Online Transaction Fraud Detection System Based on Machine Learning
Bocheng Liu, Xiang Chen, Kaizhi Yu · Journal of Physics Conference Series · 2021
Abstract With the rapid development of Internet technology, the scale of online transactions is constantly expanding. At the same time, the related network transaction fraud problem has become more significant. Compared with the credit card transaction, the network transaction has the characteristics of low cost, wide coverage and high frequency, which makes the detection of fraud more complex. Aiming at the problem of difficult fraud detection in network transactions, this paper designed two fraud detection algorithms based on Fully Connected Neural Network and XGBoost, whose AUC values can achieve 0.912 and 0.969 respectively. Meanwhile, we designed an interactive online transaction fraud detection system based on XGBoost model, which can automatically analyze the transaction data uploaded and return the fraud detection results to users.