M. Meher Tilak¹, P. Gayatri², S. Aslesha³, B. Ganesh Kumar⁴ 03 3(1) The rapid expansion of digital payment ecosystems has intensified the threat of ecommerce fraud demanding detection systems that are both accurate and interpretable This paper presents FraudGuard an intelligent webbased fraud detection application built using the Flask framework FraudGuard employs a hybrid decision mechanism that integrates rulebased heuristic scoring with machine learning inference from pretrained ensemble models including XGBoost and a stacking classifier Transaction risk is assessed across multiple dimensions transaction amount thresholds timeofday windows geodesic distance between consecutive transaction locations and international or highrisk location indicators Raw transaction attributes are transformed into a structured feature vector encompassing logtransformed amounts temporal flags and distancederived indicators The rulebased engine generates an initial fraud score along with humanreadable explanatory reasons while the machine learning component augments this score with probabilistic estimates from ensemble models A unified fraud score bounded between 0 and 100 determines a binary fraud classification using a configurable threshold User authentication is secured via SHA256 password hashing and session management Experimental evaluations on representative test scenarios confirm that the hybrid engine consistently assigns elevated scores to suspicious transactions and low scores to legitimate ones FraudGuard bridges the gap between offline machine learning experimentation and interactive web deployment serving as both a practical prototype for fraud analysts and an educational reference for integrating ML models into production Flask applications Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026