2022-09-20 | 北京天德科技有限公司 | Three-stage financial violation multiple judgment method based on block chain |
CN116596532A (en) * | 2022-11-07 | 2023-08-15 | 北京天德科技有限公司 | Supervision method based on real-time suspicious transaction identification and supervision blockchain wallet |
Also Published As
Publication number | Publication date |
---|---|
CN106682067B (en) | 2018-05-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106682067A (en) | Machine learning anti-fraud monitoring system based on transaction data | |
CN107742127A (en) | A kind of improved anti-electricity-theft intelligent early-warning system and method | |
CN109343344A (en) | Cigarette machine operating parameter optimization method | |
CN107705149A (en) | Data method for real-time monitoring, device, terminal device and storage medium | |
TW201732662A (en) | Method and apparatus for establishing data identification model | |
CN106127522A (en) | Dig based on network data and analyze method and system according to the enterprise management condition of technology | |
CN101714273A (en) | Rule engine-based method and system for monitoring exceptional service of bank | |
Sridhar et al. | Multi-head self-attention transformer for dogecoin price prediction | |
CN110490486B (en) | Enterprise big data management system | |
CN110349027A (en) | Pairs trade system based on deeply study | |
CN104850868A (en) | Customer segmentation method based on k-means and neural network cluster | |
CN111798310A (en) | Rejection inference method based on Cox regression and logistic regression and electronic equipment | |
CN111639850A (en) | Quality evaluation method and system for multi-source heterogeneous data | |
CN112330095A (en) | Quality management method based on decision tree algorithm | |
CN116468536A (en) | Automatic risk control rule generation method | |
CN108830603A (en) | transaction identification method and device | |
CN104484277B (en) | Process data dynamic analysis device and its application method based on control point | |
CN116992346A (en) | Enterprise production data processing system based on artificial intelligence big data analysis | |
KR20110114181A (en) | Loan underwriting method for improving forecasting accuracy | |
Luo et al. | Stock market forecasting algorithm based on improved neural network | |
EP3493082A1 (en) | A method of exploring databases of time-stamped data in order to discover dependencies between the data and predict future trends | |
CN115623004A (en) | Block chain-based rail transit equipment management system and method | |
CN115392663A (en) | Data acquisition and processing method based on big data | |
Yang et al. | Knowledge discovery on customer churn prediction | |
CN110659681A (en) | Time sequence data prediction system and method based on pattern recognition |
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 | ||
CP01 | Change in the name or title of a patent holder | ||
CP01 | Change in the name or title of a patent holder |
Address after: Room ABCD, 17th floor, building D, Paradise Software Park, No.3 xidoumen Road, Xihu District, Hangzhou City, Zhejiang Province, 310012 Patentee after: Zhejiang Bangsheng Technology Co.,Ltd. Address before: Room ABCD, 17th floor, building D, Paradise Software Park, No.3 xidoumen Road, Xihu District, Hangzhou City, Zhejiang Province, 310012 Patentee before: ZHEJIANG BANGSUN TECHNOLOGY Co.,Ltd. |