MACHINE LEARNING APPROACHES FOR CREDIT CARD FRAUD DETECTION: A PREDICTIVE ANALYSIS

Abstract

Technology is increasing at a very rapid pace and with this growing technology e-commerce and online transactions have also grown up and it mostly contains transactions through credit cards. When people use credit cards more often, the chances of credit card fraud are rising drastically. The most susceptible system to fraud is the credit card system. Customers and financial institutions lose billions of dollars per year due to credit card fraud, and criminals are constantly searching for new ways to commit crimes. As a result, for banks and financial institutions to reduce their losses, fraud detection systems have become critical. This research investigates the output of different types of classification models, including Decision Tree, Random Forest, Support Vector Machines (SVM), Naive Bayes, and K-Nearest Neighbors (KNN). An open data set on credit card transactions from Kaggle was used in this research. Three classifiers namely random forest, KNN, and SVM were used for modelling. The performance of the three machine learning models was compared using Precision, Recall, Accuracy, and F1 measures. It was found that Random Forest and KNN performed equally better than SVM. The knowledge acquired from this research may direct future investigations targeted at enhancing the ability of financial institutions and banks to withstand such fraudulent activities.