• Anant Parashar
• Anukriti Manchanda
• Shubham Raturi

The primary objective of data analytics is to unveil concealed patterns and leverage them to facilitate well-informed decision-making across diverse scenarios. The surge in credit card fraud, propelled by technological advancements, has rendered it a vulnerable target for fraudulent activities. This poses a significant challenge in the financial services sector, incurring substantial financial losses annually, amounting to billions of dollars. Developing an effective fraud detection algorithm is a complex undertaking, particularly due to the scarcity of real-world transaction datasets, attributed to confidentiality concerns and the inherent imbalance in publicly available datasets. In response to this challenge, our research addresses the issue by applying a spectrum of supervised machine learning algorithms to identify fraudulent credit card transactions, utilizing a real-world dataset. Taking a step further, we harness these individual algorithms to construct a robust super classifier employing ensemble learning methods. Through our analysis, we discern the critical variables that contribute to heightened accuracy in the detection of fraudulent credit card transactions. This endeavor not only aids in enhancing the efficacy of fraud detection but also sheds light on pivotal factors influencing the success of such algorithms. Moreover, our study extends beyond mere algorithmic application. We undertake a comprehensive comparative analysis, evaluating the performance of various supervised machine learning algorithms documented in the literature against the super classifier implemented in this paper.

"Transactional Fraud Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 1, page no.f800-f804, January-2024, Available :http://www.jetir.org/papers/JETIR2401600.pdf

"Transactional Fraud Detection", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 1, page no. ppf800-f804, January-2024, Available at : http://www.jetir.org/papers/JETIR2401600.pdf