CN101236638A - Web based bank card risk monitoring method and system - Google Patents
Web based bank card risk monitoring method and system Download PDFInfo
- Publication number
- CN101236638A CN101236638A CNA2008100578726A CN200810057872A CN101236638A CN 101236638 A CN101236638 A CN 101236638A CN A2008100578726 A CNA2008100578726 A CN A2008100578726A CN 200810057872 A CN200810057872 A CN 200810057872A CN 101236638 A CN101236638 A CN 101236638A
- Authority
- CN
- China
- Prior art keywords
- bank card
- data
- risk
- monitoring
- transaction
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 196
- 238000000034 method Methods 0.000 title claims abstract description 52
- 238000012806 monitoring device Methods 0.000 claims description 14
- 238000005096 rolling process Methods 0.000 claims description 11
- 230000005540 biological transmission Effects 0.000 claims description 9
- 230000006399 behavior Effects 0.000 description 22
- 238000012545 processing Methods 0.000 description 21
- 238000004458 analytical method Methods 0.000 description 15
- 238000010586 diagram Methods 0.000 description 12
- 238000011156 evaluation Methods 0.000 description 11
- 230000002354 daily effect Effects 0.000 description 8
- 230000000694 effects Effects 0.000 description 8
- 238000009825 accumulation Methods 0.000 description 5
- 238000012790 confirmation Methods 0.000 description 5
- 238000012502 risk assessment Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 4
- 238000007619 statistical method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 210000001503 joint Anatomy 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000008014 freezing Effects 0.000 description 1
- 238000007710 freezing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Landscapes
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
Abstract
The invention provides a bank card risk monitoring method and a bank card risk monitoring system based on Web. The method comprises that: transaction data of a bank card is collected in real-time; property data of the bank card is periodically collected; a bank card risk monitoring model is established; the transaction data of the bank card and the related property data of the bank card are monitored according to the bank card risk monitoring model, bank card risk monitoring result data is generated; a Web bank card risk monitoring service request is received; according to the Web bank card risk monitoring service request, the corresponding bank card risk monitoring result data is displayed in the form of Web to control the risk of the bank card service and improve the benefit level by evaluating and monitoring the bank card risk data.
Description
Technical Field
The invention relates to a computer network and a Web technology, in particular to a bank card credit risk and fraud risk monitoring method and system utilizing the computer network and the Web technology, and specifically relates to a bank card risk monitoring method and system based on the Web.
Background
The bank card is a financial product with high risk and high profit and return, and the bank card business becomes one of the most profitable businesses of commercial banks due to the fact that the back of the bank card product represents a high-quality customer group and the high return characteristic of overdraft interest with the maximum annual rate of 18 percent.
However, as the bank card business is further developed, bank card risks are more and more frequently generated. And with the increase of card issuers, special merchants and cardholders, the bank card risks show the characteristics of wide related range, various risk types and high harmfulness. The annual loss to banks due to the risk of counterfeit cards is more than 35 billion dollars.
The invention patent application 200410069101.0 discloses a system and method for risk analysis of customers by financial enterprises, which prevents risks by rating the credit of customers. The technical solution disclosed in the present invention is incorporated herein as prior art of the present invention.
Although the technical scheme that financial enterprises analyze risks of customers exists in the prior art, most banks have relatively weak management mechanisms of risks of bank cards, the early warning timeliness and detection identification rate of credit risks and fraud risks are not high, the method is backward, and quantitative statistics and monitoring of operation risks need to be perfected.
Disclosure of Invention
The invention provides a bank card risk monitoring method and system based on Web, which are used for controlling the business risk of a bank card and improving the income level by evaluating and monitoring bank card risk data.
One of the objects of the present invention is: the method for monitoring the risk of the bank card based on the Web is provided, and comprises the following steps: collecting bank card transaction data in real time; periodically collecting attribute data of the bank card; establishing a bank card risk monitoring model; monitoring the transaction data of the bank card and the attribute data of the related bank card according to the risk monitoring model of the bank card to generate risk monitoring result data of the bank card; receiving a Web bank card risk monitoring service request; and displaying corresponding bank card risk monitoring result data in a Web form according to the Web bank card risk monitoring service request.
One of the objects of the present invention is: the bank card risk monitoring system based on Web is characterized by comprising the following components: the system comprises a bank card risk monitoring device and a risk monitoring Web service device, wherein the bank card risk monitoring device is connected with the risk monitoring Web service device; wherein, bank card risk monitoring devices include: the bank card data acquisition unit is used for acquiring bank card transaction data in real time and periodically acquiring bank card attribute data; the monitoring model establishing unit is used for establishing and/or storing a bank card risk monitoring model; the bank card risk monitoring unit is used for monitoring the bank card transaction data and the related bank card attribute data according to the bank card risk monitoring model to generate bank card risk monitoring result data; the risk monitoring Web service device comprises: the Web service request receiving unit is used for receiving a Web bank card risk monitoring service request; and the Web monitoring result display unit is used for displaying the corresponding bank card risk monitoring result data in a Web form according to the Web bank card risk monitoring service request.
One of the objects of the present invention is: the bank card risk monitoring system based on Web is characterized by comprising the following components: the system comprises a bank card basic data generating device, a bank card risk monitoring device, a risk monitoring Web service device and a user terminal; the bank card basic data generating device comprises: the bank card account data unit is used for generating bank card transaction data and attribute data; the real-time transmission unit is used for transmitting the bank card transaction data in real time; the batch transmission unit is used for periodically transmitting the attribute data of the bank cards; the bank card risk monitoring device includes: the bank card data acquisition unit is used for acquiring bank card transaction data in real time and periodically acquiring bank card attribute data; the monitoring model establishing unit is used for establishing and/or storing a bank card risk monitoring model; the bank card risk monitoring unit is used for monitoring the bank card transaction data and the related bank card attribute data according to the bank card risk monitoring model to generate bank card risk monitoring result data; the risk monitoring Web service device comprises: the Web service request receiving unit is used for receiving a Web bank card risk monitoring service request; the Web monitoring result display unit is used for displaying corresponding bank card risk monitoring result data in a Web form according to the Web bank card risk monitoring service request; the user terminal comprises: an input unit for inputting a user instruction; and the display unit is used for displaying the Web interface.
