Financial Fraud Detection Using PaySim and Machine Learning

Machine Learning (ML) algorithms are robust in addressing complex challenges, such as detecting financial fraud in real-world scenarios. This research highlights the significance of ML algorithms in the context of financial fraud detection. A key focus is the use of PaySim, a tool that generates both genuine and synthetic mobile money transaction datasets. Using this dataset, the article explores data pre-processing, exploratory data analysis (EDA), and the adaptation of three ML algorithms (Naive Bayes (NBs), Random Forest (RF) and Long short-term Memory (LSTM)), offering a novel approach to developing and evaluating more robust fraud detection mechanisms.