MANY PERSPECTIVE FRAUD DETECTION ALGORITHMS FOR ONLINE OPERATIONS

Abstract

  In the realm of e-commerce, where transactions involve multiple participants such as buyers, sellers, and intermediaries, the detection of fraudulent activities presents a significant challenge. This results in substantial financial losses, with billions of dollars being lost each year. Given the expected surge in the volume of online transactions in the upcoming years, there is a critical need for improved fraud detection strategies. These algorithms work by learning patterns in the data that indicate fraudulent activity. Pattern detection involves discovering the discriminative features in the data. Compared to all related reviews on fraud detection, this survey covers much more technical articles and is the only one, to the best of our knowledge. A long time ago, many methods are utilized for fraud detection system such as Support Vector Machine (SVM), K-nearest Neighbor (KNN), neural networks (NN), Fuzzy Logic, Decision Trees, and many more. All these techniques have yielded decent results but still needing to improve the accuracy. We establish a process model concerning the B2C e-commerce platform, incorporating the detection of user behaviors. Secondly, a method for analyzing anomalies that can extract salient features from event logs is presented. The implementation of the model involves the use of the artificial bee colony (ABC) algorithm to acquire initial weight values. After that, in each step, the agent obtains a sample and performs a classification, with the environment providing a reward for each classification action.