Systemic Acquired Critique of Credit Card Deception Exposure through Machine Learning

Abstract

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.

Credit Card Fraud Detection Challenges and Solutions: A Review

“…Prevention is intended to add an extra layer of protection to thwart fraudulent attacks and eliminate the possibility of fraud before it happens. This is primarily used for terminal authentication, such as ATMs and payment websites [12,14]. Detection, on the other hand, occurs when prevention fails and it helps identify and alert financial institutions when fraudulent transactions are identified [12].…”

“…This is primarily used for terminal authentication, such as ATMs and payment websites [12,14]. Detection, on the other hand, occurs when prevention fails and it helps identify and alert financial institutions when fraudulent transactions are identified [12]. According to the nature of credit card fraudulent activity, Credit Card Fraud (CCF) can be classified as [9,15]: • Application fraud: a fraudster controls the application and steals the credentials of the cardholder to create a fake account and conduct transactions • Counterfeit fraud / Electronic or manual card imprints: a fraudster copies card details through its magnetic strip by using skimmers.…”

“…CCFDS needs to be improved to avoid loopholes exploited by fraudsters. To do this, it is key to determine the factors and challenges that impact the performance of CCFDS, such as imbalance classes (high number of fraud-free transactions compared to the low number of fraudulent), concept drift (card holder's spending nature changes), and verification latency (where a small transaction amount are timely tested by investigators) [11,12,13]. To this end, this paper presents a review of the challenges of CCFDS and how various techniques can be used to solve CCFD problems.…”

Patient Care and Financial Integrity in Healthcare Billing Through Advanced Fraud Detection Systems

“…Machine learning and artificial intelligence (AI) extend data analytics capabilities by employing algorithms that learn from historical data and continuously improve their predictive accuracy (Bauder et al, 2016;Cheng et al, 2020). Techniques such as decision trees, neural networks, and clustering algorithms have been successfully applied in fraud detection, significantly reducing the incidence of fraudulent claims (Dantas et al, 2022). Machine learning models can adapt to new fraud patterns, making them particularly effective in dynamic and evolving environments (Ekin et al, 2018).…”

“…Machine learning models can adapt to new fraud patterns, making them particularly effective in dynamic and evolving environments (Ekin et al, 2018). For example, healthcare organizations implementing machine learning algorithms report substantial reductions in fraudulent activities and financial losses (Cao & Zhang, 2019;Dantas et al, 2022;Gera et al, 2020). These technologies enhance the accuracy of fraud detection and reduce the workload on human auditors by automating the identification process (Nicholls et al, 2021).…”