CN111681044A - Method and device for processing point exchange cheating behaviors - Google Patents
Method and device for processing point exchange cheating behaviors Download PDFInfo
- Publication number
- CN111681044A CN111681044A CN202010467604.2A CN202010467604A CN111681044A CN 111681044 A CN111681044 A CN 111681044A CN 202010467604 A CN202010467604 A CN 202010467604A CN 111681044 A CN111681044 A CN 111681044A
- Authority
- CN
- China
- Prior art keywords
- cheating
- bayesian network
- card
- network model
- behavior
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0225—Avoiding frauds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- 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
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0207—Discounts or incentives, e.g. coupons or rebates
- G06Q30/0226—Incentive systems for frequent usage, e.g. frequent flyer miles programs or point systems
- G06Q30/0233—Method of redeeming a frequent usage reward
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Finance (AREA)
- Theoretical Computer Science (AREA)
- Accounting & Taxation (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Artificial Intelligence (AREA)
- Algebra (AREA)
- Probability & Statistics with Applications (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a credit exchange cheating behavior processing method and device, through inputting characteristic information of a card holding user to a preset Bayesian network model, and processing credit exchange transactions in a card according to output of the Bayesian network model, credit card credit exchange behaviors of a card holder can be predicted under the condition that normal card holders use credit exchange without being influenced, and once cheating or suspicious behaviors are found, an alarm is given immediately, and cheating behaviors of customers can be found accurately in time.
Description
Technical Field
The application relates to the technical field of computer detection, in particular to a method and a device for processing point exchange cheating behaviors.
Background
In activities of credit card credit point cashing, credit point gift exchange and credit point exchange merchant coupon picking of a bank, a lawless person uses a credit card to swipe a post machine to virtually consume and accumulate a large number of credit points, and then uses the credit points on hand to obtain cashing and free discount of the bank, or uses the credit points on hand to exchange gifts and then sell the cashing and free discount. Thus, the marketing expense of bank investment is damaged, and the normal card holder is authorized by the interests. In the prior art, banks raise cheating thresholds in security technology, or blacklist interfaces are adjusted to judge whether customers are abnormal, or a set of strict early warning system is provided to require a specially-assigned person to monitor card swiping records of credit cards. Cheating cannot be timely and accurately found when the customer points are exchanged.
Disclosure of Invention
Aiming at the problems in the prior art, the credit card credit.
In order to solve the technical problem, the application provides the following technical scheme:
one aspect of the present invention provides a method for processing point redemption cheating behaviors, including:
inputting characteristic information of a card holding user into a preset Bayesian network model so as to process the in-card point exchange transaction according to the output of the Bayesian network model, wherein the characteristic information comprises transaction information of the in-card point exchange transaction performed by the card holding user;
the output of the Bayesian network model comprises probability data that the exchange behavior of the card holding users belongs to cheating behavior, and the Bayesian network model is obtained by training according to historical characteristic information of a plurality of card holding users.
In some embodiments, the bayesian network model is a naive bayesian network model, the naive bayesian network model including correspondence of each feature information with the probability data of the cheating behavior, the output of the naive bayesian network model further including probability data that the redemption behavior of the card holding user belongs to a normal behavior; the step of processing the point redemption transaction within the card according to the output of the bayesian network model comprises:
comparing the cheating behavior probability data and the normal behavior probability data output by the naive Bayesian network;
if the probability data of the cheating behaviors is larger than the probability data of the normal behaviors, early warning processing, landing processing and/or intercepting processing are carried out on the point exchange transaction in the card;
and if the probability data of the cheating behaviors is smaller than the probability data of the normal behaviors, executing the point exchange transaction in the card.
In certain embodiments, the step of training the bayesian network model comprises:
classifying the historical characteristic information of a plurality of card-holding users according to the characteristic attributes;
generating a characteristic value of each historical characteristic information according to a set rule;
counting the number of users of normal behaviors and cheating behaviors corresponding to each characteristic value aiming at each characteristic attribute;
generating a prior probability expression and a conditional probability expression of the naive Bayesian network model according to the user quantity ratio of the normal behavior and the cheating behavior of each characteristic value;
and generating a posterior probability expression of the naive Bayesian network model according to the prior probability expression and the conditional probability expression.
In certain embodiments, further comprising:
and establishing the Bayesian network model.
In some embodiments, the feature information further comprises: the transaction information comprises user transaction data and transaction flow data.
In some embodiments, before inputting the characteristic information of the card-holding user into the preset bayesian network model, the method further includes:
and carrying out validity check on the characteristic information of the card holding user.
In some embodiments, before inputting the characteristic information of the card-holding user into the preset bayesian network model, the method further includes:
preprocessing the characteristic information of the card holding user, wherein the preprocessing comprises the following steps:
at least one of an exception data clearing process, a feature attribute integration process, and a feature information normalization process.
In some embodiments, before inputting the characteristic information of the card-holding user into the preset bayesian network model, the method further includes:
and correcting the feature information of the newly added feature attribute by adopting a Laplace correction method, wherein the feature information of the newly added attribute is the feature information of which the feature attribute is not included in the historical feature information.
Another aspect of the present invention provides a credit redemption cheating action processing apparatus, including:
the characteristic information input module is used for inputting the characteristic information of a card holding user into a preset Bayesian network model so as to process the in-card point exchange transaction according to the output of the Bayesian network model, wherein the characteristic information comprises the transaction information of the in-card point exchange transaction of the card holding user;
the output of the Bayesian network model comprises probability data that the exchange behavior of the card holding users belongs to cheating behavior, and the Bayesian network model is obtained by training according to historical characteristic information of a plurality of card holding users.
