Fraud Detection using Machine Learning

Author(s)	Ms. Jahana Sherin KJ, Sudheer S Marar
Country	India
Abstract	The dynamic nature of fraud and evolving tactics render traditional rule-based systems ineffective, leading to substantial financial losses. Objective: This research compares machine learning (ML) and deep learning (DL) approaches for credit card fraud detection using data mining techniques. Methodology: We evaluated ML models—k-Nearest Neighbor (KNN), Random Forest, and Support Vector Machine (SVM)—alongside DL models—Autoencoders, CNN, RBM, and DBN—using transaction datasets from European, Australian, and German sources. Results: Models were assessed based on AUC, Matthews Correlation Coefficient (MCC), and cost of failure to benchmark effectiveness. Conclusion: This study identifies optimal models for accurate, real-time fraud detection in financial systems.
Keywords	Keywords: Machine Learning, Fraud Detection, Credit Card Fraud, Deep Learning, Random Forest, Support Vector Machine, Convolutional Neural Networks
Field	Computer Applications
Published In	Volume 8, Issue 2, March-April 2026
Published On	2026-03-10

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research