Abstract
The effectiveness of transaction fraud detection methods directly affects the loss of users in online transactions. However, for low-frequency users with small transaction volume, the existing methods cannot accurately describe their transaction behaviors for each user, or lead to a high misjudgment rate. So we propose a new method for individual behavior construction, which can make the behavior of low-frequency users more accurate by migrating the current transaction group behavior and transaction status. Firstly, we consider the user's only historical transactions, combined with the optimal risk threshold determination algorithm, to form the user's own transaction behavior benchmark. Secondly, through the DBSCAN clustering algorithm, the behavior characteristics of all current normal samples and fraud samples are extracted to form the common behavior of the current transaction group. Finally, based on historical transaction records, the current transaction status is extracted using a sliding window mechanism. The combination of the three constitutes a new transaction behavior of the user. On this basis, a multi-behavior detection model based on new transaction behavior is proposed. According to the result of each behavior, Naive Bayes model is used to calculate the probability that current transaction belongs to fraud, and finally determine whether current transaction is fraud. Experiments prove that the method proposed in this paper can have a good effect on low-frequency users, which can accurately identify fraud transactions and has a low misjudgment rate for normal transactions.
Highlights
With the rapid development of e-commerce, online payment has become more and more popular
Fu et al [10] proposed the derived characteristics of transaction entropy to characterize the user’s transaction behavior, and converted the original one-dimensional transaction data into a twodimensional transaction matrix and input the convolutional neural network to establish a credit card fraud detection model based on deep learning
Current trading group behavior GBB = [TBB, FBB], where TBB is a matrix of Q × 6, representing the normal transaction behavior of Q class, and FBB is a matrix of P × 6, representing the fraud transaction behavior of P class
Summary
With the rapid development of e-commerce, online payment has become more and more popular. The third is to analyze group trading users and use machine learning and deep learning methods to mine common behaviors of users, such as neural networks [4], random forests [7], [8], relationship networks [13], HMM [14], and so on These methods train models based on transaction data for all users. They can only mine the common characteristics of all users, it is difficult to learn the individual behavior of each user [15], [24], and such models cannot effectively identify new types of fraud [19]–[21]. VOLUME 8, 2020 method, the fifth section introduces data source and experimental results, and the sixth section summarizes research results and future prospects
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