In some embodiments, the bayesian network model is a naive bayesian network model, the naive bayesian network model including correspondence of each feature information with the probability data of the cheating behavior, the output of the naive bayesian network model further including probability data that the redemption behavior of the card holding user belongs to a normal behavior; the credit redemption cheating action processing device further comprises:
the comparison module is used for comparing the cheating behavior probability data and the normal behavior probability data output by the naive Bayesian network;
the processing module is used for carrying out early warning processing, landing processing and/or interception processing on the point exchange transaction in the card if the probability data of the cheating behaviors is larger than the probability data of the normal behaviors;
and the transaction execution module is used for executing the point exchange transaction in the card if the probability data of the cheating behaviors is smaller than the probability data of the normal behaviors.
In certain embodiments, further comprising: a training module, the training module comprising:
the classification unit classifies the historical characteristic information of the card-holding users according to the characteristic attributes;
a feature value generation unit which generates a feature value of each piece of historical feature information according to a set rule;
the statistical unit is used for counting the number of users of normal behaviors and cheating behaviors corresponding to each characteristic value aiming at each characteristic attribute;
the first probability expression generating unit is used for generating a prior probability expression and a conditional probability expression of the naive Bayesian network model according to the user quantity ratio of the normal behavior and the cheating behavior of each characteristic value;
and the second probability expression generating unit is used for generating a posterior probability expression of the naive Bayesian network model according to the prior probability expression and the conditional probability expression.
In certain embodiments, further comprising:
and the model establishing module is used for establishing the Bayesian network model.
In some embodiments, the feature information further comprises: the transaction information comprises user transaction data and transaction flow data.
In certain embodiments, further comprising:
and the validity checking module is used for checking the validity of the characteristic information of the card holding user.
In certain embodiments, further comprising:
the preprocessing module is used for preprocessing the characteristic information of the card holding user, and the preprocessing comprises the following steps:
at least one of an exception data clearing process, a feature attribute integration process, and a feature information normalization process.
In certain embodiments, further comprising:
and the correction module corrects the feature information of the newly added feature attribute by adopting a Laplace correction method, wherein the feature information of the newly added attribute is the feature information of which the feature attribute is not included in the historical feature information.
In a third aspect, the present application provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor implements the steps of the point redemption cheating behavior processing method when executing the program.
In a fourth aspect, the present application provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the point redemption cheating action processing method described herein.
According to the technical scheme, the credit card.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a schematic flow chart of a point redemption cheating action processing method in the embodiment of the present invention.
Fig. 2 is a schematic diagram of a framework between the server S1 and the terminal device B1 in the embodiment of the present invention.
Fig. 3 is a schematic diagram of the architecture among the server S1, the terminal B1, and the terminal B2 in the embodiment of the present invention.
Fig. 4 is a flowchart of the product model training including steps 001 to 004 according to the embodiment of the present invention.
Fig. 5 is a schematic diagram of a model structure in an embodiment of the invention.
Fig. 6 is a schematic structural diagram of a point redemption cheating action processing apparatus in an embodiment of the present invention.
Fig. 7 is a schematic structural diagram of an electronic device in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some embodiments of the present application, but not all embodiments. 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 application.
In the prior art, banks raise cheating thresholds in the security technology, or a blacklist adjusting interface judges whether customers are abnormal, or a set of strict early warning system needs a specially-assigned person to monitor card swiping records of credit cards, so that cheating behaviors cannot be timely and accurately found when customer points are exchanged. The application provides a point exchange cheating behavior processing method, a point exchange cheating behavior processing device, electronic equipment and a computer storage medium for realizing the point exchange cheating behavior processing method. When a card-holding user carries out in-card point exchange transaction, inputting characteristic information of the card-holding user into a preset Bayesian network model so as to process the in-card point exchange transaction according to the output of the Bayesian network model; the output of the Bayesian network model comprises probability data that the exchange behavior of the card holding users belongs to cheating behavior, and the Bayesian network model is obtained by training according to historical characteristic information of a plurality of card holding users. The method can predict credit card.
In a model training scenario, the present application further provides a credit redemption cheating behavior processing apparatus, which may be a server S1, see fig. 2, where the server S1 may be in communication connection with at least one terminal device B1, the terminal device B1 may send the historical feature information of the corresponding card-holding user to the server S1 online, and the server S1 may receive the historical feature information of the corresponding card-holding user online. The server S1 may extract feature information corresponding to multiple feature attributes from the historical feature information online or offline, and generate a training sample set.
In some embodiments, the training sample set may be applied, a topological structure of a bayesian network is established based on a corresponding scoring function and a search algorithm, a conditional probability at each node in the topological structure of the bayesian network is determined based on a maximum likelihood estimation method, a conditional probability table of each node is obtained, and then establishment of a bayesian network model is completed.
In other embodiments, the bayesian network model may be a naive bayesian network model, that is, as shown in fig. 4, the training process may specifically be:
s01: carrying out numerical processing on the historical characteristic information in a non-numerical format to obtain a corresponding characteristic value;
s02: classifying the historical characteristic information of a plurality of card-holding users according to the characteristic attributes;
s03: for each type of characteristic attribute, performing interval division on all characteristic information belonging to the corresponding characteristic attribute according to characteristic values to generate at least one characteristic value interval;
s04: counting the number of users of normal behaviors and cheating behaviors in each characteristic value interval according to each characteristic attribute;
s05: generating a prior probability expression and a conditional probability expression of the naive Bayesian network model according to the user quantity ratio of the normal behaviors and the cheating behaviors in each characteristic interval;
the prior probability of normal behavior is the ratio of the number of normal behavior users to the number of training sample users.
The prior probability of the cheating behavior is the ratio of the number of users of the cheating behavior to the number of users of the training sample.
