BANKING DATA FRAUD DETECTION USING MACHINE LEARNING TECHNIQUES

Abstract

Banking system vulnerabilities have made us vulnerable to fraudulent activities that seriously harm the bank's brand and financial standing in addition to harming clients. An estimated large sum of money is lost financially each year as a consequence of financial fraud in banks. Early discovery aids in the mitigation of the fraud by allowing for the development of a countermeasure and the recovery of such losses. This research proposes a machine learning-based method to effectively aid in fraud detection. In order to combat counterfeits and minimize damage, the artificial intelligence (AI) based model will expedite the check verification process. In order to determine the association between specific parameters and fraudulence, we examined a number of clever algorithms that were trained on a public dataset in this article. To reduce the high class of imbalance in the dataset used for this study, it is resampled. The suggested technique is then used to evaluate the data for improved accuracy.