Evaluation of Digital Wallet Transaction Accuracy using Machine Learning

Non-card retail payments, such as direct-from-the-bank programs and E-wallets, have become increasingly common at both brick-and-mortar and online establishments. In recent years, the use of mobile wallets has increased. It relates to any form of computer program that can “learn” on its own beyond the intervention of a human. Machine learning can detect out-of-the-ordinary purchases and flag them as fraudulent by continuously monitoring data in real-time. Machine learning models are being improved by developing new methodologies based on pre-existing models. An example is a hybrid model in which the dataset is under-sampled and over-sampled; for example, credit card transactions. Digital wallets and machine learning are the main focus of this article.