CN110795466A - Anti-fraud method based on big data processing, server and computer-readable storage medium - Google Patents
Anti-fraud method based on big data processing, server and computer-readable storage medium Download PDFInfo
- Publication number
- CN110795466A CN110795466A CN201910881748.XA CN201910881748A CN110795466A CN 110795466 A CN110795466 A CN 110795466A CN 201910881748 A CN201910881748 A CN 201910881748A CN 110795466 A CN110795466 A CN 110795466A
- Authority
- CN
- China
- Prior art keywords
- data
- fraud
- applicant
- processing
- structured
- 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
- 238000012545 processing Methods 0.000 title claims abstract description 177
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000011218 segmentation Effects 0.000 claims abstract description 9
- 238000013210 evaluation model Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000011835 investigation Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 17
- 230000006399 behavior Effects 0.000 description 15
- 230000008569 process Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 238000012937 correction Methods 0.000 description 4
- 238000012502 risk assessment Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007621 cluster analysis Methods 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 238000007418 data mining Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000013467 fragmentation Methods 0.000 description 2
- 238000006062 fragmentation reaction Methods 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000026676 system process Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008094 contradictory effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000000547 structure data Methods 0.000 description 1
Images
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
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- 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
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Accounting & Taxation (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Data Mining & Analysis (AREA)
- General Business, Economics & Management (AREA)
- Technology Law (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a big data processing technology, and discloses an anti-fraud method based on big data processing, which comprises the following steps: when a data processing request is received, carrying out exhaustive splitting on the applicant address stage by stage, extracting address characteristic data, carrying out segmentation splitting on the applicant telephone number, and extracting telephone number characteristic data; integrating the address characteristic data and the telephone number characteristic data to generate preprocessed data; acquiring and processing personal historical data and associated data of an applicant inside and outside to generate structured global data; importing the preprocessed data and the structured global data into an anti-fraud evaluation model to calculate to obtain a fraud score value of the applicant; and feeding back a corresponding service processing suggestion according to the fraud score value of the applicant, and stopping service processing and generating a fraud prompt when the score value exceeds a preset value. The invention also provides a server and a computer readable storage medium, which can improve the accuracy and the real-time performance of anti-fraud in banking industry.
Description
Technical Field
The invention relates to the technical field of big data processing, in particular to an anti-fraud method based on big data processing, a server and a computer-readable storage medium.
Background
In recent years, financial fraud crimes highlight the characteristics of non-contact and disguise, and criminal committing means are developing towards the direction of specialization, intellectualization and unitization along with the improvement of the quality of committees and the progress of scientific technology. However, financial institutions such as large, medium and small commercial banks, payment institutions and the like have great difference in anti-fraud work effect, particularly, small and medium institutions are still in a starting stage, and are in a relatively lagged state in the application of advanced technologies, such as a large data storage technology and a large data processing technology, so that the capacity of rapidly and effectively identifying and dealing with fraud behaviors is lacked, and the property safety of financial platforms such as a plurality of banks, network credits and the like and users is seriously damaged.
Disclosure of Invention
In view of this, the present invention provides an anti-fraud method, a server and a computer-readable storage medium based on big data processing, which can improve the accuracy and real-time performance of enterprise anti-fraud, and reduce fraud risk and loss thereof.
Firstly, in order to achieve the above object, the present invention provides an anti-fraud method based on big data processing, which comprises the steps of:
when a data processing request is received, carrying out exhaustive splitting on the applicant address stage by stage, extracting address characteristic data, carrying out segmentation splitting on the applicant telephone number, and extracting telephone number characteristic data;
integrating the address characteristic data and the telephone number characteristic data to generate preprocessed data;
acquiring and processing personal historical data and associated data of the applicant inside and outside to generate structured global data;
importing the preprocessed data and the structured global data into an anti-fraud assessment model to calculate the fraud score value of the applicant;
and feeding back a corresponding service processing suggestion according to the fraud score value of the applicant, and stopping service processing and generating a fraud prompt when the score value exceeds a preset value.
Optionally, the acquiring and processing personal history data and associated data inside and outside the applicant, integrating the preprocessed data, and generating the structured global data specifically includes the following steps:
extracting the internal personal historical data and the associated data of the applicant from an internal database, and performing structuring processing to obtain structured internal data;
extracting external personal historical data and associated data of the applicant from external credit investigation data, and performing structuring processing to obtain structured external data;
and integrating the preprocessed data, the structured internal data and the structured external data to obtain structured global data.
Optionally, the step of importing the preprocessed data and the structured global data into an anti-fraud assessment model to calculate a fraud score of the applicant includes the following steps:
importing the preprocessed data and the structured global data into an anti-fraud assessment model for processing;
and matching the processing result with the scoring card to obtain the fraud scoring value of the applicant.
Optionally, the step of feeding back a corresponding service processing suggestion according to the fraud score value of the applicant, and when the score value exceeds a preset value, stopping service processing and generating a fraud prompt includes the following steps:
when the fraud score value of the applicant is received, the server automatically matches an anti-fraud processing rule;
and feeding back a corresponding service processing suggestion according to the matching result, and stopping service processing and generating a fraud prompt when the score value exceeds a preset value.