According to a naive Bayesian network model, all attributes are independent of each other, and the conditional probability of each attribute is the probability of each attribute occurring under normal behaviors and cheating behaviors. Taking training sample client A as an example, client A is young.
The probability of the age attribute of the client occurring under the normal behavior is that the number of users in the normal behavior of the training sample is young compared with the number of users in the normal behavior of the training sample.
The probability that the age attribute of the client occurs under the cheating behavior is the ratio of the number of the users who are young in the cheating behavior in the training sample to the number of the users who are cheating behavior in the training sample.
S06: and generating a posterior probability expression of the naive Bayesian network model according to the prior probability expression and the conditional probability expression.
Based on the above description, the server S1 may also be replaced by a database for being accessed by the server S1, i.e., the server S1 may obtain the historical feature information of the card holding user from the database at different times or at regular time intervals.
In a model prediction scenario, referring to fig. 3, the server S1 may further be in communication connection with at least one terminal device B2, where the terminal device B2 may be a mobile phone, a tablet, a computer, and the like, and when a user performs an in-card point redemption transaction through a credit card app installed on the terminal device B2, the characteristic information of the card user is sent to the server S1 online, and the server S1 inputs the characteristic information as a prediction sample into a preset bayesian network model and outputs probability data that a redemption behavior of the card user belongs to a cheating behavior and a normal behavior.
In a naive bayesian network model, the bayesian network model includes a corresponding relationship between each feature information and prior probability, a corresponding relationship between each feature information and conditional probability, and a corresponding relationship between each feature information and posterior probability, and then the server S1 sends probability data that the exchange behavior of the card user belongs to the cheating behavior and the normal behavior to the terminal device B1 on line, so that the terminal device B1 timely obtains the probability data that the exchange behavior of the card user belongs to the cheating behavior and the normal behavior.
Based on the above, the terminal device B1 may have a display interface, so that the user can view the probability data of the cheating behavior and the normal behavior of the card-holding user sent by the server S1 according to the interface.
It is understood that the terminal device B1 may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a Personal Digital Assistant (PDA), a vehicle-mounted device, a smart wearable device, and the like. Wherein, intelligence wearing equipment can include intelligent glasses, intelligent wrist-watch, intelligent bracelet etc..
In practical applications, part of the processing of point redemption cheating actions may be performed on the side of the server S1 as described above, that is, in the architecture shown in fig. 2 or fig. 3, all operations may be performed in the terminal B1, and the terminal B1 may be directly connected to the terminal B2 and the power system in a communication manner. Specifically, the selection may be performed according to the processing capability of the terminal device B1, the limitation of the user usage scenario, and the like. This is not a limitation of the present application. If all the operations are completed in the terminal device B1, the terminal device B1 may further include a processor for performing a specific process of the point redemption cheating action process.
In addition, in a model prediction scenario, the terminal device B2 may be a payment terminal such as a pos machine or a handheld pos machine, and performs point-of-card redemption by swiping a card through a field service person, at this time, the terminal device B2 receives probability data of whether the redemption behavior of the card user sent from the server S1 belongs to a cheating behavior and a normal behavior, and determines whether the redemption behavior belongs to the cheating behavior according to a preset comparison rule (the probability data of the cheating behavior is greater than the probability data of the normal behavior), if so, the point-of-card redemption transaction is processed on the ground or intercepted directly according to whether the early warning mode and the point-of-card redemption transaction set by a bank teller are on the ground, that is, the point-of-card redemption transaction can be implemented at the terminal device B2.
The terminal device may have a communication module (i.e., a communication unit), and may be in communication connection with the terminal device and the server, so as to implement data transmission with the terminal device and the server. For example, the communication unit acquires the historical feature information through the server so that the terminal device constructs the bayesian network model according to the relevant data. The server may include a server on the task scheduling center side, and in other implementation scenarios, the server may also include a server on an intermediate platform, for example, a server on a third-party server platform that is communicatively linked to the task scheduling center server. The server may include a single computer device, or may include a server cluster formed by a plurality of servers, or a server structure of a distributed apparatus.
The server and the terminal device may communicate using any suitable network protocol, including network protocols not yet developed at the filing date of this application. The network protocol may include, for example, a TCP/IP protocol, a UDP/IP protocol, an HTTP protocol, an HTTPS protocol, or the like. Of course, the network Protocol may also include, for example, an RPC Protocol (Remote Procedure Call Protocol), a REST Protocol (Representational State Transfer Protocol), and the like used above the above Protocol.
This application is through inputing card user's characteristic information to predetermined Bayesian network model to according to the output of Bayesian network model is handled the point exchange transaction in the card, can be under the condition that does not influence normal cardholder and use the point exchange, predict cardholder's credit card point exchange action, in case discover cheating or suspicious action and report to the police immediately, can in time accurately discover customer cheating action. The following embodiments and two application scenarios are specifically described.
In order to realize automatic prediction of cheating behaviors of card-holding users such as credit cards and the like and make the prediction more efficient and accurate, the embodiment of the application provides a point redemption cheating behavior processing method, which is shown in fig. 1 and specifically comprises the following contents:
step 100: inputting characteristic information of a card holding user into a preset Bayesian network model so as to process the in-card point exchange transaction according to the output of the Bayesian network model, wherein the characteristic information comprises transaction information of the in-card point exchange transaction performed by the card holding user;
the output of the Bayesian network model comprises probability data that the exchange behavior of the card holding users belongs to cheating behavior, and the Bayesian network model is obtained by training according to historical characteristic information of a plurality of card holding users.
It can be understood that processing the card credit exchange transaction according to the output of the bayesian network model can be performed by a server, for example, the server directly performs blocking, early warning and the like on the corresponding account, or can be performed by an independent device, for example, an early warning device, a shutdown device and the like connected to the server network are provided, and then the server transmits a corresponding processing instruction to the independent device, which is not limited in this application.
