Fraud Detection for Online Interbank Transaction Using Deep Learning

Abstract

The World Banking with its various financial services is an easy target for fraudsters to carry out their actions. Various kinds of fraud that occurred such as credit card fraud, online payment fraud, debit card fraud, online transaction fraud, e-commerce fraud and other services including interbank online transactions. Fast and reliable fraud detection is important because many financial losses have occurred due to fraud. The objective of this study is obtaining a more effective deep learning model for fraud detection in the interbank online transaction system compared to similar models. This study using CNN, LSTM and hybrid model CNN-LSTM models are used to build an interbank online transaction system. The proposed model CNN consist of three convolution layer, one maxpooling layer, one dropout layer and one fully connected layer. The proposed model LSTM built by double layer LSTM with each layer consist 32 cell LSTM, dropout layer and one fully connected layer. The proposed model CNN-LSTM built by combination three convolution layer, 1 maxpooling layer, dropout layer, 1 LSTM layer with 64 LSTM cell and one fully connected layer. The Dataset taken from an interbank online transaction in March 2021 from one of the switching company in Indonesia. SMOTE is use to overcome the imbalance Dataset in training and validation Dataset. The Dataset contains 279513 transactions with 2374 transactions categorized as fraud. The results showed that the CNN model scored an F1-score value at 93,09%, followed by the LSTM model at 86,25% and the CNN-LSTM hybrid model at 69,22%. Based on these results, the proposed CNN model can be accurate for fraud detection in interbank online transaction systems compared to similar models.