The invention has important significance for controlling bank card risk of banks and improving income level of banks by providing the system and the method for quantifying and evaluating credit risk and fraud risk of bank card customers, which are objective, effective, simple and convenient to operate and high in processing efficiency, and has the following specific effects:
risk discovery timeliness. Through the quasi-real-time monitoring mode, the credit risk and the fraud risk of the bank card client can be found in time, and the loss caused by the bank card risk to the bank is effectively reduced.
And (4) risk evaluation comprehensiveness. And the bank card transaction is evaluated through a plurality of risk monitoring models, and the evaluation is relatively comprehensive.
High efficiency is achieved. Compared with the prior manual processing mode, the method has high processing efficiency and higher operability in the daily bank card risk management work, and effectively improves the efficiency of the bank card risk management;
along with the continuous accumulation of data, the risk monitoring model after repeated correction is more scientific and effective, so that more accurate risk data are generated.
Drawings
FIG. 1 is a schematic diagram of the system connection of the present invention;
FIG. 2 is a block diagram of the basic data generating device of the bank card of the system of the present invention;
FIG. 3 is a block diagram of the risk monitoring device of the bank card of the system of the present invention;
FIG. 4 is a block diagram of the Web services apparatus of the system of the present invention;
FIG. 5 is a block diagram of the architecture of an embodiment of the system of the present invention;
FIG. 6 is a flowchart illustrating operation of an embodiment of the present invention;
FIG. 7 is a block diagram of a monitoring model of the system of the present invention;
FIG. 8 is a block diagram of a transaction index monitoring model of the system of the present invention;
FIG. 9 is a block diagram of the objective logic monitoring model of the system of the present invention;
FIG. 10 is a block diagram of a transaction habit monitoring model of the system of the present invention;
FIG. 11 is a block diagram of a monitoring model of particular interest for the system of the present invention;
FIG. 12 is a schematic time-slicing diagram of the segmented monitoring according to the embodiment of the present invention;
fig. 13 is a diagram illustrating quantitative evaluation of risk of bank cards according to an embodiment of the present invention.
Detailed Description
The following describes embodiments of the present invention with reference to the drawings. The invention collects the transaction data of the bank card in real time, analyzes and measures the transaction data by utilizing the risk rule summarizing the analysis and research of the card risk behavior, accurately identifies the risk event and the corresponding bank card, extracts the associated information of the risk card, helps the bank card risk prevention personnel to process the event, and takes the corresponding measures in time to prevent the fund loss.
As shown in fig. 1, the bank card online service system server 101 is a daily service processing system of a bank, and is responsible for background online processing of services such as card opening, card consumption, cash withdrawal and the like of a bank card, and basic data generated by the server, such as bank card attributes and transaction data such as account basic information, account balance condition, account card swiping consumption condition, account cash withdrawal condition, account overdraft condition and the like, are basic data for analyzing card usage behavior of the bank card. The data in the bank card online service system server 101 is downloaded to the data server 102 via the local area network in two ways: for the bank card transaction data, the requirement on monitoring timeliness is high, and the data is downloaded to the data server 102 in real time through a gateway real-time issuing mechanism; and (II) for some bank card attribute information for analysis, such as customer data, account data and card data, generally need to be acquired through an association relation, if the real-time acquisition has a great influence on the performance of an online service system, the timeliness and accuracy of such data are not high, and therefore the data can be downloaded to the data server 102 in a daily batch mode. Through a data transmission mode combining real-time and batch, the peak of normal business transaction can be avoided, the pressure of an online system is reduced, the running performance of normal business is ensured, meanwhile, abnormal transaction can be found in time, and the two modes are matched for use, so that system resources and monitoring effects are balanced.
The data server 102 is a database management system, and is used for performing risk analysis and measurement by using a risk monitoring model based on the bank card related data acquired from the online business system server 101 to obtain risk monitoring result data including information of risk cards, risk transaction events, risk merchants and the like. Meanwhile, the data server 102 also provides data access service for the bank card risk management operation, and the provided data content also comprises auxiliary analysis data such as customer information, account information, card information, merchant information, recent transaction information and the like besides the monitoring result data; and is also responsible for storing and providing management data of the risk event, such as investigation, confirmation, evaluation and other operation information of the risk event.
The application server 103 is responsible for the logical processing of the system, and accesses the data server 102 according to the user request sent by the Web server 104, and after obtaining the data requested by the user or updating the data according to the user request, returns the result to the Web server 104, and the Web server 104 performs the display processing. In addition, it is also responsible for providing some application services related to risk management work, mainly risk verification and handling measures, such as: the system is connected with a telephone center in a butt joint mode and provides a telephone dialing service; the system is connected with an information platform in a butt joint mode and provides e-mail and short message services; and the system is in butt joint with the bank card online business system, and provides contents such as account/card freezing operation service and the like. The relevant operation result information should be returned to the data server 102 for storage.
The Web server 104 provides http and https based services for the client, dynamically generates Web page files, provides the Web page files to the user terminal devices 105 and 106 through the local area network, and realizes interaction with the user terminal devices 105 and 106. The Web server 104 processes interface processing of the Web page, and specific business logic processing is transferred to the application server 103 for processing, receives a processing result of the application server 103 for subsequent processing, and finally transmits the processing result to the client terminal apparatuses 105 and 106.