It is understood that the bayesian network bn (bayesian network model), also called belief network, is composed of a Directed Acyclic Graph (DAG) and Conditional Probability Tables (CPT). In a bayesian network, two variables X and Y, if directly connected, indicate a direct dependency between them, and knowledge of X affects the confidence in Y and vice versa. In this sense, we mean that information can be passed between two directly connected nodes. On the other hand, if two variables X and Y are not directly connected, then information needs to pass between the two through the other variables. If all the information paths between X and Y are blocked, information cannot be passed between them. In this case, knowledge of one of the variables does not affect the confidence of the other variable, so X and Y are conditionally independent of each other. If the basic case is considered where two variables X and Y are indirectly connected through a third variable Z, the bayesian network can be decomposed into three basic structures, namely, forward, split and aggregate.
Among them, the advantages of the bayesian network are mainly reflected in:
(1) the Bayesian network describes the interrelation among the data by using a graph method, has clear semantics and is easy to understand. The graphical knowledge representation method facilitates the consistency and the integrity of the probability knowledge base, and the network module can be conveniently reconfigured according to the change of conditions.
(2) Bayesian networks are prone to handling incomplete data sets. All possible data inputs must be known for the traditional standard supervised learning algorithm, if some input is missing, the established model is biased, the method of the Bayesian network reflects a probability relation model among data in the whole database, and an accurate model can still be established if some data variable is missing.
(3) Bayesian networks allow learning causal relationships between variables. In the past data analysis, the causal relationship of a problem is that when the interference is large, the system can not make an accurate prediction. This causal relationship has been included in bayesian network models. The Bayesian method has causal and probabilistic semantics, and can be used for learning causal relationships in data and learning according to the causal relationships.
(4) The combination of Bayesian network and Bayesian statistics can make full use of domain knowledge and sample data information. The Bayesian network expresses the dependency relationship among variables by arcs, expresses the strength of the dependency relationship by a probability distribution table, organically combines the prior information with the sample knowledge, promotes the integration of the prior knowledge and the data, and is particularly effective when the sample data is sparse or the data is difficult to obtain.
More preferably, a naive bayesian network model can be adopted, and in specific application, the prior probability P (c) of whether the point redemption behavior is cheating is firstly calculated, the conditional probability P (x | c) of whether each attribute x is the point cheating behavior is calculated, and the posterior probability P (x | c) of whether the point cheating behavior is cheating is calculated. Based on the Bayesian theorem, the method can be known,
p (x) is a factor for normalization. For a given attribute x, the normalization factor P (x) is independent of whether or not to classify a transaction anomaly, so the problem of predicting a posterior probability P (c | x) of cheating translates into how to estimate the prior probability P (c) and the conditional probability P (x | c) based on training data. However, the conditional probability P (x | c) is a joint probability over all attributes, and is difficult to estimate directly from a limited sample. So this scheme employs a naive bayes classifier, assuming that all attributes are independent of each other, as shown in fig. 5 below.
The posterior probability P (c | x) of whether the customer's point redemption behavior is anomalous may be rewritten as:
in this application, the feature information further includes: the transaction information comprises user transaction data and transaction flow data.
Specifically, the personal information of the user is also called basic information of the user, please refer to table 1, and the characteristic information includes basic information (including age stage, gender, and academic calendar) of the customer, account information (including whether there is an alias of the account, the number of credit cards held, and whether there are other development records in a week), transaction data (including an interval between transactions, whether the request IP of the previous 1 transaction is the same, whether the request MAC of the previous 1 transaction is the same, whether the reserved phone number of the account opening is the same as the login binding phone number, and the amount of money), transaction flow data (including the authentication type, the length of time for the signature verification, the signature verification interval between transactions, whether a single transaction exceeds the credit card limit, and whether a single day exceeds the credit card limit).
TABLE 1 characteristic Attribute and characteristic value correspondence Table
It is understood that, as can be seen from table 1, the feature information may be classified according to feature attributes, and each feature information corresponds to a feature value, for example, in the feature information with the feature attribute of "money amount", the feature value of small money amount is 1, the feature value of medium money amount is 2, and the large money amount is 3.
As can be understood from table 1, the redemption of points by the card holder is a cheating behavior y, which is independent of the attributes, such as age x1, gender x2, amount x3, length of check-out time x4, and the like. That is, y is linked to x1, in direct relation; x1 is not connected to x2 and has no direct relationship.
In order to further improve the accuracy and reliability of the prediction, in an embodiment of the present application, the method for processing the point redemption cheating behavior further includes: and before the characteristic information of the card holding user is input into a preset Bayesian network model, carrying out validity check on the characteristic information of the card holding user to ensure the accuracy of data.
In order to further enable model prediction to be more accurate, before inputting the characteristic information of the card-holding user into a preset bayesian network model, the method further comprises the following steps:
preprocessing the characteristic information of the card holding user, wherein the preprocessing comprises the following steps:
at least one of an exception data clearing process, a data integration process, and a feature information normalization process.
The data integration processing of the invention, such as transaction requests, can only collect transaction time, but we need to count the interval between transactions (whether the time difference between the three consecutive requests is the same), for example, the time interval Δ T1 between the current transaction and the previous transaction needs to be collected, the time interval Δ T2 between the previous transaction and the previous transaction, and then the interval between transactions is obtained through Δ T1 — Δ T2.
Specifically, the data is preprocessed, including processing exception information A, integrating feature data B, and processing feature values C.
