Performance of machine learning techniques in the detection of financial frauds

Financial fraud presents more and more threat that has serious consequences in the financial sector. As a result, financial institutions are forced to continually im-prove their fraud detection systems. In recent years, several studies have used machine learning and data mining techniques to provide solutions to this problem. In this paper, we propose a state of art on various fraud techniques, as well as de-tection and prevention techniques proposed in the literature such as classification, clustering, and regression. The aim of this study is to identify the techniques and methods that give the best results that have been perfected so far.