Credit Card Fraud Detection Using Big Data Analytics and Machine Learning
K P Bindu Madavi, K Krishna Sowjanya · 2023
Credit card fraud (CCF) detection is a critical issue faced by financial institutions and their customers. Fraudulent activities in credit card transactions can result in significant financial losses for both parties and detecting fraud is vital to prevent such losses. The detection of CCF remains an ongoing challenge, requiring continuous improvement of fraud detection methods to stay ahead of fraudulent activities. This study focuses on machine learning (ML) algorithms and presents several algorithms that can classify credit card transactions as either genuine or fraudulent. The study includes a comparative literature review analysis of various ML techniques for CCF detection, including Random Forest Classification (RFC), Decision Tree Classifier (DT), Support-Vector Machine (SVM), Logistic Regression (LogReg), K-Nearest Neighbours (KNN), Bagging Classifier (BAG), XGBoost (XGB), Stochastic Gradient Descent Classifier (SGD), and Gaussian Classifier (Gauss). This analysis provides a brief idea for the users to choose the optimal algorithm that gives better accuracy. Results show that each algorithm can accurately detect credit card fraud, and their performance is evaluated based on metrics such as accuracy, precision, recall, and F1-score.