The lan is an enterprise lan and may be Ethernet (Ethernet), or other lans, such as Fiber Distributed Data Interface (FDDI), Token Ring (Token-Ring), and the like. In addition, local area networks of all branches can be connected to form a larger Intranet (Intranet) by means of renting special lines and the like.
The user terminal devices 105 and 106 are clients of the system, and may be a PC installed with browser software, or other devices capable of running the browser software, such as an NC, a Windows graphic terminal, and the like. It has a display device, which may be a display, and an input device, which may be a keyboard and a mouse. The user terminal apparatuses 105 and 106 are connected to an internal network, and realize connection with the Web server 104.
The teller authentication device 107 is responsible for performing identity authentication on a user, the user must log in before using the system, the user inputs authentication information such as a user name and a password on the user terminal devices 105 and 106, the client terminal devices 105 and 106 send the user authentication information to the Web server 104 through an internal network, the Web server 104 transfers the user authentication information to the application server 103 for processing, when the application server 103 is processed and is supposed to perform authentication (if the user is not authenticated), the authentication information is transferred to the teller authentication device 107 for authentication processing, the authentication result is returned to the application server 103, the authentication result is stored in a memory of the application server 103 so as to confirm whether the user is authenticated in the integrated login operation process, and a related operation record is also recorded in the data server 102.
As shown in fig. 2, the device for generating basic data of a bank card includes a bank card account data unit for generating transaction data and attribute data of the bank card; the real-time transmission unit is used for transmitting the bank card transaction data in real time; and the batch transmission unit is used for periodically transmitting the attribute data of the bank card.
As shown in fig. 3, the device for monitoring bank card risk includes a bank card data collecting unit, configured to collect transaction data of a bank card in real time and periodically collect attribute data of the bank card; the monitoring model establishing unit is used for establishing and/or storing a bank card risk monitoring model; and the bank card risk monitoring unit is used for monitoring the transaction data of the bank card and the related attribute data of the bank card according to the bank card risk monitoring model to generate bank card risk monitoring result data.
As shown in fig. 4, the risk monitoring Web service device includes a Web service request receiving unit, configured to receive a Web bank card risk monitoring service request; and the Web monitoring result display unit is used for displaying the corresponding bank card risk monitoring result data in a Web form according to the Web bank card risk monitoring service request.
As shown in fig. 5, the system is a Web-based bank card risk monitoring system, and the system includes: the system comprises a bank card basic data generating device, a bank card risk monitoring device, a risk monitoring Web service device and a user terminal; the bank card basic data generating device comprises: the bank card account data unit is used for generating bank card transaction data and attribute data; the real-time transmission unit is used for transmitting the bank card transaction data in real time; the batch transmission unit is used for periodically transmitting the attribute data of the bank cards; the bank card risk monitoring device includes: the bank card data acquisition unit is used for acquiring bank card transaction data in real time and periodically acquiring bank card attribute data; the monitoring model establishing unit is used for establishing and/or storing a bank card risk monitoring model; the bank card risk monitoring unit is used for monitoring the bank card transaction data and the related bank card attribute data according to the bank card risk monitoring model to generate bank card risk monitoring result data; the risk monitoring Web service device comprises: the Web service request receiving unit is used for receiving a Web bank card risk monitoring service request; the Web monitoring result display unit is used for displaying corresponding bank card risk monitoring result data in a Web form according to the Web bank card risk monitoring service request; the user terminal comprises: an input unit for inputting a user instruction; and the display unit is used for displaying the Web interface. Before a monitoring service request is made, a user needs to perform identity authentication.
As shown in fig. 6, the steps of the present embodiment are described as follows:
step S101: and collecting basic data. The data acquisition is divided into three parts: firstly, data files of bank card customers, accounts, cards and the like in the bank card online business system 1 are downloaded to the data service device 2 in batches every day; secondly, downloading the online transaction data of the bank card in the online business system 1 of the bank card to the data service device 1 in a real-time manner; thirdly, the model parameters, such as the list of key merchants, the amount threshold, etc., are input by the monitoring teller and then stored in the data service device 1. The period of data entry is irregular and is updated to the system according to the change adjustment of the service.
The data of the three aspects are basic data required for carrying out the card behavior risk analysis for the bank card.
Step S102: and performing primary processing on the basic data to form intermediate result data, such as the accumulated consumption amount/number of strokes of the customer on the day, a high-risk merchant list and the like.
Step S103: and (5) carrying out quasi-real-time risk analysis. In the most ideal case, a real-time transaction data should be received, and the transaction is immediately analyzed to determine whether it satisfies the monitoring standard of the expert model. However, the expert model includes a plurality of complex statistical analysis logics, and this kind of real-time processing method needs to perform real-time statistics on the relevant data of the transaction each time, such as contents of accumulated transaction amount/number of transactions in a previous period of the transaction, and especially, part of the expert model has a time period rolling type monitoring statistical requirement, and the cost of system implementation is quite high, so we must perform differential treatment on the contents requiring quasi-real-time monitoring processing.
One is a risk model that can be analyzed on-the-fly to obtain monitoring results. The model can directly obtain an analysis conclusion by associating other auxiliary information such as risk merchants, historical average transaction amount/transaction number, transaction places and the like through isolated analysis of single transaction behaviors, and the data computation amount is generally small.
