TECHNIQUES FOR DETECTING CREDIT CARD FRAUD

Credit card fraud is a critical crime. Fraud detection have impacts on many industries such as banks, retail, financial services, health care, etc. According to the Federal Trade Commission reports, data shows that credit card theft has raised by 44.6% from year 2019 to 2020. Newly released Federal Trade Commission data shows that in year 2021 about 389,737 credit card theft report are received. This research work focus to explore possible ways to identify credit card fraudulent activities that have a negative impact on financial institutions. In this paper Machine learning algorithms such as Random Forest, Decision Trees and Xgboost, K-Means, Logistic Regression and Neural Network are implemented for detection of fraudulent transactions. A comparative analysis of these algorithms is performed to determine the best model for predicting credit card frauds. Our result shows that Random Forest Algo give highest Accuracy, Precision and AUC score for credit card fraud detection.