Banking operations have changed due to technological advancement. On one hand, modernization in technology has facilitated the daily operation of banks; on the other hand, this has also resulted in an increase in the number of cyber-attacks. Artificial Intelligence has introduced new models to detect and prevent cybercrimes. Some fraud has also occurred due to the involvement of employees inside particular organizations. So, this study has focused on both sides: the machine as well as the human. Firstly, the research has focused on fraud diamond theory and has analyzed factors such as rationalization, capabilities, perceived pressure, and perceived opportunities to understand the psychology of the fraudster. Secondly, Artificial Intelligence characteristics, threat exposure, big data management, explainability, cost effectiveness, and risk prediction are evaluated to explore their use in fraud reduction in banks. The research data have been collected from 15 Banks in Pakistan with the help of a questionnaire using five-item Likert scales. The data have been analyzed using IBM SPSS Software. The results gained after correlation and regression analysis proved that Fraud diamond theory and AI characteristics have positive and significant effects on cybercrimes. This study is a great contribution to the banking industry of Pakistan as it provides a complete analysis to control fraud inside organizations by understanding the mindset of fraudsters with the help of fraud diamond theory. At the same time, outside fraud will be handled with the help of Artificial Intelligence. This will result in banks growth, which ultimately boosts the economy of a country.

A wide range of recent studies are focusing on current issues of financial fraud, especially concerning cybercrimes. The reason behind this is even with improved security, a great amount of money loss occurs every year due to credit card fraud. In recent days, ATM fraud has decreased, while credit card fraud has increased. This study examines articles from five foremost databases. The literature review is designed using extraction by database, keywords, year, articles, authors, and performance measures based on data used in previous research, future research directions and purpose of the article. This study identifies the crucial gaps which ultimately allow research opportunities in this fraud detection process by utilizing knowledge from the machine learning domain. Our findings prove that this research area has become most dominant in the last ten years. We accessed both supervised and unsupervised machine learning techniques to detect cybercrime and management techniques which provide evidence for the effectiveness of machine learning techniques to control cybercrime in the credit card industry. Results indicated that there is room for further research to obtain better results than existing ones on the basis of both quantitative and qualitative research analysis.