Credit card fraud remains a critical and escalating challenge within the global financial ecosystem, driving substantial annual losses and necessitating the continuous evolution of detection methodologies. This paper presents a systematic literature review, conducted via the Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework, which comprehensively analyzes the state-of-the-art in electronic credit card fraud detection. Through a rigorous examination of 49 high-quality studies, this review maps the methodological evolution from traditional rulebased systems and statistical models to advanced artificial intelligence techniques, including machine learning, deep learning, and graph-based approaches. The analysis reveals that while individual methods possess distinct advantages and limitations; such as: the interpretability of rules versus the adaptability of machine learning, no single methodology offers a complete solution. The findings strongly indicate that hybrid models, which integrate multiple techniques, and graph technology, which uncovers relational fraud patterns, represent the most promising directions for achieving high accuracy and robustness. Consequently, this review concludes that fraud cannot be eradicated but must be managed through dynamic, multilayered, and intelligent systems. Key recommendations include the adoption of hybrid frameworks, a greater emphasis on explainable AI (XAI) for transparency, and the exploration of privacy preserving technologies like federated learning. This study provides a consolidated foundation for researchers and practitioners, outlining a clear trajectory for developing next-generation, adaptive fraud detection systems capable of mitigating emerging threats in the digital finance landscape.
Sayikanmi et al. (Sun,) studied this question.