This study presents a comparative evaluation of various fraud detection techniques in the banking sector,
focusing on traditional methods, advanced AI-based approaches, and hybrid systems incorporating
fuzzy logic. Traditional rule-based and statistical methods are benchmarked against machine learning
models such as Support Vector Machines (SVM) and Random Forest, as well as deep learning techniques
like neural networks. The hybrid system, integrating AI with fuzzy logic, is also assessed. Experimental
results reveal that while traditional methods offer moderate performance, machine learning and deep
learning models significantly improve accuracy, precision, and recall in fraud detection. The hybrid
AI and fuzzy logic system outperforms all other techniques, achieving the highest accuracy and recall
rates despite a longer processing time. This comprehensive analysis highlights the superior effectiveness
of advanced and hybrid methods in handling the complexities of real-time fraud detection, offering
valuable insights for enhancing security measures in the banking industry.
