Credit Card Fraud Detection using Deep and Machine Learning

Abstract

Credit-Card Fraud is indeed a menace in the financial system, with far-reaching consequences. The loss of a credit card or its information is considered Credit Card Fraud. A variety of machine learning techniques can be utilized to detect this fraud. This study demonstrates a variety of classification algorithms. Whether the transaction is a fraud or a real one is difficult to determine without an efficient machine learning algorithm. The models that are utilized in this paper were Logistic Regression, XGBoost, and Multi-Layer Perceptron. Kaggle dataset is used to train and test these models. Accuracy, confusion matrix, Area under ROC Curve, recall, f1 score, and precision were the classification metrics used to judge the performance of the proposed system models. This research work conclude that the Multi-Layer Perceptron [MLP] outperforms XGBoost and Logistic Regression.