The other type is a risk model which can not obtain a conclusion through isolated analysis, the model generally has statistical judgment conditions such as accumulation (including the accumulation requirement of a rolling time period), continuous occurrence and the like, a plurality of transaction indexes before the transaction occurs need to be associated and counted, and certain monitoring accuracy can be considered to be sacrificed in specific implementation so as to achieve balance of monitoring coverage and system performance. A method of segmented statistical analysis is described below:
as shown in fig. 12, for a rolling cumulative H hours (i.e., H hours advanced from the time the transaction occurred), the transaction amount reaches the monitoring threshold. And (4) segmenting from a time axis, and segmenting the statistical time period H into N segments. The finer the time slicing, the larger N, the more accurate the statistics. And summarizing the transaction indexes of all the cards which have transaction in the previous H hours in each time segment, and comparing the transaction indexes with the monitoring standard to obtain monitoring result data. If the time period H of the rolling accumulation statistic is 8 hours, a time period is sliced every 0.5 hours. Suppose that 1 ten thousand bank card transactions occur every 0.5 hour, 1 ten thousand cards are involved, 8 ten thousand bank card transactions occur in 8 hours, and 4 ten thousand cards are involved. Then in computing this monitoring model, the standard calculation method is: and taking out the transaction data of the card in the past 8 hours from the transaction detail data, summarizing and counting the accumulated transaction amount and comparing the accumulated transaction amount with the parameter value. According to the assumption, 24 thousands of bank card transactions occur every day, the transaction detail table needs to be inquired 24 thousands of times according to the method (due to different transaction occurrence time, the statistical time period is different, and the 24 ten thousands of inquiries can be executed separately), 2 transaction detail data are averagely inquired every time, and the summarized transaction amount is compared with the threshold value. Counting the accumulated transaction indexes of the cards which are transacted in the time period and each card in the past 16 time segments respectively every 0.5 hour, then correlating the two results, and simultaneously comparing the two results with a monitoring threshold standard to obtain monitoring result data. Although the transaction data volume of each inquiry/statistic is 1 ten thousand transactions, and the association between 1 ten thousand cards (occurring within 0.5 hour) and 4 ten thousand cards (occurring within 8 hours) needs to be made once, the inquiry statistic times are reduced from 24 ten thousand times per day to 48 times, so that the whole-table scanning times of the transaction detail data table are greatly reduced, and the overall operation efficiency is greatly improved.
Step S104: and (4) carrying out batch risk analysis at the end of the day. For some risk models which need to count data of multiple days for analysis, the monitoring target is to find regular and longer-term risk behaviors, and the timeliness requirement is not very high. For such models, we can monitor daily in batches, and perform statistical analysis on the transaction data for day T + 1.
Step S105: and (6) distributing tasks. For pending risk events monitored by the expert model, verification and confirmation needs to be assigned to risk management personnel within the risk management system.
Step S106: and managing risk events. After the risk management personnel receive the risk event sent by the system, effective measures are taken to verify and confirm the risk event, the paths of the risk management personnel include internal communication, telephone, short message, e-mail and the like, and the effect of efficient intensive management can be achieved by combining the cooperation of platforms such as office management and a telephone center (customer service center). And (4) making a final qualitative conclusion on the risk event by the risk management personnel according to the grasped condition, and taking a countermeasure according to the requirement. The main risk countermeasures include loss reporting (customer initiated), collection hastening, payment stopping and the like.
Step S107: and (5) quantitatively evaluating the risk degree.
In order to know the risk occurrence situation in time, the system provides a risk evaluation mechanism. The risk evaluation is to quantify the risk condition of the institution, the card, the client and the merchant related to the risk event. The specific method is that different risk scores are given according to qualitative conclusions of different degrees made by risk management personnel on risk events, and then summary statistics is carried out according to evaluation objects. The evaluation objects generally comprise card issuing organizations, transaction cards, customers, customer classifications, merchants and merchant types. According to the historical change of risk evaluation, risk management and business marketing strategies can be adjusted in time, and risks are controlled while business is developed. The risk was quantitatively evaluated as shown in FIG. 13.
Step S108: and quantitatively evaluating the model discrimination rate.
Due to the constant change in the form of risk with cards, expert models are required to be constantly revised. The evaluation of the model is the main basis for modifying the model, and the model discrimination is the main index for evaluating the quality of the model. The system regularly (month or year) counts the discrimination rate of the model, the main method is that risk events processed by risk managers are grouped according to an expert model, the 'alarm card times', the 'pass card times' and the 'confirmation risk card times' are counted, and the 'card types' and the 'card issuing areas' can be brought into grouping conditions by considering the risk difference between different card types and different areas.
(alarm card) card number (risk event) which is analyzed by expert model and pre-warned by system
Card pass the card number, the card number which is verified by the risk manager to be 'normal' (risk event)
Identification of a risk card (i.e., a card number that is identified as "case" or "violation/default" after verification by a risk manager
[ ratio of risk confirmation card number to alarm card number ]/[ alarm card number ]
[ example of confirmation Risk Care and passage Care ]/[ example of passage Care ]
The higher the ratio of the confirmed risk card number to the alarm card number or the ratio of the confirmed risk card number to the pass card number is, the higher the monitoring accuracy of the model is, the higher the reasonability and the accuracy of the model design are, and the better the monitoring effect is. On the contrary, the accuracy of the model is not high, the monitoring effect is poor, and the model needs to be revised.
Step S109: and (5) improving the model.
As for the processing result in step S108, the bank card department should improve the model with lower score, and the improvement method includes adjusting the valve parameter and revising the model rule, thereby achieving better monitoring effect.
As shown in fig. 7, the monitoring model plays a significant role in the overall risk monitoring for the entire system. The basis for constructing the monitoring model is a group of methods summarized by combining the case characteristics of the bank card from the card using habit of the user. The following is a description of the establishment of the monitoring model:
as shown in fig. 8, for the establishment method of the transaction index monitoring model, the following analysis indexes are commonly used:
the amount of the single transaction. The index is used for directly judging single transaction, and judging whether the transaction amount reaches the early warning standard or not according to a preset parameter threshold value. The index aims to find out the large-amount abnormal transaction risk in time, is applied to prevention of credit risk and fraud risk, has high requirement on timeliness, and is generally used as a real-time monitoring index.
