Detecting Electronic Banking Fraud on Highly Imbalanced Data using Hidden Markov Models

Recent researches have revealed the capability of Machine Learning (ML) techniques to effectively detect fraud in electronic banking transactions since they potential new and unknown intrusions. A major challenge application ML detection is presence highly imbalanced data sets. In many available datasets, majority are genuine with an extremely small percentage fraudulent ones. Designing accurate efficient system that low on false positives but detects activity a significant for researchers. this paper, framework based Hidden Markov Models (HMM), modified Density Based Spatial Clustering Applications Noise (DBSCAN) Synthetic Minority Oversampling Technique Techniques (SMOTE) proposed dataset. The various transaction types, amounts frequency taken into consideration by model enable effective detection. With different number hidden states HMMs, simulations performed four (4) approaches their performances compared using precision, recall rate F1-Score as evaluation metrics. study that, our approach able more reasonably positives.