Optionally, before the step of performing exhaustive splitting on the applicant address stage by stage and extracting the address feature data, the step of performing segmentation splitting on the applicant phone number and extracting the phone number feature data when receiving the data processing request further includes the following steps:
matching the application information of the applicant with a service controlled list, and judging whether the applicant belongs to a controlled executor or not;
and if the applicant belongs to the controlled executed person, feeding back the state of the controlled executed person and rejecting the service request of the applicant. In addition, in order to achieve the above object, the present invention further provides a server, including a memory and a processor, where the memory stores thereon a big data processing based anti-fraud system operable on the processor, and when executed by the processor, the big data processing based anti-fraud system implements the following steps of a big data processing based anti-fraud method:
when a data processing request is received, carrying out exhaustive splitting on the applicant address stage by stage, extracting address characteristic data, carrying out segmentation splitting on the applicant telephone number, and extracting telephone number characteristic data;
integrating the address characteristic data and the telephone number characteristic data to generate preprocessed data;
acquiring and processing personal historical data and associated data of the applicant inside and outside to generate structured global data;
importing the preprocessed data and the structured global data into an anti-fraud assessment model to calculate the fraud score value of the applicant;
and feeding back a corresponding service processing suggestion according to the fraud score value of the applicant, and stopping service processing and generating a fraud prompt when the score value exceeds a preset value.
Optionally, the acquiring and processing personal history data and associated data inside and outside the applicant, integrating the preprocessed data, and generating the structured global data specifically includes the following steps:
extracting the internal personal historical data and the associated data of the applicant from an internal database, and performing structuring processing to obtain structured internal data;
extracting external personal historical data and associated data of the applicant from external credit investigation data, and performing structuring processing to obtain structured external data;
integrating the preprocessed data, the structured internal data and the structured external data to obtain structured global data
Optionally, the step of importing the preprocessed data and the structured global data into an anti-fraud assessment model to calculate a fraud score of the applicant includes the following steps:
importing the preprocessed data and the structured global data into an anti-fraud assessment model for processing;
and matching the processing result with the scoring card to obtain the fraud scoring value of the applicant.
Optionally, the step of feeding back a corresponding service processing suggestion according to the fraud score value of the applicant, and when the score value exceeds a preset value, stopping service processing and generating a fraud prompt includes the following steps:
when the fraud score value of the applicant is received, the server automatically matches an anti-fraud processing rule;
and feeding back a corresponding service processing suggestion according to the matching result, and stopping service processing and generating a fraud prompt when the score value exceeds a preset value.
Optionally, before the step of performing exhaustive splitting on the applicant address stage by stage and extracting the address feature data, the step of performing segmentation splitting on the applicant phone number and extracting the phone number feature data when receiving the data processing request further includes the following steps:
matching the application information of the applicant with a service controlled list, and judging whether the applicant belongs to a controlled executor or not;
and if the applicant belongs to the controlled executed person, feeding back the state of the controlled executed person and rejecting the service request of the applicant.
Further, to achieve the above object, the present invention also provides a computer-readable storage medium storing a big data processing based anti-fraud system, which is executable by at least one processor to cause the at least one processor to execute the steps of the big data processing based anti-fraud method as described above.
Compared with the prior art, the anti-fraud method based on big data processing, the server and the computer readable storage medium provided by the invention can improve the accuracy and real-time performance of anti-fraud in banking industry and reduce fraud risk and loss caused by fraud risk.
Drawings
FIG. 1 is a schematic diagram of an alternative hardware architecture for a server according to the present invention;
FIG. 2 is a schematic diagram of program modules of a first embodiment of the big data processing based anti-fraud system of the present invention;
FIG. 3 is a schematic diagram of program modules of a second embodiment of the big data processing based anti-fraud system of the present invention;
FIG. 4 is a flow chart of a first embodiment of the anti-fraud method based on big data processing;
FIG. 5 is a flow chart of a second embodiment of the anti-fraud method based on big data processing of the present invention;
FIG. 6 is a flow chart of a third embodiment of the anti-fraud method based on big data processing of the present invention;
the implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the description relating to "first", "second", etc. in the present invention is for descriptive purposes only and is not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In addition, technical solutions between various embodiments may be combined with each other, but must be realized by a person skilled in the art, and when the technical solutions are contradictory or cannot be realized, such a combination should not be considered to exist, and is not within the protection scope of the present invention.
Fig. 1 is a schematic diagram of an alternative hardware architecture of the server 2 according to the present invention.
In this embodiment, the server 2 may include, but is not limited to, a memory 11, a processor 12, and a network interface 13, which may be communicatively connected to each other through a system bus. It is noted that fig. 1 only shows the server 2 with components 11-13, but it is to be understood that not all of the shown components are required to be implemented, and that more or fewer components may be implemented instead.
The server 2 may be a rack server, a blade server, a tower server, or a rack server, and the server 2 may be an independent server or a server cluster formed by a plurality of servers.
The memory 11 includes at least one type of readable storage medium including a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. In some embodiments, the storage 11 may be an internal storage unit of the server 2, such as a hard disk or a memory of the server 2. In other embodiments, the memory 11 may also be an external storage device of the server 2, such as a plug-in hard disk, a Smart Memory Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the server 2. Of course, the memory 11 may also comprise both an internal storage unit of the server 2 and an external storage device thereof. In this embodiment, the memory 11 is generally used for storing an operating system installed in the server 2 and various types of application software, such as program codes of the anti-fraud system 200 based on big data processing. Furthermore, the memory 11 may also be used to temporarily store various types of data that have been output or are to be output.
The processor 12 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 12 is typically used to control the overall operation of the server 2. In this embodiment, the processor 12 is configured to execute the program code stored in the memory 11 or process data, for example, execute the anti-fraud system 200 based on big data processing.
The network interface 13 may comprise a wireless network interface or a wired network interface, and the network interface 13 is generally used for establishing communication connection between the server 2 and other electronic devices.
The hardware structure and functions of the related devices of the present invention have been described in detail so far. Various embodiments of the present invention will be presented based on the above description.
First, the present invention proposes an anti-fraud system 200 based on big data processing.
Referring to fig. 2, a program module diagram of a first embodiment of the big data processing based anti-fraud system 200 of the present invention is shown.
