Enhancing Security in Mobile Wallet Payments: Machine Learning-Based Fraud Detection Across Prominent Wallet Platforms

This paper presents a novel approach to enhancing the security of financial transactions within mobile wallet applications through the implementation of machine learning-based fraud detection models. This study implements four machine learning models: Random Forest, Logistic Regression, Support Vector Machine and Artificial Neural Networks (ANN), and it evaluates the effectiveness of these models in detecting fraudulent activities within four prominent mobile wallet platforms: EVC Plus, Premier Wallet, Dahabshil Wallet, and IBS Wallet. The evaluation encompasses a comprehensive analysis of model performance metrics, including accuracy, precision, and recall, to assess the efficacy of fraud detection across different wallet ecosystems. The results demonstrated that the ANN-based model exhibits promising accuracy and effectiveness in identifying fraudulent transactions by achieving an accuracy of 91.39%, thereby providing users with enhanced security and confidence in their digital financial transactions. By integrating these fraud detection capabilities into mobile wallet applications, users can proactively mitigate fraud risks and safeguard their financial assets, fostering trust and reliability in the digital financial ecosystem. This research contributes valuable insights and solutions to the ongoing efforts to combat fraud in mobile wallet payments, paving the way for more secure and resilient financial transactions in the digital era.