Abstract

The main aim of this project is to detect fraudulent credit card transactions by utilizing credit card details. As financial transactions grow in volume and complexity, it becomes increasingly critical for credit card companies to identify fraudulent activities to protect customers from unauthorized charges. Although instances of fraud are relatively infrequent, they present substantial financial risks to both consumers and financial institutions. This research employs three machine learning techniques—One-Class SVM, Local Outlier Factor, and Isolation Forest—to analyse transaction data in real-time, addressing the challenges posed by imbalanced datasets and the sophistication of fraud schemes. By implementing a comprehensive detection system using these models on a credit card transaction dataset, the study aims to enhance the accuracy of fraud detection and provide timely alerts to prevent financial losses. Key results indicate that the proposed methodology significantly improves the identification of fraudulent transactions, ultimately leading to more secure credit card usage for consumers. The conclusions drawn from this research emphasize the necessity for ongoing innovation in fraud detection methodologies to keep pace with the ever- changing landscape of financial fraud.