In this embodiment, the big data processing based anti-fraud system 200 includes a series of computer program instructions stored on the memory 11, which when executed by the processor 12, can implement the big data processing based anti-fraud operations of the embodiments of the present invention. In some embodiments, big data processing based anti-fraud system 200 may be divided into one or more modules based on the particular operations implemented by the portions of the computer program instructions. For example, in fig. 2, the big data processing based anti-fraud system 200 may be partitioned into a preprocessing module 201, a generation module 202, a calculation module 203, and a feedback module 204. Wherein:
the preprocessing module 201, when receiving a data processing request, performs exhaustive splitting on the applicant address stage by stage, extracts address characteristic data, performs segmentation splitting on the applicant telephone number, and extracts telephone number characteristic data.
Specifically, anti-fraud of financial enterprises such as banks is a prediction behavior, fraud crimes thereof highlight non-contact and covert characteristics, criminals tend to specialize, intelligentize and group, and property safety of financial platforms such as banks and network credits and users is seriously damaged. Fraud risk analysis and early warning are works with higher difficulty coefficient for commercial banks, and professional talent ability requirements are higher. In order to deal with constantly renovated financial fraud means, financial institutions need to consider active investment of anti-fraud technical means, prevention and control tools and strategies, comprehensively utilize various internal and external basic data, construct an intelligent database, a wind control model, an anti-fraud assessment model and the like based on technologies such as big data storage and big data processing, improve fraud transaction identification rate, and effectively reduce risk loss and capital loss caused by fraud. However, the fraud analysis data commonly used in the industry at present is based on an older batch processing mode, such as an SAS mode, which belongs to a disaster-free single-point mode, and the adoption of a data batch processing mode has low clustering capability, slow aging, limited capacity, poor capacity expansibility, and limited rule mode, and cannot expand rules. When the system processes data, the number of users is often limited to historical data, information among different service systems is relatively isolated, timely transmission, integration and sharing cannot be achieved, and the fragmentation problem is serious; the rule matching prejudgment is based on rule matching prejudgment, the limitation is strong, the traditional rule matching universality is poor, along with the appearance of a new parameter state, a new matching rule is often required to be customized in time to carry out new fraud judgment, and the fraud judgment rule is required to be updated quickly but cannot be met. In order to improve the accuracy and real-time performance of prediction and reduce fraud risk and loss, a business system is required to be capable of collecting and processing behavior data of an applicant in real time. Therefore, the scheme provides a centralized application anti-fraud method based on an elastic search cluster and a big data processing technology, which is stronger in the aspects of instantaneity, flexibility, processing capability expandability and the like, and the ES can provide real-time reliable guarantee in the aspects of searching and analyzing big data.
At present, the situations of group fraud crime are often crime by using the. If there are many reports from public security data or network data in the latest period of an address, the server may also reduce the risk of fraud if it can make corresponding warnings when it receives the service request from the address. Splitting the address is beneficial to structuring the data, and is convenient for completing the data processing more quickly and in real time.
The applicant address comprises a home address, a work address, a past residence address, other permanent addresses, a mobile phone positioning address and the like. For example, when the server receives a home address of 'A province, B city, C district, D district, E district, F district, G unit and XXXX room', the server automatically splits the home address into 8 parts, namely, A province, B city, C district, D district, E district, F district, G unit and XXXX room; when the server receives a working address with the address of 7 parts of the working address, namely 7 layers of YYYY rooms of the H track and the J track of the C area, the I track and the J track of the B city, the A province, the B city, the C area, the H track, the I track, the J layer and the YYYY room.
Fraud is usually sudden, especially when a group crime acts, the crime group may use the same phone number or the same numbers to act within a short time, and if the server can identify and give an early warning in time, it is possible to avoid loss. The telephone number is split, so that the data structuring is facilitated, and the telephone number is provided with the geographic position information, so that the data comparison can be completed more quickly and in real time.
The telephone number comprises the mobile phone number of the applicant, a family fixed phone, a unit fixed phone and the like. For example, when the server receives the mobile phone number "139 × × 8888", the mobile phone number is divided into 3 parts, that is, 139 × × 8888, and the four digits correspond to the geographic location information, which can also be used to check the received address information, thereby improving the anti-fraud recognition capability. The above examples are provided only for better explaining the present invention and are not intended to limit the present invention. The generating module 202 is configured to integrate the address feature data and the phone number feature data to generate preprocessed data.
Specifically, in order to realize real-time efficient big data processing, the integrated applicant preprocessed data contains the applicant characteristic data for identifying fraudulent behaviors, is structured, contains a fixed field format, and can be flexibly changed and expanded according to business requirements. The fields of the preprocessed data include at least applicant name, gender, date of birth, the address characteristic data, the phone number characteristic data, and the like.
The generating module 202 is further configured to acquire and process personal history data and associated data of the applicant inside and outside, integrate the preprocessed data, and generate structured global data.
Specifically, in order to improve the usability of data, a bank as a user of data needs to structure data in various formats after obtaining various in-line and out-line data.
Fraud risk exists both personally and socially and increasingly in the form of fraudulent groups, anti-fraud work has not been limited to individuals alone, and the associated chains behind individuals should also be investigated by simultaneous analysis. For example, when the server receives a credit card transaction request from an applicant, the server recognizes that the address information, telephone number, or company name used by the applicant is already in the fraud group database, and the server may determine that the service request is at risk of fraud and issue an alert. Therefore, when receiving a business application request of an individual applicant, the server needs to acquire and process personal history data and associated data of the individual applicant inside and outside, integrate the preprocessed data, and generate structured global data.
