Naive Bayes Model for Scam Detection: An Analysis of Financial Fraud

Author(s)	Vishal Sharma, Dr. Ankush Shrivastava
Country	India
Abstract	The exponentially growing number of digital financial transactions has brought a concurrent rise in the occurrence of increasingly complex and sophisticated financial fraud. This requires accurate and efficient automated detection mechanisms. In this research, the use of the Naive Bayes classifier is explored to detect scams in financial transaction data. The detection problem is framed as one of binary classification, which assumes the Gaussian distributions for the continuous features and derives the full mathematical formalism of the Naive Bayes model. The tests are performed using a real-world transaction dataset of 10,000 instances (balanced with respect to legitimate and scam transactions) and assess its accuracy, precision, recall, and F_1-score. The Naive Bayes classifier achieved a high average accuracy of 97.3%, the scam class precision is 96.9%, the recall for the scam class is 95.0%, and F_1-score is 95.9%. The findings in this research suggest that even with its inherent simplifications, Naive Bayes continues to be a formidable choice for real-time scam detection.
Keywords	Naive Bayes, scam detection, financial fraud, classification, Gaussian Naive Bayes, machine learning, transaction monitoring, fraud analytics.
Field	Engineering
Published In	Volume 8, Issue 3, May-June 2026
Published On	2026-05-31

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