Article
CLOUD-BASEDFRAUDDETECTIONSYSTEM FORONLINETRANSACTIONS
The rapid growth of digital payment systems, ecommerce platforms, and online banking has significantly increased the volume of financial transactions, thereby elevating the risk of fraudulent activities. Traditional fraud detection systems, primarily based on static rule-based approaches, are no longer sufficient to handle evolving and sophisticated fraud patterns. This project presents a Cloud-Based Fraud Detection System designed to accurately identify fraudulent transactions using machine learning techniques. The system incorporates data preprocessing, feature engineering, and classification algorithms to analyze transaction patterns and distinguish between genuine and fraudulent activities. Various supervised learning models, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, Naive Bayes, and KNearest Neighbors, are implemented and evaluated using performance metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. To address the issue of imbalanced datasets, techniques such as resampling and Synthetic Minority Over-sampling Technique (SMOTE) are applied. The selected optimized model is integrated into a Flask-based web application that enables real-time fraud prediction. Cloud deployment ensures scalability, flexibility, and high availability, allowing the system to handle large volumes of transaction data efficiently. The proposed system enhances detection accuracy, reduces false positives, and provides a secure and reliable solution for online transaction monitoring. Overall, the integration of machine learning with cloud computing offers a robust framework for preventing financial fraud and improving trust in digital financial systems.
Full Text Attachment