In other embodiments of the present invention, the generating module 202 is further configured to extract the internal personal historical data and the associated data of the applicant from an internal database, and perform a structuring process to obtain structured internal data;
specifically, most of the applicant often transacts the same or various different businesses in a business for a plurality of times, personal information provided by the applicant in the past is stored in an internal bank system, and in order to improve the safety of the transaction, the server simultaneously inquires relevant data when receiving business requests of clients.
The generating module 202 is further configured to extract external personal historical data and associated data of the applicant from external credit investigation data, and perform structuring processing to obtain structured external data;
in particular, with the advent of the internet + age, a variety of customer information is increasingly recorded in the form of "data" stored in various data formats, a large amount of customer data is distributed inside and outside banks, and in many cases, the variety of customer data outside banks is richer and the integrity is better. In order to improve the accuracy and real-time performance of prediction, when a bank carries out anti-fraud work, the bank can simultaneously use internal data and a large amount of external data for analysis.
The generating module 202 is further configured to integrate the preprocessed data, the structured internal data, and the structured external data to obtain structured global data.
Specifically, the data submitted by the applicant, and historical personal data and associated data related to the applicant in the inside and the outside are screened and then integrated according to a certain data structure, so that ordered data meeting the data processing rules can be obtained. The internal and external personal data at least comprises applicant name, birth date, certificate type, certificate number, gender, mobile phone number, address, work, income, academic history, marital status, credit status, assets and debts, hobbies, social relations, network access habits, internet surfing duration, internet surfing state, fuzzy geographic position and the like;
the internal and external association data are various behavior data of the relationship persons who have contacted with the applicant in the past period. The relatives at least comprise father, brother and sister, colleagues, classmates, other relatives who have loan relations, guarantee relations and the like with the applicant, and other relatives who are identical or similar to the address, telephone, IP address and the like of the applicant. The various behavior data of the relatives comprise names, birth dates, certificate types, certificate numbers, sexes, mobile phone numbers, addresses, works, incomes, academic records, marital conditions, credit conditions, assets and liabilities, preferences, social relations, network access habits, internet surfing duration, internet surfing states, fuzzy geographical positions and the like.
The calculating module 203 is configured to import the preprocessed data and the structured global data into an anti-fraud assessment model to calculate a fraud score value of the applicant.
Specifically, an excellent fraud assessment model must be based on statistical analysis technology, so that risk assessment can be performed more accurately and more quickly, and the ES cluster can carry rapid processing of the fraud assessment model based on big data processing technology. In this embodiment, the calculation module 203 imports the preprocessed data and the structured global data into an anti-fraud evaluation model for processing, so as to obtain a processing result; and matching the processing result with the scoring card to obtain the fraud scoring value of the applicant.
The structured global data is imported into the anti-fraud evaluation model for processing, and the processing mode is based on a big data real-time processing technology and comprises accurate data correction, fuzzy data correction, cluster analysis and the like. The data collation subject may be name, date of birth, certificate type, certificate number, sex, cell phone number, address, work, income, academic history, marital status, credit status, asset liability, etc. The processing result can be that, for example, the age and the academic history are not in accordance with income, owned assets such as vehicles and rooms are not in accordance with living addresses or consumption levels, the difference between the current living addresses and the company addresses is large, the same account number logs in IP with large differences of multiple regions in a short time, and fraud behaviors occur in relationship circles.
In other embodiments of the present invention, the server further has self-learning and self-updating capabilities, and can automatically enhance the adaptability to new fraud patterns through internal model updating, and perform deep data mining by analyzing behavioral characteristic patterns of various groups of people and using mathematical statistics technology, continuously and automatically correct and optimize anti-fraud assessment models, and improve the control capability of business risks.
The feedback module 204 feeds back a corresponding service processing suggestion according to the fraud score value of the applicant, and stops service transaction and generates a fraud prompt when the score value exceeds a preset value.
Specifically, the server automatically matches anti-fraud processing rules when the fraud score value of the applicant is received;
and feeding back a corresponding service processing suggestion according to the matching result, and stopping service processing and generating a fraud prompt when the score value exceeds a preset value.
In other embodiments of the present invention, the server may further provide a manual data input interface for the associated data, and when receiving a manual operation instruction, pop up the manual data input interface, and after completing manual data input, store the manual data input interface and integrate the manual data input interface into the structured global data as a part of the structured global data.
Through the program module 201 and the program module 204, the anti-fraud system based on big data processing provided by the embodiment can effectively utilize data inside and distributed in the external society for collection and processing, quickly identify possible fraud behaviors, improve the accuracy and real-time of anti-fraud in the banking industry, and reduce fraud risk and loss caused by fraud.
Referring to fig. 3, a program module diagram of a second embodiment of the big data processing based anti-fraud system 200 of the present invention is shown. In this embodiment, the anti-fraud system 200 based on big data processing includes a determination module 205 in addition to the preprocessing module 201, the generation module 202, the calculation module 203, and the feedback module 204 in the first embodiment.
The judging module 205 is configured to match the application information of the applicant with a service controlled list, and judge whether the applicant belongs to a controlled executor.
Specifically, some of the applicants are listed in the business controlled list of the enterprise before the applicant initiates the business application due to reasons such as overdue loan, long-term loan, and card-raising number, and for this part of the applicants, new business cannot be accepted for the applicants. And if the applicant belongs to the controlled executed person, feeding back the state of the controlled executed person and rejecting the service request of the applicant.
The service controlled list source comprises an in-line blacklist library, an in-line distrusted person name list library, person credit data, court execution data and the like.
Through the program module 205, the anti-fraud system based on big data processing provided by this embodiment can filter out some problems from the source and apply for the application, thereby further improving the speed of identifying the bank business fraud and improving the business efficiency.
In addition, the invention also provides an anti-fraud method based on big data processing.
