Main Article Content
Search Money Laundering is increasing considerably with the development of modern technology and the global superhighways of communication. Money Laundering and other frauds cost consumers and financial companies billions of dollars annually, and fraudsters continuously try to find new rules and tactics to commit illegal actions. Thus, fraud detection systems became essential for banks and financial organizations, to attenuate their losses. However, there is a lack of published literature on money laundering through mobile transaction techniques, due to the unavailable dataset on financial services and especially in the emerging mobile money transaction domain for researchers. Along with the great increase in mobile money transactions, fraud has become increasingly rampant in recent years. This study investigates the efficacy of applying different classification models to mobile money transaction fraud detection problems. Three different classification methods, i.e., Random Forest Classifier, KNNeighbors classifier, and logistic regression are tested for their applicability in fraud detections. The performance evaluation is performed on a synthetic mobile money transaction dataset to demonstrate the benefit of the different models.