A, exception information processing: if a certain piece of basic information of the customer is missing, the basic information of the customer in the previous transaction of the customer is taken as a default. If some transaction information is missing, the data caused by transaction abnormality is considered invalid, and the data is cleared. B, integration characteristics: the collected data are integrated according to the characteristic attributes of the customer point exchange behaviors, for example, the interval between transactions needs to be collected, namely, the time interval delta T1 between the current transaction and the previous transaction and the time interval delta T2 between the previous transaction and the previous two transactions are collected, and then the data are obtained through delta T1-delta T2. And C, processing the characteristic value, namely classifying and standardizing the collected data according to the characteristic attribute value related to the point exchange behavior of the client.
Further preferably, in the present application, before inputting the feature information of the card holder user into the preset bayesian network model, the method further includes:
and correcting the feature information of the newly added feature attribute by adopting a Laplace correction method, wherein the feature information of the newly added attribute is the feature information of which the feature attribute is not included in the historical feature information.
Specifically, if a certain feature attribute value of a customer does not appear in table 1, the conditional probability of whether the customer's point redemption behavior is abnormal behavior at the feature attribute is 0. It is obviously not reasonable to calculate the posterior probability P with a probability value of 0 according to equation 2. In order to avoid that the information carried by the event attribute does not occur in the historical data set, a smoothing process needs to be performed on the attribute value, so that the predicted result is more likely to be an actual value. This scheme employs a laplace correction method. Let N denote the dataset, D denote the number of characteristic attributes, and Ni denote the ith characteristic attribute value.
And re-calculating the prior probability and the conditional probability of the newly-added feature attribute according to the formula 3 and the formula 4. Therefore, by adopting a naive Bayesian classifier learning method and combining a Laplace correction method, the situation that the estimation probability is 0 due to insufficient samples of the training data set can be avoided, and when the training data set is continuously enlarged, the probability value through the Laplace correction method gradually tends to the actual probability value.
It is to be understood that the preprocessing, the laplace correction processing, and the validity check may be performed together or at least partially together in the present application, and are not limited herein.
According to the point exchange cheating behavior processing method, the characteristic information of the card holder is input into the preset Bayesian network model, and the point exchange transaction in the card is processed according to the output of the Bayesian network model, so that the credit card point exchange behavior of the card holder can be predicted under the condition that the normal card holder uses point exchange, and once cheating or suspicious behaviors are found, an alarm is given immediately, and the cheating behaviors of the customer can be found timely and accurately.
The embodiment of the present application further provides a specific embodiment of a point redemption cheating action processing apparatus for implementing all the contents in the point redemption cheating action processing method, see fig. 6, where the point redemption cheating action processing apparatus specifically includes the following contents:
the characteristic information input module 10 is used for inputting the characteristic information of the card-holding user into a preset Bayesian network model so as to process the point exchange transaction in the card according to the output of the Bayesian network model, wherein the characteristic information comprises the transaction information of the point exchange transaction in the card-holding user;
the output of the Bayesian network model comprises probability data that the exchange behavior of the card holding users belongs to cheating behavior, and the Bayesian network model is obtained by training according to historical characteristic information of a plurality of card holding users.
The embodiment of the point redemption cheating behavior processing apparatus provided in the present application may be specifically configured to execute all processing flows of the embodiments of the point redemption cheating behavior processing method in the above embodiments, and the functions of the embodiment are not described herein again, and reference may be made to the detailed description of the method embodiments.
As can be seen from the above description, the credit redemption cheating behavior processing device provided in the embodiment of the present application inputs the feature information of the card holder to the preset bayesian network model through the feature information input module 10, and processes the credit redemption transaction in the card according to the output of the bayesian network model, so that the credit redemption behavior of the card holder can be predicted without affecting the normal use of credit redemption by the card holder, and once cheating or suspicious behavior is found, an alarm is given immediately, and the cheating behavior of the customer can be timely and accurately found.
In order to provide a more accurate and targeted bayesian network model to further improve the efficiency of the diagnosis process and the accuracy of the diagnosis result, in an embodiment of the present application, the device for processing credit redemption cheating actions further includes a model building module 00, where the model building module 00 specifically includes the following contents:
in some embodiments, further comprising: a training module, the training module comprising:
the classification unit classifies the historical characteristic information of the card-holding users according to the characteristic attributes;
a feature value generation unit which generates a feature value of each piece of historical feature information according to a set rule;
the statistical unit is used for counting the number of users of normal behaviors and cheating behaviors corresponding to each characteristic value aiming at each characteristic attribute;
the first probability expression generating unit is used for generating a prior probability expression and a conditional probability expression of the naive Bayesian network model according to the user quantity ratio of the normal behavior and the cheating behavior of each characteristic value;
and the second probability expression generating unit is used for generating a posterior probability expression of the naive Bayesian network model according to the prior probability expression and the conditional probability expression.
In some embodiments, further comprising: and the validity checking module is used for checking the validity of the characteristic information of the card holding user.
In some embodiments, further comprising: the preprocessing module is used for preprocessing the characteristic information of the card holding user, and the preprocessing comprises the following steps:
at least one of an exception data clearing process, a feature attribute integration process, and a feature information normalization process.
In some embodiments, the bayesian network model is a naive bayesian network model, the naive bayesian network model including correspondence of each feature information with the probability data of the cheating behavior, the output of the naive bayesian network model further including probability data that the redemption behavior of the card holding user belongs to a normal behavior; the device for processing point redemption cheating behavior please continue to combine with fig. 6, further comprising:
a comparison module 20 for comparing the cheating behavior probability data and the normal behavior probability data output by the naive Bayesian network;
the processing module 30 is used for performing early warning processing, landing processing and/or interception processing on the point exchange transaction in the card if the probability data of the cheating behavior is larger than the probability data of the normal behavior;
and the transaction execution module 40 is used for executing the credit exchange transaction in the card if the probability data of the cheating behaviors is smaller than the probability data of the normal behaviors.