Fig. 4 is a schematic flow chart of a first embodiment of the fraud prevention method based on big data processing according to the present invention. In this embodiment, the execution order of the steps in the flowchart shown in fig. 4 may be changed and some steps may be omitted according to different requirements.
And step S400, when a data processing request is received, performing exhaustive splitting on the applicant address stage by stage, extracting address characteristic data, performing segmentation splitting on the applicant telephone number, and extracting telephone number characteristic data.
Specifically, anti-fraud of financial enterprises such as banks is a prediction behavior, fraud crimes thereof highlight non-contact and covert characteristics, criminals tend to specialize, intelligentize and group, and property safety of financial platforms such as banks and network credits and users is seriously damaged. Fraud risk analysis and early warning are works with higher difficulty coefficient for commercial banks, and professional talent ability requirements are higher. In order to deal with constantly renovated financial fraud means, financial institutions need to consider active investment of anti-fraud technical means, prevention and control tools and strategies, comprehensively utilize various internal and external basic data, construct an intelligent database, a wind control model, an anti-fraud assessment model and the like based on technologies such as big data storage and big data processing, improve fraud transaction identification rate, and effectively reduce risk loss and capital loss caused by fraud. However, the fraud analysis data commonly used in the industry at present is based on an older batch processing mode, such as an SAS mode, which belongs to a disaster-free single-point mode, and the adoption of a data batch processing mode has low clustering capability, slow aging, limited capacity, poor capacity expansibility, and limited rule mode, and cannot expand rules. When the system processes data, the number of users is often limited to historical data, information among different service systems is relatively isolated, timely transmission, integration and sharing cannot be achieved, and the fragmentation problem is serious; the rule matching prejudgment is based on rule matching prejudgment, the limitation is strong, the traditional rule matching universality is poor, along with the appearance of a new parameter state, a new matching rule is often required to be customized in time to carry out new fraud judgment, and the fraud judgment rule is required to be updated quickly but cannot be met. In order to improve the accuracy and real-time performance of prediction and reduce fraud risk and loss, a business system is required to be capable of collecting and processing the behavior data of a customer in real time. Therefore, the scheme provides a centralized application anti-fraud method based on the ES cluster and big data processing technology, which is more powerful in the aspects of instantaneity, flexibility, processing capability expandability and the like, and the ES can provide real-time reliable guarantee in the aspects of big data searching and analyzing.
At present, the situations of group fraud crime are often crime by using the. If there are many reports from public security data or network data in the latest period of an address, the server may also reduce the risk of fraud if it can make corresponding warnings when it receives the service request from the address. Splitting the address is beneficial to structuring the data, and is convenient for completing the data processing more quickly and in real time.
The applicant address comprises a home address, a work address, a past residence address, other permanent addresses, a mobile phone positioning address and the like. For example, when the server receives a home address of 'A province, B city, C district, D district, E district, F district, G unit and XXXX room', the server automatically splits the home address into 8 parts, namely, A province, B city, C district, D district, E district, F district, G unit and XXXX room; when the server receives a working address with the address of 7 parts of the working address, namely 7 layers of YYYY rooms of the H track and the J track of the C area, the I track and the J track of the B city, the A province, the B city, the C area, the H track, the I track, the J layer and the YYYY room.
Fraud is usually sudden, especially when a group crime acts, the crime group may use the same phone number or the same numbers to act within a short time, and if the server can identify and give an early warning in time, it is possible to avoid loss. The telephone number is split, so that the data structuring is facilitated, and the telephone number is provided with the geographic position information, so that the data comparison can be completed more quickly and in real time.
The telephone number comprises the mobile phone number of the applicant, a family fixed phone, a unit fixed phone and the like. For example, when the server receives the mobile phone number "139 × × 8888", the mobile phone number is divided into 3 parts, that is, 139 × × 8888, and the four digits correspond to the geographic location information, which can also be used to check the received address information, thereby improving the anti-fraud recognition capability. The above examples are provided only for better explaining the present invention and are not intended to limit the present invention.
Step S402, integrating the address characteristic data and the telephone number characteristic data to generate preprocessing data.
Specifically, in order to realize real-time efficient big data processing, the integrated applicant preprocessed data contains the applicant characteristic data for identifying fraudulent behaviors, is structured, contains a fixed field format, and can be flexibly changed and expanded according to business requirements. The fields of the preprocessed data include at least applicant name, gender, date of birth, the address characteristic data, the phone number characteristic data, and the like.
And S404, acquiring and processing personal historical data and associated data of the applicant inside and outside, integrating the preprocessed data, and generating structured global data.
Specifically, as a user of data, in order to improve usability of data, after various inline and offline data are obtained, data in various formats needs to be structured.
Fraud risk exists both personally and socially and increasingly in the form of fraudulent groups, anti-fraud work has not been limited to individuals alone, and the associated chains behind individuals should also be investigated by simultaneous analysis. For example, when the server receives a credit card transaction request from an applicant, the server recognizes that the address information, telephone number, or company name used by the applicant is already in the fraud group database, and the server may determine that the service request is at risk of fraud and issue an alert. Therefore, when receiving a business application request of an individual applicant, the server needs to acquire and process personal history data and associated data of the individual applicant inside and outside, integrate the preprocessed data, and generate structured global data.
Step S406, importing the preprocessed data and the structured global data into an anti-fraud assessment model to calculate the fraud score value of the applicant.
Specifically, an excellent fraud assessment model must be based on statistical analysis technology, so that risk assessment can be performed more accurately and more quickly, and the ES cluster can carry rapid processing of the fraud assessment model based on big data processing technology.
In this embodiment, the step S406 specifically includes the following steps:
importing the preprocessed data and the structured global data into an anti-fraud evaluation model for processing to obtain a processing result;
and matching the processing result with the scoring card to obtain the fraud scoring value of the applicant.
