Performance Comparison of Various Supervised Learning Algorithms for Credit Card Fraud Detection

The aim of this research work is to classify credit card fraudulent transactions. Nowadays, online transactions have become a necessary part of our lives. Credit card fraud has skyrocketed. In fact, it is one of the most prevalent menaces of the banking, financial services, and insurance (BFSI) sector. In the era of digitalization, there are so many frauds happening. Credit card fraud is the most common thing happening nowadays; thus, the need to identify the same is necessary. In this work, firstly, collected the unstructured data related to this research from a frequently used site, i.e., Kaggle. Secondly, implemented different machine learning classification algorithms (supervised) like linear regression (LR), decision trees (DT), artificial neural networks (ANN), and gradient boosting (GB). Among all machine learning (ML) algorithms, DT outperforms the other algorithms with accuracy. The performance of these specified algorithms was marked by their comparative analysis with some performance metrics.