Comparative analysis of the Performance of Machine Learning Algorithms & Models in Detecting Fraud in Fintech platforms in Uganda Fintech Industry

The study compares the performance of machine learning (ML) algorithms in detecting fraud on fintechplatforms, with a focus on Uganda's mobile money ecosystem. With financial fraud evolving incomplexity, traditional rule-based systems struggle to keep up. The research evaluates supervised,unsupervised, and hybrid ML approaches using a publicly available dataset, and Python-basedimplementations. The study results show the superior performance of ensemble methods (RandomForests) and Neural Networks (deep learning models) in detecting fraudulent activity, especially whenenhanced by techniques such as Synthetic Minority Over-Sampling Technique (SMOTE) andAutoEncoders. This work provides a comparison of the performance of different ML models and revealsthe significance for Uganda's fintech firms to adopt context-sensitive, data-driven fraud detectionsystems. It proposes strategic recommendations for data sharing, labour capacity building, regulatoryreform, and Artificial Intelligence (AI) adoption.