Credit Card Fraud detection using Random Forest and CART Algorithms
Credit Card Fraud detection using Random Forest and CART Algorithms
Authors:
Anisetty Manogna 1, Kola Pavani 2, Chandragiri Siva Kumar 3, Battula Yaswanth 4
1B-TECH IT STUDENT SRI MITTAPALLI COLLEGE OF ENGINEERING
2B-TECH IT STUDENT SRI MITTAPALLI COLLEGE OF ENGINEERING
3B-TECH IT STUDENT SRI MITTAPALLI COLLEGE OF ENGINEERING
4B-TECH IT STUDENT SRI MITTAPALLI COLLEGE OF ENGINEERING
Abstract - Credit card fraud is a significant concern for financial institutions, causing substantial financial losses annually. Effective detection of fraudulent transactions is essential to reduce risk and improve security. This paper investigates credit card fraud detection using two machine learning algorithms: Random Forest (RF) and Classification and Regression Trees (CART). The dataset contains transactions made by European cardholders in September 2013, with 492 fraudulent transactions out of 284,807 total transactions. Due to the highly imbalanced nature of the dataset, appropriate evaluation metrics are applied. Experimental results demonstrate that the Random Forest classifier achieves superior performance in terms of accuracy, precision, recall, and F1-score compared to CART, making it a promising approach for real-time fraud detection.
Key Words: Credit Card Fraud, Random Forest, CART, Machine Learning, Imbalanced Data, Fraud Detection.