Prediction of Financial Crime Using Machine Learning

Abstract

The purpose of data analytics is to uncover  previously unknown patterns and make use of such patterns  to help in making educated decisions across a wide range of  contexts. Because of advances in modern technology and the  fact that credit cards have become an easy target for fraudu 

lent activity, the incidence of credit card fraud has consider ably increased in recent years. Credit card fraud is a signifi cant issue in the industry of financial services, and it results  in annual losses of billions of dollars. The development of a  fraud detection algorithm is a difficult endeavor due to the  paucity of real-world transaction datasets that are available  due to confidentiality concerns and the very unbalanced  nature of the datasets that are publicly available. Use a da taset from the real world in conjunction with a variety of  supervised machine learning algorithms to identify potential ly fraudulent credit card transactions. In addition, make use  of these techniques to create a super classifier through the  use of ensemble learning methods. Determine which varia bles are the most significant and could perhaps lead to a  higher level of accuracy in the identification of fraudulent  credit card transactions. In addition, we evaluate and discuss  the performance of a number of other supervised machine  learning algorithms that are currently available in the litera ture in contrast to the super classifier that can be implement ed.