Identifying Potentially Fraudulent Credit Card Transactions with the use of Soft Computing Methods

Abstract

One of the most pervasive difficulties facing modern finance organisations, corporations, and governments is the alarming rise in fraudulent or dishonest practises around financial transactions, especially those using credit cards. As difficulties go, this is one of the more prevalent ones. To protect the interests of both consumers and businesses, it is crucial to implement a fraud detection system that heavily relies on the use of intelligent fraud detection tactics. Numerous fraud detection methods, strategies, and systems have been reported in the scholarly literature; many of them make use of intelligent strategies like algorithms and frameworks. This project begins out with an exploratory data analysis aimed at identifying potentially fraudulent credit card transactions. The authors next provide some categorization models that are implemented in soft computing by means of ingenious methodologies. For the aim of evaluation, several other classification algorithms such decision trees, random forests, and logistic regressions have been used in addition to the Knearest neighbour (K-NN) technique. The suggested model provides a more accurate, computationally efficient, and lightweight option for detecting credit card fraud.