Digital Fraud Analytics: De¬tection and Prevention of Online Payment Scams

Digital fraud has become a significant concern with the rise of online transactions.Cybercriminals exploit vulnerabilities in payment systems, leading to financial losses and reputational damage.This project aims to develop a machine learning model using the Random Forest algorithm to detect fraudulent transactions.The dataset, sourced from Kaggle, undergoes pre-processing, feature engineering, and data balancing using SMOTE to improve fraud detection accuracy.The model is evaluated based on performance metrics such as accuracy, precision, recall, and F1-score.A Streamlit-based dashboard is implemented for real-time fraud detection visualization, offering an interactive interface for financial institutions and users.The project contributes to enhancing cybersecurity measures by providing an efficient and scalable fraud detection system.The system also generates a Fraud Level score, indicating the potential risk associated with each transaction.This Fraud level score helps in categorizing transactions based on their risk levels, enabling quicker decisionmaking for fraud prevention.