In order to further improve the coupling of the point redemption cheating behavior prediction and the prediction model, the method further comprises the following steps:
and the correction module corrects the feature information of the newly added feature attribute by adopting a Laplace correction method, wherein the feature information of the newly added attribute is the feature information of which the feature attribute is not included in the historical feature information.
According to the point exchange cheating behavior processing device, the characteristic information of the card holding user is input into the preset Bayesian network model, and the point exchange transaction in the card is processed according to the output of the Bayesian network model, so that the credit card point exchange behavior of the card holding person can be predicted under the condition that the normal card holding person uses the point exchange, and once cheating or suspicious behaviors are found, an alarm is given immediately, and the cheating behavior of the customer can be timely and accurately found.
The embodiment of the present application further provides a specific implementation manner of an electronic device, which is capable of implementing all steps in the point redemption cheating behavior processing method in the foregoing embodiment, and referring to fig. 7, the electronic device specifically includes the following contents:
a processor (processor)601, a memory (memory)602, a communication interface (communications interface)603, and a bus 604;
the processor 601, the memory 602 and the communication interface 603 complete mutual communication through the bus 604; the communication interface 603 is used for realizing information transmission among the point exchange cheating behavior processing device, the client terminal, the terminal equipment and other participating institutions;
the processor 601 is configured to call a computer program in the memory 602, and the processor executes the computer program to implement all the steps in the point redemption cheating action processing method in the above embodiments, for example, when the processor executes the computer program, the processor implements the following steps:
step 100: inputting characteristic information of a card holding user into a preset Bayesian network model so as to process the in-card point exchange transaction according to the output of the Bayesian network model, wherein the characteristic information comprises transaction information of the in-card point exchange transaction performed by the card holding user;
the output of the Bayesian network model comprises probability data that the exchange behavior of the card holding users belongs to cheating behavior, and the Bayesian network model is obtained by training according to historical characteristic information of a plurality of card holding users.
As can be seen from the above description, according to the electronic device provided by the application, the feature information of the card holder user is input into the preset bayesian network model, and the point exchange transaction in the card is processed according to the output of the bayesian network model, so that the credit card point exchange behavior of the card holder can be predicted under the condition that the normal card holder uses the point exchange, and once cheating or suspicious behavior is found, an alarm is given immediately, and the cheating behavior of the customer can be timely and accurately found.
Embodiments of the present application further provide a computer-readable storage medium capable of implementing all steps in the point redemption cheating action processing method in the above embodiments, where the computer-readable storage medium stores thereon a computer program, and when the computer program is executed by a processor, the computer program implements all steps of the point redemption cheating action processing method in the above embodiments, for example, when the processor executes the computer program, the processor implements the following steps:
step 100: inputting characteristic information of a card holding user into a preset Bayesian network model so as to process the in-card point exchange transaction according to the output of the Bayesian network model, wherein the characteristic information comprises transaction information of the in-card point exchange transaction performed by the card holding user;
the output of the Bayesian network model comprises probability data that the exchange behavior of the card holding users belongs to cheating behavior, and the Bayesian network model is obtained by training according to historical characteristic information of a plurality of card holding users.
As can be seen from the above description, the computer-readable storage medium provided by the present application can predict credit card credit point redemption behavior of a cardholder without affecting normal cardholder using point redemption by inputting characteristic information of the cardholder into a preset bayesian network model and processing the in-card point redemption transaction according to the output of the bayesian network model, and can immediately alarm once cheating or suspicious behavior is found, and can timely and accurately find the cheating behavior of the customer.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment. Although embodiments of the present description provide method steps as described in embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or end product executes, it may execute sequentially or in parallel (e.g., parallel processors or multi-threaded environments, or even distributed data processing environments) according to the method shown in the embodiment or the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, in implementing the embodiments of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, and the like. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form. The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein. The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment. In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of an embodiment of the specification. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction. The above description is only an example of the embodiments of the present disclosure, and is not intended to limit the embodiments of the present disclosure. Various modifications and variations to the embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present specification should be included in the scope of the claims of the embodiments of the present specification.
Claims (14)
1. A point redemption cheating action processing method is characterized by comprising the following steps:
inputting characteristic information of a card holding user into a preset Bayesian network model so as to process the in-card point exchange transaction according to the output of the Bayesian network model, wherein the characteristic information comprises transaction information of the in-card point exchange transaction performed by the card holding user;
the output of the Bayesian network model comprises probability data that the exchange behavior of the card holding users belongs to cheating behavior, and the Bayesian network model is obtained by training according to historical characteristic information of a plurality of card holding users.
2. The point redemption cheating behavior processing method of claim 1, wherein the bayesian network model is a naive bayesian network model, the naive bayesian network model comprising correspondence of each feature information with the cheating behavior probability data, the output of the naive bayesian network model further comprising probability data that the card holding user's redemption behavior belongs to normal behavior; the step of processing the point redemption transaction within the card according to the output of the bayesian network model comprises:
comparing the cheating behavior probability data and the normal behavior probability data output by the naive Bayesian network;
if the probability data of the cheating behaviors is larger than the probability data of the normal behaviors, early warning processing, landing processing and/or intercepting processing are carried out on the point exchange transaction in the card;
and if the probability data of the cheating behaviors is smaller than the probability data of the normal behaviors, executing the point exchange transaction in the card.
3. The method of claim 2, wherein the step of training the bayesian network model comprises:
classifying the historical characteristic information of a plurality of card-holding users according to the characteristic attributes;
generating a characteristic value of each historical characteristic information according to a set rule;
counting the number of users of normal behaviors and cheating behaviors corresponding to each characteristic value aiming at each characteristic attribute;
generating a prior probability expression and a conditional probability expression of the naive Bayesian network model according to the user quantity ratio of the normal behavior and the cheating behavior of each characteristic value;
and generating a posterior probability expression of the naive Bayesian network model according to the prior probability expression and the conditional probability expression.
