Enhancing Credit Card Security: Machine Learning Approaches for Fraud Detection

Abstract

This paper explores the application of machine learning techniques in credit card fraud detection. It delves into various ML algorithms, including decision trees, random forests, support vector machines, and neural networks, assessing their efficacy in distinguishing between legitimate and fraudulent transactions. The focus is not only on accurately identifying fraudulent activities but also on minimizing false positives to avoid inconveniencing legitimate cardholders.Feature engineering plays a crucial role in enhancing the performance of machine learning models. By extracting meaningful features from raw transaction data, such as transaction amount, location, time, and frequency, ML algorithms can better discern fraudulent patterns. This paper examines advanced techniques like anomaly detection and ensemble learning, which further improve detection accuracy and robustness