The structured global data is imported into the anti-fraud evaluation model for processing, and the processing mode is based on a big data real-time processing technology and comprises accurate data correction, fuzzy data correction, cluster analysis and the like. The data collation subject may be name, date of birth, certificate type, certificate number, sex, cell phone number, address, work, income, academic history, marital status, credit status, asset liability, etc. The processing result can be that, for example, the age and the academic history are not in accordance with income, owned assets such as vehicles and rooms are not in accordance with living addresses or consumption levels, the difference between the current living addresses and the company addresses is large, the same account number logs in IP with large differences of multiple regions in a short time, and fraud behaviors occur in relationship circles.
In other embodiments of the present invention, the server further has self-learning and self-updating capabilities, and can automatically enhance the adaptability to new fraud patterns through internal model updating, and perform deep data mining by analyzing behavioral characteristic patterns of various groups of people and using mathematical statistics technology, continuously and automatically correct and optimize anti-fraud assessment models, and improve the control capability of business risks.
And step S408, feeding back a corresponding service processing suggestion according to the fraud score value of the applicant, and stopping service transaction and generating a fraud prompt when the score value exceeds a preset value.
Specifically, the server automatically matches anti-fraud processing rules when the fraud score value of the applicant is received;
and feeding back a corresponding service processing suggestion according to the matching result, and stopping service processing and generating a fraud prompt when the score value exceeds a preset value.
In other embodiments of the present invention, the server may further provide a manual data input interface for the associated data, and when receiving a manual operation instruction, pop up the manual data input interface, and after completing manual data input, store the manual data input interface and integrate the manual data input interface into the structured global data as a part of the structured global data.
Through the anti-fraud method based on big data processing provided by the embodiment of the steps S400-S408, data in the interior and distributed in the external society can be effectively utilized for collection and processing, possible fraud behaviors can be rapidly identified, the accuracy and the real-time performance of anti-fraud in the banking industry are improved, and fraud risks and losses caused by fraud are reduced.
Fig. 5 is a schematic flow chart of a second embodiment of the anti-fraud method based on big data processing according to the present invention. In this embodiment, steps S500 to S504 of the big data processing-based anti-fraud method are similar to steps S400 to S408 of the first embodiment, and the difference is that the step of preprocessing the application information input by the client to obtain the client preprocessed data when receiving the service application request of the client, specifically includes the following steps:
step S500, extracting the internal personal historical data and the associated data of the applicant from an internal database, and performing structuring processing to obtain structured internal data;
specifically, most of the applicant often transacts the same or various different businesses in a business for a plurality of times, personal information provided by the applicant in the past is stored in an internal bank system, and in order to improve the safety of the transaction, the server simultaneously inquires relevant data when receiving business requests of clients.
Step S502, extracting external personal historical data and associated data of the applicant from external credit investigation data, and performing structuring processing to obtain structured external data;
in particular, with the advent of the internet + age, a variety of customer information is increasingly recorded in the form of "data" stored in various data formats, a large amount of customer data is distributed inside and outside banks, and in many cases, the variety of customer data outside banks is richer and the integrity is better. In order to improve the accuracy and real-time performance of prediction, when a bank carries out anti-fraud work, the bank can simultaneously use internal data and a large amount of external data for analysis.
Step S504, the preprocessed data, the structured internal data and the structured external data are integrated to obtain structured global data.
Specifically, the data submitted by the applicant, and historical personal data and associated data related to the applicant in the inside and the outside are screened and then integrated according to a certain data structure, so that ordered data meeting the data processing rules can be obtained. The internal and external personal data at least comprises applicant name, birth date, certificate type, certificate number, gender, mobile phone number, address, work, income, academic history, marital status, credit status, assets and debts, hobbies, social relations, network access habits, internet surfing duration, internet surfing state, fuzzy geographic position and the like;
the internal and external association data are various behavior data of the relationship persons who have contacted with the applicant in the past period. The relatives at least comprise father, brother and sister, colleagues, classmates, other relatives who have loan relations, guarantee relations and the like with the applicant, and other relatives who are identical or similar to the address, telephone, IP address and the like of the applicant. The various behavior data of the relatives comprise names, birth dates, certificate types, certificate numbers, sexes, mobile phone numbers, addresses, works, incomes, academic records, marital conditions, credit conditions, assets and liabilities, preferences, social relations, network access habits, internet surfing duration, internet surfing states, fuzzy geographical positions and the like.
Through the anti-fraud method based on big data processing provided by the embodiment of the above steps S500 to S504, the data submitted by the applicant, the internal personal history data and the associated data, and the external personal history data and the associated data can be integrated to obtain the structured global data convenient for big data processing.
Further, based on the above-mentioned first and second embodiments of the big data processing-based anti-fraud method of the present invention, a third embodiment of the big data processing-based anti-fraud of the present invention is proposed. Fig. 6 is a schematic flow chart of a third embodiment of the anti-fraud method based on big data processing according to the present invention. In this embodiment, when a data processing request is received, before preprocessing data submitted by an applicant to obtain preprocessed data, the method specifically includes the following steps:
step S600, matching the application information of the applicant with a service controlled list, and judging whether the client belongs to a controlled executor or not;
specifically, the business controlled list is a list in which an enterprise performs partial limitation or direct rejection processing on business requests of partial personnel, and the enterprise lists partial personnel with business risks according to historical experience of business transactions and information known from the outside so as to reduce risk and loss of business activities of the enterprise. Through the service controlled list, the service handling personnel can quickly determine the service handling mode of the personnel in the controlled list.
Step S602, if the applicant belongs to the controlled executed person, feeding back the state of the controlled executed person and rejecting the service request of the client;
specifically, some of the applicants are listed in the business controlled list of the enterprise before the applicant initiates the business application due to reasons such as overdue loan, long-term loan, and card-raising number, and for this part of the applicants, new business cannot be accepted for the applicants.
