AN INTELLIGENT CREDIT CARD FRAUD DETECTION FRAMEWORK USING RANDOM FOREST AND CART MACHINE LEARNING ALGORITHMS

Abstract

The rapid growth of digital payment systems and online banking has significantly increased the use of credit cards for financial transactions. Along with this growth, credit card fraud has become one of the major challenges faced by financial institutions, resulting in substantial economic losses and security concerns. Detecting fraudulent transactions accurately and in real time is essential to minimize financial risks and protect customer information. Traditional fraud detection methods are often unable to identify sophisticated fraud patterns due to the highly imbalanced and continuously evolving nature of transaction data. This project proposes an intelligent credit card fraud detection framework using Random Forest and Classification and Regression Tree (CART) machine learning algorithms to improve fraud detection accuracy. The system utilizes a publicly available Kaggle credit card transaction dataset, where data preprocessing techniques such as data cleaning, normalization, and train-test splitting are performed before model training. The Random Forest algorithm constructs multiple decision trees and combines their predictions to improve classification performance, while the CART algorithm provides efficient binary classification based on decision rules. The performance of both algorithms is evaluated using classification metrics such as accuracy, precision, recall, F1-score, and confusion matrix analysis. Experimental results demonstrate that the Random Forest classifier outperforms the CART algorithm by achieving approximately 99.7% classification accuracy, with superior capability in identifying fraudulent transactions while minimizing false-positive predictions. The proposed framework provides an efficient, scalable, and reliable solution for real-time fraud detection in financial systems. Its implementation using Python and machine learning libraries enables fast model development and deployment, making it suitable for banking institutions, online payment gateways, and financial organizations. The proposed system contributes to enhancing transaction security, reducing financial fraud, and supporting intelligent decision-making in modern digital payment ecosystems.