Fraud Detection for Online Interbank Transaction Using Deep Learning

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 debit transaction e-commerce and other including interbank transactions. Fast reliable detection important because many losses have due fraud. objective this study obtaining a more effective deep learning model in the system compared similar models. This using CNN, LSTM hybrid CNN-LSTM models are used build system. proposed CNN consist three convolution layer, one maxpooling dropout layer fully connected layer. built by double each 32 cell LSTM, combination 1 64 Dataset taken from March 2021 switching company Indonesia. SMOTE use overcome imbalance training validation Dataset. contains 279513 transactions 2374 categorized results showed scored F1-score value at 93,09%, followed 86,25% 69,22%. Based on these results, can be accurate systems