The accumulated transaction amount over the period of the scroll. The index is used for judging a plurality of transaction behaviors of the card in a certain time period, counting the time of self-transaction occurrence of the card, advancing the accumulated transaction amount in a fixed period, and judging whether the accumulated transaction amount reaches an early warning standard. The purpose of this indicator is to find in time a transaction risk that is intended to evade large-value transaction monitoring, but actually has a large amount of fund variation. The index is mainly used for monitoring fraud risks, has high requirements on timeliness and is generally used as a real-time monitoring index. The rolling period of the index can also be in units of days, so that the time efficiency requirement is relatively low, and the rolling period can be used as a batch monitoring index.
Frequency of transactions within a rolling period. The index is also used for judging a plurality of transaction behaviors of the card in a certain time period, counting the time of self-transaction occurrence of the card, advancing the accumulated transaction number in a fixed period, and judging whether the accumulated transaction number reaches an early warning standard. The purpose of the index is to timely find the potential risk of frequent non-large-amount transactions, and the index is mainly used for monitoring the fraud risk.
The account current overdraft balance/overdraft ratio. The index is used for judging the overdraft degree of the card after transaction, aims to find malicious overdraft behaviors in time, is mainly used for monitoring credit risks, has high requirement on timeliness, and is generally used as a real-time monitoring index. Because overdraft is just the business characteristic of the bank card, belongs to normal card using behaviors, and is also the main profit point of the bank card business, the index generally needs to be combined with other behavior analysis methods for monitoring, such as a large amount of overdraft withdrawal when a card is newly opened, return at the end of an initial overdraft period every time, and the like.
As shown in fig. 9, in the method for establishing the objective logic monitoring model, the analysis method mainly screens out illogical transaction behaviors from objective condition attributes in the transaction information to prevent risk loss in time. Common analytical methods are:
and judging whether the place where the transaction occurs is reasonable. The reasonability of the transaction place is generally judged by the occurrence time interval and the physical distance of two transactions before and after. For example, if the two transactions are carried out at an interval of 8 hours before and after the same card, and the transaction is carried out in beijing and new york, respectively, of china, it is considered that the card is at a high risk of counterfeiting, because it takes at least ten hours between beijing and new york even if the fastest transportation vehicle is used. The method is used for monitoring fraud risks, has high requirements on timeliness and generally needs real-time monitoring. Of course, in the times of rapid development, new situations must be considered, for example, the method cannot be used for monitoring online transactions.
And (6) trying to swipe the card. Normal transactions generally do not fluctuate much in their transaction amount and should be unordered, with a high probability of fraud risk when a small transaction occurs followed by a subsequent (typically within tens of minutes) continuous multiple large consumption transactions. The case in this situation is mainly a pseudo card transaction, and fraudsters try to consume a small amount of money first and then continuously consume a large amount of money once successful.
The high risk authorization denies the transaction. The high-risk authorized refusal transaction refers to the transactions of continuously and repeatedly inputting wrong passwords, making mistakes in card numbers, using stolen cards and the like, and the transactions have high probability of fraud and almost certainly are fraud. High risk events are monitored in this way and should be monitored in real time.
The new card starts to overdraft in a short time. The new card is used for carrying out the large overdraft transaction in a short time, and particularly for the large overdraft cash withdrawal transaction, the probability of credit risk of the card is higher. If the card account has the records of overdue and delinquent in the first two months and has high overdraft cash-taking behavior, the cardholder is likely to have the risk of fund interruption, and the risk loss of the bank in the future is far higher than that of a common card.
As shown in FIG. 10, in the transaction habit monitoring model building method, the transaction habits of the customers are generally regular, and more than 99% of transactions follow the regular patterns, if the card usage behavior of the card user does not conform to the regular daily behavior of the card user, the risk of the corresponding transactions is much higher than that of the general transaction behaviors. Common such analytical methods are:
customer consumption/cash withdrawal habits (single pen). And counting the highest consumption/withdrawal amount and the average consumption/withdrawal amount of the customer in the past period, immediately performing correlation judgment with the daily transaction habit indexes when one transaction occurs on the card, and ensuring that the corresponding transaction risk is higher when the transaction exceeds a normal floating range. For example, a user rarely performs cash overdraft cash withdrawal transactions at ordinary times, but recently, if the card is overdrawn for a long time, the card may have a greater credit risk or fraud risk. The method is suggested as a real-time monitoring content, and can achieve a good monitoring effect.
Customer consumption/cash-out habits (running up). Similar to the above monitoring method, the transaction behavior analysis accumulated for a period of time is adopted as a supplement to the single monitoring, and the statistical indexes are changed into monthly average consumption/withdrawal amount, monthly average overdraft amount and the like. The method is mainly used for monitoring the credit risk, has low requirement on timeliness, and can be used as batch monitoring content.
And (5) business rules of the merchant. The analysis method can be applied to monitoring the risk of the merchant in an expanded mode. The monitoring mode is similar to the two methods, but the statistical object is the merchant/transaction place from the customer, and the statistical object mainly counts indexes such as average pen consumption amount, average daily consumption amount/amount and the like in the merchant/transaction place in the past period, and finds out the fraud risk of the merchant and the potential credit risk of the customer for cash register by using the bank card in time. The method has low requirement on timeliness and can be used as batch monitoring content.
Domestic/overseas large consumption. The internal consumption and the external consumption have different characteristics, so the internal consumption and the external consumption can participate in risk operation as different weight factors.
