Credit Card Fraud Detection Using Different Machine Learning Techniques

Abstract

Changing technology leads to various advancements. With the growth of ecommerce websites online transactions have become an important and necessary part of our lives. Because credit cards are the most popular method of payment, the number of fraud cases involving them is on the rise. It is critical for credit card firms to be able to spot fraudulent credit card transactions so that customers are not charged for things they did not buy. As frequency of transactions is increasing, number of fraudulent transactions are also increasing rapidly. Thus, to stop these frauds, we need a powerful fraud detection system that detects it in an accurate manner. So, in this research we are trying to find the solution by applying different machine learning algorithms such as logistic regression, random forests, AdaBoost, KNN, ANN, Gradient Boosting classification, and XGBoosting, to detect the fraudulent transactions by building efficient system. The results of all the algorithms are based on accuracy, precision, recall, and F1-score. The ROC curve is plotted based on the confusion matrix. All the algorithms are compared and the algorithm that has the greatest accuracy, precision, recall, and F1-score is AdaBoost and Gradient Boosting which considered as the best algorithm that is used to detect the fraud.