Online Payments Fraud Detection Using Machine Learning
K. Pujitha1, G. Midun Surya Sai2, J. Venkata Mohan3, K. Brahma Rao4, A. Leela Sai5
Dr. A. S. Kanaka Ratnam6 | Professor, Department of CSE (AI & ML)
228x1a4236@khitguntur.ac.in1, 228x1a4229@khitguntur.ac.in2, 228x1a4231@khitguntur.ac.in3, 228x1a4263@khitguntur.ac.in4, 218x1a4250@khitguntur.ac.in5, sriram.abburi@gmail.com6
Kallam Haranadhareddy Institute of Technology (Autonomous), Guntur, Andhra Pradesh, India
ABSTRACT:
The exponential growth of e-commerce has revolutionized global commerce, offering convenience and accessibility to consumers worldwide. However, this digital transformation has been accompanied by a surge in online payment fraud, posing a significant threat to businesses and consumers alike. Traditional rule based fraud detection systems are increasingly inadequate against sophisticated and evolving fraudulent techniques. Machine learning (ML) has emerged as a powerful paradigm shift in fraud detection, offering the ability to learn complex patterns, adapt to dynamic fraud landscapes, and proactively identify fraudulent transactions in real-time. This paper explores the critical role of machine learning in online payment fraud detection. It delves into the various machine learning techniques employed, including supervised, unsupervised, and deep learning approaches, highlighting their strengths and limitations. The paper further examines the essential data pre-processing steps, feature engineering strategies, and evaluation metrics crucial for building robust and effective fraud detection systems. Moreover, it discusses the challenges and future directions in this dynamic field, emphasizing the ongoing need for innovation to stay ahead of increasingly sophisticated fraudsters in the evolving digital payment ecosystem. Ultimately, this paper underscores the transformative potential of machine learning in safeguarding online transactions and fostering a more secure and trustworthy e-commerce environment
KEYWORDS:
Online Fraud, Payment Transactions, Multifaceted Approach Technology, Fraud Detection, Random Forest, Machine Learning