As shown in fig. 11, to pay special attention to the monitoring model establishment method, which mainly aims at the known transaction behaviors needing special attention, most aiming at the fraud risk, available methods are:
a suspected bad account. For suspected bad card accounts with frequent delinquent records and with delinquent degrees reaching certain standards, important attention needs to be paid to overdraft behaviors. The method is mainly used for preventing credit risks.
High risk national/regional transactions. In some countries or regions, bank card fraud is rampant, so for transactions occurring in these countries/regions, the weight of participation in risk calculation should be increased.
And (4) high-risk merchant consumption. Some merchants have fraud behaviors such as multiple cash register, pseudo card consumption and the like in history, and are considered to be high-risk merchants, and for transactions conducted by the merchants, the weights of participation in risk calculation should be increased. The list of merchants may be obtained through statistical analysis of the institution, or may be a blacklist (CPP key merchants) published by a bank card receiving organization.
Consumption by college student groups. College students are a relatively special group, most people are not income, and therefore the potential credit risk is also high. The card transaction and repayment conditions of college students within three months before graduation are monitored in a key mode, and attempts of individual students to prepare large overdraft and abandon cards can be found out in time.
Several methods for constructing a bank card risk monitoring model are introduced from different angles. In fact, a risk behavior, in general, satisfies a number of conditions. Therefore, the above methods need to be combined when constructing the model. Index analysis is consistent throughout. Different behaviors may constitute different models. Different standard setting methods are adopted when the amount index or the stroke number index is set for different behaviors, and a plurality of standard setting methods are also adopted sometimes. By means of cross combination of the methods, a plurality of models can be constructed, so that the models are wide in coverage and strong in pertinence.
The invention provides a system and a method for quantifying and evaluating credit risk and fraud risk of bank card customers, which are objective, effective, simple and convenient to operate and high in processing efficiency, and have important significance for controlling bank card risk of banks and improving income level of banks, and the specific effects are as follows:
risk discovery timeliness. Through the quasi-real-time monitoring mode, the credit risk and the fraud risk of the bank card client can be found in time, and the loss caused by the bank card risk to the bank is effectively reduced.
And (4) risk evaluation comprehensiveness. The bank card transaction is evaluated through a plurality of expert models, and the evaluation is relatively comprehensive.
High efficiency is achieved. Compared with the prior manual processing mode, the method has high processing efficiency and higher operability in the daily bank card risk management work, and effectively improves the efficiency of the bank card risk management;
along with the continuous accumulation of data, the calculation model after repeated correction is more scientific and effective, so that more accurate risk data is generated.
The above embodiments are merely illustrative of the invention and are not intended to be limiting.
Claims (15)
1. A bank card risk monitoring method based on Web is characterized by comprising the following steps:
collecting bank card transaction data in real time;
periodically collecting attribute data of the bank card;
establishing a bank card risk monitoring model;
monitoring the transaction data of the bank card and the attribute data of the related bank card according to the risk monitoring model of the bank card to generate risk monitoring result data of the bank card;
receiving a Web bank card risk monitoring service request;
and displaying corresponding bank card risk monitoring result data in a Web form according to the Web bank card risk monitoring service request.
2. The method of claim 1, wherein said collecting bank card transaction data in real time comprises: collecting bank card swiping consumption data, bank card swiping cashing data, bank card account balance data and bank card account overdraft data in real time;
the periodically collecting the attribute data of the bank card comprises the following steps: and collecting the bank card client data, the bank card account data and the bank card data in batch in a set time period.
3. The method of claim 1, wherein said establishing a bank card risk monitoring model comprises: and establishing a transaction index monitoring model according to the single transaction amount of the bank card, the accumulated transaction amount in the rolling period, the transaction frequency in the rolling period and the current overdraft balance/overdraft proportion of the account.
4. The method of claim 1, wherein said establishing a bank card risk monitoring model comprises: and establishing an objective logic monitoring model according to the bank card transaction place, the card swiping trial event, the transaction refusing event and the new card high overdraft event.
5. The method of claim 1, wherein said establishing a bank card risk monitoring model comprises: and establishing a transaction habit monitoring model according to the single consumption/cash-out habit of the bank card client, the accumulated consumption/cash-out habit of the client, the transaction rule of the client and the international and overseas large-amount consumption.
6. The method of claim 1, wherein said establishing a bank card risk monitoring model comprises: and establishing a special attention monitoring model according to suspected bad accounts of the bank card, high-risk national/regional transactions, high-risk merchant consumption and college student group consumption.
7. The method as claimed in any one of claims 3 to 6, wherein the bank card risk monitoring model is improved according to the accuracy of the bank card risk monitoring result data.
8. A bank card risk monitoring system based on Web is characterized by comprising: the system comprises a bank card risk monitoring device and a risk monitoring Web service device, wherein the bank card risk monitoring device is connected with the risk monitoring Web service device; wherein,
the bank card risk monitoring device includes: the bank card data acquisition unit is used for acquiring bank card transaction data in real time and periodically acquiring bank card attribute data; the monitoring model establishing unit is used for establishing and/or storing a bank card risk monitoring model; the bank card risk monitoring unit is used for monitoring the bank card transaction data and the related bank card attribute data according to the bank card risk monitoring model to generate bank card risk monitoring result data;
the risk monitoring Web service device comprises: the Web service request receiving unit is used for receiving a Web bank card risk monitoring service request; and the Web monitoring result display unit is used for displaying the corresponding bank card risk monitoring result data in a Web form according to the Web bank card risk monitoring service request.
9. The system of claim 8, wherein said bank card transaction data comprises: collecting bank card swiping consumption data, bank card swiping cashing data, bank card account balance data and bank card account overdraft data in real time;
the attribute data of the bank card comprises: and collecting the bank card client data, the bank card account data and the bank card data in batch in a set time period.