4. The credit redemption cheating behavior processing method of claim 2, further comprising, before inputting the card user's characteristic information into a preset bayesian network model:
and carrying out validity check on the characteristic information of the card holding user.
5. The credit redemption cheating behavior processing method of claim 1, further comprising, before inputting the card user's characteristic information into a preset bayesian network model:
preprocessing the characteristic information of the card holding user, wherein the preprocessing comprises the following steps:
at least one of an exception data clearing process, a feature attribute integration process, and a feature information normalization process.
6. The credit redemption cheating behavior processing method of claim 3, further comprising, before inputting the card user's characteristic information into a preset Bayesian network model:
and correcting the feature information of the newly added feature attribute by adopting a Laplace correction method, wherein the feature information of the newly added attribute is the feature information of which the feature attribute is not included in the historical feature information.
7. A credit redemption cheating action processing device is characterized by comprising:
the system comprises a characteristic information input module, a processing module and a processing module, wherein the characteristic information input module is used for inputting the characteristic information of a card holding user to a preset Bayesian network model so as to process the in-card point exchange transaction according to the output of the Bayesian network model, and the characteristic information comprises the transaction information of the in-card point exchange transaction of the card holding user;
the output of the Bayesian network model comprises probability data that the exchange behavior of the card holding users belongs to cheating behavior, and the Bayesian network model is obtained by training according to historical characteristic information of a plurality of card holding users.
8. The point redemption cheating behavior processing apparatus according to claim 7, wherein the bayesian network model is a naive bayesian network model that includes correspondence of each feature information with the cheating behavior probability data, an output of the naive bayesian network model further including probability data that the card holding user's redemption behavior belongs to normal behavior; the credit redemption cheating action processing device further comprises:
the comparison module is used for comparing the cheating behavior probability data and the normal behavior probability data output by the naive Bayesian network;
the processing module is used for carrying out early warning processing, landing processing and/or interception processing on the point exchange transaction in the card if the probability data of the cheating behaviors is larger than the probability data of the normal behaviors;
and the transaction execution module is used for executing the point exchange transaction in the card if the probability data of the cheating behaviors is smaller than the probability data of the normal behaviors.
9. The credit redemption cheating action processing apparatus according to claim 8, further comprising: a training module, the training module comprising:
the classification unit classifies the historical characteristic information of the card-holding users according to the characteristic attributes;
a feature value generation unit which generates a feature value of each piece of historical feature information according to a set rule;
the statistical unit is used for counting the number of users of normal behaviors and cheating behaviors corresponding to each characteristic value aiming at each characteristic attribute;
the first probability expression generating unit is used for generating a prior probability expression and a conditional probability expression of the naive Bayesian network model according to the user quantity ratio of the normal behavior and the cheating behavior of each characteristic value;
and the second probability expression generating unit is used for generating a posterior probability expression of the naive Bayesian network model according to the prior probability expression and the conditional probability expression.
10. The credit redemption cheating action processing apparatus according to claim 8, further comprising:
and the validity checking module is used for checking the validity of the characteristic information of the card holding user.
11. The credit redemption cheating action processing apparatus according to claim 8, further comprising:
the preprocessing module is used for preprocessing the characteristic information of the card holding user, and the preprocessing comprises the following steps:
at least one of an exception data clearing process, a feature attribute integration process, and a feature information normalization process.
12. The credit redemption cheating action processing apparatus according to claim 8, further comprising:
and the correction module corrects the feature information of the newly added feature attribute by adopting a Laplace correction method, wherein the feature information of the newly added attribute is the feature information of which the feature attribute is not included in the historical feature information.
13. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps of the point redemption cheating action processing method of any one of claims 1-6.
14. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the point redemption cheating behavior processing method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010467604.2A CN111681044A (en) | 2020-05-28 | 2020-05-28 | Method and device for processing point exchange cheating behaviors |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010467604.2A CN111681044A (en) | 2020-05-28 | 2020-05-28 | Method and device for processing point exchange cheating behaviors |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111681044A true CN111681044A (en) | 2020-09-18 |
Family
ID=72453674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010467604.2A Pending CN111681044A (en) | 2020-05-28 | 2020-05-28 | Method and device for processing point exchange cheating behaviors |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111681044A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112184306A (en) * | 2020-09-26 | 2021-01-05 | 中国建设银行股份有限公司 | Automatic cashback method, device, electronic equipment and computer readable storage medium |
