Enhancing Security for Online Transactions through Supervised Machine Learning and Block Chain Technology in Credit Card Fraud Detection

This research probed the capabilities of supervised machine learning algorithms in credit card fraud detection, an essential facet of contemporary digital finance, and integrated the transformative idea of blockchain for added security and transparency. Findings highlighted the predominant efficiency of the XGBoost algorithm, which recorded an accuracy of 97%, a precision of 94%, and an AUC of 0.97. Other notable performers included the Gradient Boosting Machine and Random Forest. The study underscores the potential of integrating advanced machine learning techniques and blockchain technology to significantly enhance fraud detection systems, ultimately enhancing user trust and the security of online transactions. Recommendations for the adoption of algorithms like XGBoost and the utilization of blockchain ensures immutable transaction records and continuous monitoring for adaptive defense against evolving cyber threats. Future research directions might encompass the exploration of hybrid models, blockchain integration, and deep learning techniques to further enhance fraud detection mechanisms. This research provides research reference for financial institutions that strive to optimize the digital transaction standards.