10. The system of claim 8, wherein the monitoring model building unit: the method is used for establishing a transaction index monitoring model according to the single transaction amount of the bank card, the accumulated transaction amount in the rolling period, the transaction frequency in the rolling period and the current overdraft balance/overdraft proportion of the account.
11. The system of claim 8, wherein the monitoring model building unit: the method is used for establishing an objective logic monitoring model according to the bank card transaction occurrence place, the card swiping trial event, the transaction rejection event and the new card high overdraft event.
12. The system of claim 8, wherein the monitoring model building unit: the method is used for establishing a transaction habit monitoring model according to the single consumption/cash-out habit of the bank card client, the accumulated consumption/cash-out habit of the client, the transaction rule of the client and the international and overseas large-amount consumption.
13. The system of claim 8, wherein the monitoring model building unit: the method is used for establishing a special attention monitoring model according to suspected bad accounts of bank cards, high-risk national/regional transactions, high-risk merchant consumption and college student group consumption.
14. The system of claim 8, wherein said bank card risk monitoring device further comprises: and the monitoring model improving unit is used for improving the bank card risk monitoring model according to the accuracy of the data of the bank card risk monitoring result.
15. A bank card risk monitoring system based on Web is characterized by comprising: the system comprises a bank card basic data generating device, a bank card risk monitoring device, a risk monitoring Web service device and a user terminal; wherein,
the bank card basic data generation device comprises: the bank card account data unit is used for generating bank card transaction data and attribute data; the real-time transmission unit is used for transmitting the bank card transaction data in real time; the batch transmission unit is used for periodically transmitting the attribute data of the bank cards;
the bank card risk monitoring device includes: the bank card data acquisition unit is used for acquiring bank card transaction data in real time and periodically acquiring bank card attribute data; the monitoring model establishing unit is used for establishing and/or storing a bank card risk monitoring model; the bank card risk monitoring unit is used for monitoring the bank card transaction data and the related bank card attribute data according to the bank card risk monitoring model to generate bank card risk monitoring result data;
the risk monitoring Web service device comprises: the Web service request receiving unit is used for receiving a Web bank card risk monitoring service request; the Web monitoring result display unit is used for displaying corresponding bank card risk monitoring result data in a Web form according to the Web bank card risk monitoring service request;
the user terminal comprises: an input unit for inputting a user instruction; and the display unit is used for displaying the Web interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2008100578726A CN101236638A (en) | 2008-02-20 | 2008-02-20 | Web based bank card risk monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNA2008100578726A CN101236638A (en) | 2008-02-20 | 2008-02-20 | Web based bank card risk monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101236638A true CN101236638A (en) | 2008-08-06 |
Family
ID=39920234
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNA2008100578726A Pending CN101236638A (en) | 2008-02-20 | 2008-02-20 | Web based bank card risk monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101236638A (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104156442A (en) * | 2014-08-13 | 2014-11-19 | 中国银行股份有限公司 | Method and system for multi-dimension accumulation on basis of dynamic data and static data and accumulated data application method |
| TWI488131B (en) * | 2008-12-26 | 2015-06-11 | Syscom Comp Engineering Co | Fake card analysis systems and methods, and computer program products thereof |
| CN105205715A (en) * | 2015-09-24 | 2015-12-30 | 北京银丰新融科技开发有限公司 | On-line bank exception business monitoring system |
| CN105405048A (en) * | 2014-09-09 | 2016-03-16 | 阿里巴巴集团控股有限公司 | Method and device for recognizing periodic behavior |
| CN105590156A (en) * | 2014-11-25 | 2016-05-18 | 中国银联股份有限公司 | Method for detecting high-risk bankcard and data processing device |
| CN107330572A (en) * | 2016-04-28 | 2017-11-07 | 阿里巴巴集团控股有限公司 | Air control method, apparatus and system |
| WO2018014811A1 (en) * | 2016-07-22 | 2018-01-25 | 阿里巴巴集团控股有限公司 | Risk identification method, client device, and risk identification system |
| CN108682088A (en) * | 2018-05-14 | 2018-10-19 | 平安科技（深圳）有限公司 | ATM-based cross-border abnormal transaction determination method and device |
| CN109509082A (en) * | 2018-10-31 | 2019-03-22 | 中国银行股份有限公司 | The monitoring method and device of bank application system |
| CN109636572A (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 readable storage medium storing program for executing of bank card |
| CN110020862A (en) * | 2018-01-10 | 2019-07-16 | 中国移动通信有限公司研究院 | A kind of business risk appraisal procedure, device and computer readable storage medium |
| CN110097369A (en) * | 2019-03-18 | 2019-08-06 | 深圳壹账通智能科技有限公司 | Transaction data processing method, device, electronic equipment and storage medium |
| CN110413609A (en) * | 2019-06-18 | 2019-11-05 | 平安银行股份有限公司 | Data jam mends information table generating method, server and storage medium |
| WO2020011191A1 (en) * | 2018-07-11 | 2020-01-16 | 海南新软软件有限公司 | Monitoring method for unusual digital currency transaction, device, and system |
| CN111062518A (en) * | 2019-11-22 | 2020-04-24 | 成都铂锡金融信息技术有限公司 | Method, device and storage medium for processing hastening service based on artificial intelligence |
