Artificial Intelligence-Driven Business Analytics for Real-Time Fraud Detection in Financial Organizations

Asif Idris Tuhin 1, *, Aloke Soumya Saborna 2, Jamil Uddin Bhuiyan 3, Monohar Barman Momokrishna 4 and Md. Nurul Huda Akhand 5

1 Department of Information and Communication Technology (ICT), Bangladesh Army University of Science and Technology, Saidpur, Bangladesh.
2 Department of Chemistry, Jahangirnagar University. Dhaka, Bangladesh.
3 Ageno School of Business, Golden Gate University, San Francisco, USA.
4 Department of Business Administration, Jiangsu University of Science and Technology, Jiangsu, China.
5 School of Business, Bangladesh Open University, Gazipur, Bangladesh.
* Corresponding Author
ORCID Details
Monohar Barman Momokrishna: https://orcid.org/0009-0001-9865-1842
 
Research Article
International Journal of Science and Technology Research Archive, 2026, 11(01), 059–071.
Article DOI: 10.53771/ijstra.2026.11.1.0032
Publication history: 
Received on 12 August 2026; revised on 20 September 2026; accepted on 22 September 2026
 
Abstract: 
Financial organizations require intelligent fraud-detection systems capable of identifying suspicious transactions accurately and supporting rapid operational decisions. This study developed an artificial intelligence-driven business analytics framework for real-time fraud detection using the PaySim dataset containing 6,362,620 transactions, including 8,213 fraudulent cases. Nineteen pre-transaction features were generated, and four models—Random Forest, XGBoost, Support Vector Machine (SVM), and 1D Convolutional Neural Network (CNN)—were evaluated using a chronological 70% training, 15% validation, and 15% test framework. Random Forest achieved the best performance on the naturally imbalanced test set, obtaining a PR-AUC of 0.9999, precision of 99.87%, recall of 99.35%, and F1-score of 99.61%. The proposed framework also converts fraud-risk scores into operational decisions for transaction approval, manual review, or blocking. The findings demonstrate the potential of AI-driven business analytics for timely fraud-risk identification, although validation with real institutional transaction data is required before practical deployment.
 
Keywords: 
Artificial Intelligence; Business Analytics; Real-Time Fraud Detection; Financial Fraud; Machine Learning; Paysim
 
Full text article in PDF: 
 
Copyright information: 
Copyright © 2026 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0