Credit Card Fraud Detection Using Hybrid Machine Learning Algorithms

Abstract

Credit cards have a high frequency of transactions taking place daily. There are approximately 36.4 percent fraud related to commercial cards which include credit card, debit card, etc. In 2022 there are 64 million people who use credit cards to initiate the transaction, therefore they are also prone to card fraud. To evaluate the model efficacy, a publicly available credit card data set is used. Investigation on different hybrid algorithms for the given dataset were studied. This research investigates seven different hybrid machine learning models to detect fraudulent activities. Our findings indicated that the hybrid model of Adaboost and LGBM is the most efficient model due to its high performance.