And step S604, if the applicant does not belong to the internal control executed person, continuing to execute the next step of the business process.
The service controlled list source comprises an in-line blacklist library, an in-line distrusted person name list library, person credit data, court execution data and the like.
Through the steps S600 to S604, the anti-fraud system based on big data processing provided in this embodiment can filter out part of the problems from the source and apply for the application, thereby further improving the speed of identifying the bank business fraud and improving the business efficiency.
The present invention also provides another embodiment, which is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a big data processing-based anti-fraud program, and the big data processing-based anti-fraud program is executable by at least one processor to cause the at least one processor to execute the steps of the big data processing-based anti-fraud method as described above.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal device (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. An anti-fraud method based on big data processing, characterized in that the method comprises the steps of:
when a data processing request is received, carrying out exhaustive splitting on the applicant address stage by stage, extracting address characteristic data, carrying out segmentation splitting on the applicant telephone number, and extracting telephone number characteristic data;
integrating the address characteristic data and the telephone number characteristic data to generate preprocessed data;
acquiring and processing personal historical data and associated data of the applicant inside and outside to generate structured global data;
importing the preprocessed data and the structured global data into an anti-fraud assessment model to calculate the fraud score value of the applicant;
and feeding back a corresponding service processing suggestion according to the fraud score value of the applicant, and stopping service processing and generating a fraud prompt when the score value exceeds a preset value.
2. The big data processing-based anti-fraud method according to claim 1, wherein the obtaining and processing of personal history data and associated data of the applicant inside and outside, the integration of pre-processed data, and the generation of structured global data, specifically comprises the following steps:
extracting the internal personal historical data and the associated data of the applicant from an internal database, and performing structuring processing to obtain structured internal data;
extracting external personal historical data and associated data of the applicant from external credit investigation data, and performing structuring processing to obtain structured external data;
and integrating the preprocessed data, the structured internal data and the structured external data to obtain structured global data.
3. The big data processing-based anti-fraud method according to claim 1, wherein the importing the preprocessed data and the structured global data into an anti-fraud assessment model to calculate a fraud score of the applicant comprises the following steps:
importing the preprocessed data and the structured global data into an anti-fraud evaluation model for processing to obtain a processing result;
and matching the processing result with the scoring card to obtain the fraud scoring value of the applicant.
4. The big data processing-based anti-fraud method according to claim 1, wherein the corresponding business processing suggestion is fed back according to the fraud score value of the applicant, and when the score value exceeds a preset value, the business processing is stopped and a fraud prompt is generated, specifically comprising the following steps:
when the fraud score value of the applicant is received, the server automatically matches an anti-fraud processing rule;
and feeding back a corresponding service processing suggestion according to the matching result, and stopping service processing and generating a fraud prompt when the score value exceeds a preset value.
5. The big data processing-based anti-fraud method according to claim 1, wherein before the step of performing a step-by-step exhaustive splitting of the applicant's address and extracting address feature data, the step of performing a segment-by-segment splitting of the applicant's phone number and extracting phone number feature data when receiving a data processing request, the method further comprises the steps of:
matching the application information of the applicant with a service controlled list, and judging whether the applicant belongs to a controlled executor or not;
and if the applicant belongs to the controlled executed person, feeding back the state of the controlled executed person and rejecting the service request of the applicant.
6. A server, comprising a memory, a processor, the memory having stored thereon a big data processing based anti-fraud system operable on the processor, the big data processing based anti-fraud system when executed by the processor implementing the steps of:
when a data processing request is received, carrying out exhaustive splitting on the applicant address stage by stage, extracting address characteristic data, carrying out segmentation splitting on the applicant telephone number, and extracting telephone number characteristic data;
integrating the address characteristic data and the telephone number characteristic data to generate preprocessed data;
acquiring and processing personal historical data and associated data of the applicant inside and outside to generate structured global data;
importing the preprocessed data and the structured global data into an anti-fraud assessment model to calculate the fraud score value of the applicant;
and feeding back a corresponding service processing suggestion according to the fraud score value of the applicant, and stopping service processing and generating a fraud prompt when the score value exceeds a preset value.
7. The server according to claim 6,
the method for acquiring and processing the personal historical data and the associated data of the applicant inside and outside, integrating the preprocessed data and generating the structured global data specifically comprises the following steps:
extracting the internal personal historical data and the associated data of the applicant from an internal database, and performing structuring processing to obtain structured internal data;
extracting external personal historical data and associated data of the applicant from external credit investigation data, and performing structuring processing to obtain structured external data;
and integrating the preprocessed data, the structured internal data and the structured external data to obtain structured global data.
8. The server according to claim 6, wherein the importing the preprocessed data and the structured global data into an anti-fraud assessment model to calculate a fraud score of the applicant comprises:
importing the preprocessed data and the structured global data into an anti-fraud evaluation model for processing to obtain a processing result;
and matching the processing result with the scoring card to obtain the fraud scoring value of the applicant.
The method for feeding back the corresponding service processing suggestion according to the fraud score value of the applicant and stopping service transaction and generating a fraud prompt when the score value exceeds a preset value specifically comprises the following steps:
when the fraud score value of the applicant is received, the server automatically matches an anti-fraud processing rule;
and feeding back a corresponding service processing suggestion according to the matching result, and stopping service processing and generating a fraud prompt when the score value exceeds a preset value.
9. The server according to claim 6, wherein before preprocessing the data submitted by the applicant when the data processing request is received to obtain the preprocessed data, the method further comprises the following steps:
matching the application information of the applicant with a service controlled list, and judging whether the client belongs to a controlled executor or not;
and if the applicant belongs to the controlled executed person, feeding back the state of the controlled executed person and rejecting the service request of the applicant.