| CN111507649A (en) * | 2020-06-30 | 2020-08-07 | 南昌木本医疗科技有限公司 | Financial big data wind control platform based on block chain |
-
2008
- 2008-02-20 CN CNA2008100578726A patent/CN101236638A/en active Pending
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI488131B (en) * | 2008-12-26 | 2015-06-11 | Syscom Comp Engineering Co | Fake card analysis systems and methods, and computer program products thereof |
| CN104156442A (en) * | 2014-08-13 | 2014-11-19 | 中国银行股份有限公司 | Method and system for multi-dimension accumulation on basis of dynamic data and static data and accumulated data application method |
| CN104156442B (en) * | 2014-08-13 | 2018-12-25 | 中国银行股份有限公司 | Cumulative data application method |
| CN105405048A (en) * | 2014-09-09 | 2016-03-16 | 阿里巴巴集团控股有限公司 | Method and device for recognizing periodic behavior |
| CN105590156A (en) * | 2014-11-25 | 2016-05-18 | 中国银联股份有限公司 | Method for detecting high-risk bankcard and data processing device |
| CN105205715A (en) * | 2015-09-24 | 2015-12-30 | 北京银丰新融科技开发有限公司 | On-line bank exception business monitoring system |
| CN107330572B (en) * | 2016-04-28 | 2020-06-02 | 阿里巴巴集团控股有限公司 | Wind control method, device and system |
| CN107330572A (en) * | 2016-04-28 | 2017-11-07 | 阿里巴巴集团控股有限公司 | Air control method, apparatus and system |
| WO2018014811A1 (en) * | 2016-07-22 | 2018-01-25 | 阿里巴巴集团控股有限公司 | Risk identification method, client device, and risk identification system |
| US11075938B2 (en) | 2016-07-22 | 2021-07-27 | Advanced New Technologies Co., Ltd. | Identifying high risk computing operations |
| JP2019525334A (en) * | 2016-07-22 | 2019-09-05 | アリババ グループ ホウルディング リミテッド | Risk identification method, client device, and risk identification system |
| US11570194B2 (en) | 2016-07-22 | 2023-01-31 | Advanced New Technologies Co., Ltd. | Identifying high risk computing operations |
| TWI761349B (en) * | 2016-07-22 | 2022-04-21 | 開曼群島商創新先進技術有限公司 | Risk identification method, client device and risk identification system |
| CN110020862A (en) * | 2018-01-10 | 2019-07-16 | 中国移动通信有限公司研究院 | A kind of business risk appraisal procedure, device and computer readable storage medium |
| CN108682088A (en) * | 2018-05-14 | 2018-10-19 | 平安科技（深圳）有限公司 | ATM-based cross-border abnormal transaction determination method and device |
| WO2020011191A1 (en) * | 2018-07-11 | 2020-01-16 | 海南新软软件有限公司 | Monitoring method for unusual digital currency transaction, device, and system |
| CN109636572A (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 readable storage medium storing program for executing of bank card |
| CN109509082A (en) * | 2018-10-31 | 2019-03-22 | 中国银行股份有限公司 | The monitoring method and device of bank application system |
| CN110097369A (en) * | 2019-03-18 | 2019-08-06 | 深圳壹账通智能科技有限公司 | Transaction data processing method, device, electronic equipment and storage medium |
| CN110413609A (en) * | 2019-06-18 | 2019-11-05 | 平安银行股份有限公司 | Data jam mends information table generating method, server and storage medium |
| CN110413609B (en) * | 2019-06-18 | 2024-03-26 | 平安银行股份有限公司 | Data card hanging and supplementing information table generation method, server and storage medium |
| CN111062518A (en) * | 2019-11-22 | 2020-04-24 | 成都铂锡金融信息技术有限公司 | Method, device and storage medium for processing hastening service based on artificial intelligence |
| CN111062518B (en) * | 2019-11-22 | 2023-06-09 | 成都铂锡金融信息技术有限公司 | Method, device and storage medium for processing collect-promoting business based on artificial intelligence |
| CN111507649A (en) * | 2020-06-30 | 2020-08-07 | 南昌木本医疗科技有限公司 | Financial big data wind control platform based on block chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101236638A (en) | Web based bank card risk monitoring method and system | |
| US8463702B2 (en) | Global compliance processing system for a money transfer system | |
| US7181428B2 (en) | Automated political risk management | |
| US11037229B2 (en) | Fraud detection system for the faster payments system | |
| US7627522B2 (en) | System, apparatus and methods for comparing fraud parameters for application during prepaid card enrollment and transactions | |
| CN111476660B (en) | Intelligent wind control system and method based on data analysis | |
| US20030177087A1 (en) | Transaction surveillance | |
| US12118524B2 (en) | Instant funds availability risk assessment and real-time loss alert system and method | |
| US20020143562A1 (en) | Automated legal action risk management | |
| Eze et al. | Electronic banking and profitability of commercial banks in Nigeria | |
| WO2006130819A2 (en) | Dynamic multidimensional risk-weighted suspicious activities detector | |
| US11941632B2 (en) | Instant funds availability risk assessment and real-time fraud alert system and method | |
| CN115564449A (en) | Risk control method and device for transaction account and electronic equipment | |
| US8036978B1 (en) | Method of upgrading third party functionality in an electronic fraud management system | |
| KR101926270B1 (en) | Analysis apparatus for foreign exchange abnormal transaction and method thereof | |
| CN108198073A (en) | Management method and system after a kind of throwing of stock right financing | |
| KR20090001917A (en) | System and method for early warning on credit customer and program recording medium | |
| CN113919937B (en) | KS monitoring system based on loan assessment wind control | |
| CN109360085A (en) | A kind of bank client responsible investigation method and system | |
| KR20090086370A (en) | System for processing credit customer grading | |
| KR20090001940A (en) | System and method for preliminarily selecting insolvent credit transaction company and program recording medium | |
| CN113822679A (en) | Intelligent anti-fraud loan management system and method with automatic decision making function | |
| CN113191770A (en) | Anti-fraud algorithm model system architecture design method based on gateway transaction | |
| Ibrahim et al. | Fraud management system in detecting fraud in cellular telephone networks | |
| CN118761773A (en) | Bill payment system based on business configuration |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Open date: 20080806 |