| CN116089401A (en) * | 2023-02-17 | 2023-05-09 | 国网浙江省电力有限公司营销服务中心 | User data management method and system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040225473A1 (en) * | 2003-05-07 | 2004-11-11 | Intelligent Wave, Inc. | Fraud score calculating program, method of calculating fraud score, and fraud score calculating system for credit cards |
| CN103077172A (en) * | 2011-10-26 | 2013-05-01 | 腾讯科技（深圳）有限公司 | Method and device for mining cheating user |
| CN103744878A (en) * | 2013-12-21 | 2014-04-23 | 云南大学 | Large-scale Bayesian network parallel inference method based on MapReduce |
| CN105912690A (en) * | 2016-04-20 | 2016-08-31 | 上海垒土资产管理有限公司 | Grouping Naive Bayes model based multi-factor online prediction method and system |
| CN106096996A (en) * | 2016-05-31 | 2016-11-09 | 北京奇虎科技有限公司 | The detection method of mobile terminal cheating and related device |
| CN106599200A (en) * | 2016-12-14 | 2017-04-26 | 陕西学前师范学院 | Intelligent remote financial data anti-cheating system and anti-cheating method thereof |
| CN106897743A (en) * | 2017-02-22 | 2017-06-27 | 广州市勤思网络科技有限公司 | The anti-cheating big data detection method of movable attendance checking based on Bayesian model |
| CN107481019A (en) * | 2017-07-28 | 2017-12-15 | 上海携程商务有限公司 | Order fraud recognition methods, system, storage medium and electronic equipment |
| US20180239870A1 (en) * | 2016-07-27 | 2018-08-23 | Intuit Inc. | Method and system for identifying and addressing potential healthcare-based fraud |
| CN109034194A (en) * | 2018-06-20 | 2018-12-18 | 东华大学 | Transaction swindling behavior depth detection method based on feature differentiation |
| CN110378699A (en) * | 2019-07-25 | 2019-10-25 | 中国工商银行股份有限公司 | A kind of anti-fraud method, apparatus and system of transaction |
-
2020
- 2020-05-28 CN CN202010467604.2A patent/CN111681044A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040225473A1 (en) * | 2003-05-07 | 2004-11-11 | Intelligent Wave, Inc. | Fraud score calculating program, method of calculating fraud score, and fraud score calculating system for credit cards |
| CN103077172A (en) * | 2011-10-26 | 2013-05-01 | 腾讯科技（深圳）有限公司 | Method and device for mining cheating user |
| CN103744878A (en) * | 2013-12-21 | 2014-04-23 | 云南大学 | Large-scale Bayesian network parallel inference method based on MapReduce |
| CN105912690A (en) * | 2016-04-20 | 2016-08-31 | 上海垒土资产管理有限公司 | Grouping Naive Bayes model based multi-factor online prediction method and system |
| CN106096996A (en) * | 2016-05-31 | 2016-11-09 | 北京奇虎科技有限公司 | The detection method of mobile terminal cheating and related device |
| US20180239870A1 (en) * | 2016-07-27 | 2018-08-23 | Intuit Inc. | Method and system for identifying and addressing potential healthcare-based fraud |
| CN106599200A (en) * | 2016-12-14 | 2017-04-26 | 陕西学前师范学院 | Intelligent remote financial data anti-cheating system and anti-cheating method thereof |
| CN106897743A (en) * | 2017-02-22 | 2017-06-27 | 广州市勤思网络科技有限公司 | The anti-cheating big data detection method of movable attendance checking based on Bayesian model |
| CN107481019A (en) * | 2017-07-28 | 2017-12-15 | 上海携程商务有限公司 | Order fraud recognition methods, system, storage medium and electronic equipment |
| CN109034194A (en) * | 2018-06-20 | 2018-12-18 | 东华大学 | Transaction swindling behavior depth detection method based on feature differentiation |
| CN110378699A (en) * | 2019-07-25 | 2019-10-25 | 中国工商银行股份有限公司 | A kind of anti-fraud method, apparatus and system of transaction |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112184306A (en) * | 2020-09-26 | 2021-01-05 | 中国建设银行股份有限公司 | Automatic cashback method, device, electronic equipment and computer readable storage medium |
| CN116089401A (en) * | 2023-02-17 | 2023-05-09 | 国网浙江省电力有限公司营销服务中心 | User data management method and system |
| CN116089401B (en) * | 2023-02-17 | 2023-09-05 | 国网浙江省电力有限公司营销服务中心 | User data management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11430057B1 (en) | Parameter-based computer evaluation of user accounts based on user account data stored in one or more databases | |
| US11977995B2 (en) | Machine learning artificial intelligence system for predicting hours of operation | |
| JP6913241B2 (en) | Systems and methods for issuing loans to consumers who are determined to be creditworthy | |
| US11810204B2 (en) | Artificial intelligence transaction risk scoring and anomaly detection | |
| CN110443700A (en) | The transregional piece of moneytary operations optimized using machine learning | |
| US9294497B1 (en) | Method and system for behavioral and risk prediction in networks using automatic feature generation and selection using network topolgies | |
| AU2023206104A1 (en) | Network-based automated prediction modeling | |
| US11587101B2 (en) | Platform for detecting abnormal entities and activities using machine learning algorithms | |
| US11928016B2 (en) | Failure prediction in distributed environments | |
| US20190073714A1 (en) | System and method for issuing a loan to a consumer determined to be creditworthy onto a transaction card | |
| US20210264448A1 (en) | Privacy preserving ai derived simulated world | |
| US20200134579A1 (en) | Systems and methods for identifying indicators of cryptocurrency price reversals leveraging data from the dark/deep web | |
| CN111681044A (en) | Method and device for processing point exchange cheating behaviors | |
| Adedoyin et al. | Predicting fraud in mobile money transfer using case-based reasoning | |
| Ojugo et al. | Forging a user-trust memetic modular neural network card fraud detection ensemble: A pilot study | |
| US20210174367A1 (en) | System and method including accurate scoring and response | |
| Nilsen | Limelight: Real-time detection of pump-and-dump events on cryptocurrency exchanges using deep learning | |
| CN111797942A (en) | User information classification method and device, computer equipment and storage medium | |
| CN112541765A (en) | Method and apparatus for detecting suspicious transactions | |
| Kaur | Development of Business Intelligence Outlier and financial crime analytics system for predicting and managing fraud in financial payment services | |
| CN114787846A (en) | Method and system for assessing reputation of merchant | |
| US20230145924A1 (en) | System and method for detecting a fraudulent activity on a digital platform | |
| Mendes | Forecasting bitcoin prices: ARIMA vs LSTM | |
| Vaquero | LITERATURE REVIEW OF CREDIT CARD FRAUD DETECTION WITH MACHINE LEARNING | |
| CN117313008A (en) | Abnormal node determination method and device, storage medium and electronic device |
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 |