Credit Card Fraud Detection Using a New Hybrid Machine Learning Architecture

The negative effect of financial crimes on institutions has grown dramatically over the years. To detect such as credit card fraud, several single and hybrid machine learning approaches have been used. However, these significant limitations no further investigation different algorithms for a given dataset were studied. This research proposes investigates seven models to fraudulent activities with real word dataset. developed consisted two phases, state-of-the-art used first then, methods constructed based best algorithm from phase. Our findings indicated that model Adaboost + LGBM is champion it displayed highest performance. Future studies should focus studying types hybridization in domain.