• Kunal Roy
• Roshni Chaubey
• Sristita Paul
• Rahul Kumar Singh
• Siddhartha Majumder

With the fast pace of growth in digital payment systems, online transactions are easier and more convenient; however, it has also increased the cases of frauds significantly. The main aim of this project is to develop an advanced ML-based fraud detection system for improved security of online payments. This system will be designed based on historical transaction data that recognizes patterns and anomalies to distinguish between fraudulent and legitimate transactions. It uses techniques such as data preprocessing, feature engineering, and the use of robust ML algorithms like Random Forest and Gradient Boosting to ensure high detection accuracy. Reducing false positives and negatives is very important while ensuring security and user experience. This work contributes to the development of scalable, adaptive, and efficient fraud detection mechanisms tailored to modern digital ecosystems.

Data Preprocessing, Digital Payment Systems, Feature Engineering, Fraud Detection, Gradient Boosting, Machine Learning, Random Forest.

"Enhancing Online Payment Security using ML : Advanced Techniques for Fraud Detection in Digital Transactions", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.d156-d160, December-2024, Available :http://www.jetir.org/papers/JETIR2412319.pdf

"Enhancing Online Payment Security using ML : Advanced Techniques for Fraud Detection in Digital Transactions", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppd156-d160, December-2024, Available at : http://www.jetir.org/papers/JETIR2412319.pdf