Fraud detection and prevention in mobile money transfer based on machine learing methods

Keywords: Classification Algorithms, Data Mining, Mobile Money Service, fraud detection; Kappa Coefficient, Matthews Correlation Coefficient, Database The use of mobile money transaction is growing steadily throughout the world, especially in Africa, with the potential to revolutionize the continent's money-based economy into a cashless economy. With the increased use of mobile money services and the number of use cases designed every day, it is imperative to develop a comprehensive approach to mobile money security that will reduce security risks and prevent fraud. Some mobile money service providers have lost millions of dollars to this growing threat. This research therefore examines the measures that mobile network operators providing mobile money services can use to prevent and detect fraud. The study also looks at the perception of mobile money users about the link between mobile phone protection and the security of mobile money service on their phones. This study uses qualitative and quantitative data collected using the Paysim data generator, and classification algorithms to detect the fraud in mobile money transaction.