10. A computer-readable storage medium storing a big-data-processing-based anti-fraud system, the big-data-processing-based anti-fraud system being executable by at least one processor to cause the at least one processor to perform the steps of the big-data-processing-based anti-fraud method according to any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910881748.XA CN110795466A (en) | 2019-09-18 | 2019-09-18 | Anti-fraud method based on big data processing, server and computer-readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910881748.XA CN110795466A (en) | 2019-09-18 | 2019-09-18 | Anti-fraud method based on big data processing, server and computer-readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110795466A true CN110795466A (en) | 2020-02-14 |
Family
ID=69427300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910881748.XA Pending CN110795466A (en) | 2019-09-18 | 2019-09-18 | Anti-fraud method based on big data processing, server and computer-readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110795466A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111986020A (en) * | 2020-06-05 | 2020-11-24 | 深圳市卡牛科技有限公司 | Financial loan risk assessment method, device, equipment and storage medium |
| CN113051406A (en) * | 2021-03-23 | 2021-06-29 | 龙马智芯（珠海横琴）科技有限公司 | Character attribute prediction method, device, server and readable storage medium |
| CN113837777A (en) * | 2021-09-30 | 2021-12-24 | 浙江创邻科技有限公司 | Graph database-based anti-fraud management and control method, device, system and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190066248A1 (en) * | 2017-08-25 | 2019-02-28 | Intuit Inc. | Method and system for identifying potential fraud activity in a tax return preparation system to trigger an identity verification challenge through the tax return preparation system |
| CN109636568A (en) * | 2018-10-25 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Risk checking method, device, equipment and the storage medium of telephone number |
| US20190141183A1 (en) * | 2017-08-16 | 2019-05-09 | Royal Bank Of Canada | Systems and methods for early fraud detection |
| CN110119980A (en) * | 2019-04-23 | 2019-08-13 | 北京淇瑀信息科技有限公司 | A kind of anti-fraud method, apparatus, system and recording medium for credit |
-
2019
- 2019-09-18 CN CN201910881748.XA patent/CN110795466A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190141183A1 (en) * | 2017-08-16 | 2019-05-09 | Royal Bank Of Canada | Systems and methods for early fraud detection |
| US20190066248A1 (en) * | 2017-08-25 | 2019-02-28 | Intuit Inc. | Method and system for identifying potential fraud activity in a tax return preparation system to trigger an identity verification challenge through the tax return preparation system |
| CN109636568A (en) * | 2018-10-25 | 2019-04-16 | 深圳壹账通智能科技有限公司 | Risk checking method, device, equipment and the storage medium of telephone number |
| CN110119980A (en) * | 2019-04-23 | 2019-08-13 | 北京淇瑀信息科技有限公司 | A kind of anti-fraud method, apparatus, system and recording medium for credit |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111986020A (en) * | 2020-06-05 | 2020-11-24 | 深圳市卡牛科技有限公司 | Financial loan risk assessment method, device, equipment and storage medium |
| CN113051406A (en) * | 2021-03-23 | 2021-06-29 | 龙马智芯（珠海横琴）科技有限公司 | Character attribute prediction method, device, server and readable storage medium |
| CN113837777A (en) * | 2021-09-30 | 2021-12-24 | 浙江创邻科技有限公司 | Graph database-based anti-fraud management and control method, device, system and storage medium |
| CN113837777B (en) * | 2021-09-30 | 2024-02-20 | 浙江创邻科技有限公司 | Anti-fraud management and control method, device and system based on graph database and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11989740B2 (en) | Reducing false positives using customer feedback and machine learning | |
| CN108876133B (en) | Risk assessment processing method, device, server and medium based on business information | |
| CN110704730B (en) | Product data pushing method and system based on big data and computer equipment | |
| CN111666346B (en) | Information merging method, transaction inquiring method, device, computer and storage medium | |
| US20130031109A1 (en) | Method, system, and computer program product for linking customer information | |
| CN109815803B (en) | Face examination risk control method and device, computer equipment and storage medium | |
| CN110795466A (en) | Anti-fraud method based on big data processing, server and computer-readable storage medium | |
| CN113657993B (en) | Credit risk identification method, apparatus, device and storage medium | |
| CN117114514B (en) | Talent information analysis management method, system and device based on big data | |
| CN110766275A (en) | Data verification method and device, computer equipment and storage medium | |
| CN111552680A (en) | Construction method and device of business fraud identification database and computer equipment | |
| CN108090831A (en) | Credit Risk Assessment method, application server and computer readable storage medium | |
| CN110197426B (en) | Credit scoring model building method, device and readable storage medium | |
| CN113888299A (en) | Wind control decision method and device, computer equipment and storage medium | |
| CN112232950A (en) | Loan risk assessment method and device, equipment and computer-readable storage medium | |
| CN116307671A (en) | Risk early warning method, risk early warning device, computer equipment and storage medium | |
| CN112598499A (en) | Method and device for determining credit limit | |
| CN117575773A (en) | Method, device, computer equipment and storage medium for determining service data | |
| CN115345727B (en) | Method and device for identifying fraudulent loan application | |
| US20180060379A1 (en) | Automated correlation and deduplication of identities | |
| CN109918552B (en) | Method for identifying aversion group complaint trend personnel, server and computer readable storage medium | |
| CN107516213B (en) | Risk identification method and device | |
| CN113706258A (en) | Product recommendation method, device, equipment and storage medium based on combined model | |
| US20230360051A1 (en) | Detecting unauthorized online applications using machine learning | |
| CN114662824A (en) | Wind control strategy switching method and device, computer equipment and 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200214 |