Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
With increasing use of online transactions, there are increasing concerns for financial fraud, as many criminals and fraudsters are acting in new and better ways to affect internet users and businesses involved in electronics transactions. To put it a different way, where fraud protection methods have been slow to move forward with the comparison of then to now in the availability of sophisticated fraudsters, thus, while fraud detection methods themselves do move forward, fraudsters adapt to fraudulent detection methods by now responding to changes in transaction data that may be suspect, noticing trends in the recent transaction behaviours that may have changed, and being able to provide alerts when anomalies are detected. It is very interesting that machine learning methods can detect and push back reduce financial fraud that is so critical in society today, and so, in this paper, looks at applying machine learning techniques which are supervised methods at some of the most popular supervised learning methods with Logistic Regression, Random Forest and XGBoost, and looks at data that has been balanced using the SMOTE(Synthetic Minority Over Sampling Technique). In this development of the web application where certain methods of the machine learning can be made accessible in the app to demonstrate an application that is efficient to address a solution to detect online financial fraud via a web application built on the Flask framework, and with the added feature of email alerts automatically being sent to alert when instances occur. Experimental results demonstrate high accuracy and efficacy for this method which offers better security along with a reduced number of false positives.
Keywords:
Fraud Detection, Machine Learning, AI, Real-Time Alerts, Online Transactions, SMOTE, Flask based web application, Supervised Learning
Cite Article:
"Smart Fraud Detection System for Online Payments Using AI and Real-Time Notifications", International Journal of Science & Engineering Development Research (www.ijrti.org), ISSN:2455-2631, Vol.10, Issue 4, page no.c638-c643, April-2025, Available :http://www.ijrti.org/papers/IJRTI2504299.pdf
Downloads:
000324
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator