Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal International Conference on Health Science, Green Economics, Educational Review and Technology (IHERT)
Rishabh Vinod Kumar Dubey
Unknown Affiliation
Computer Science & IT Economics, Econometrics & Finance Education Health Professions

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
MACHINE LEARNING PARADIGMS IN BANKING AND FINANCE: TRANSFORMING RISK ASSESSMENT, FRAUD DETECTION, AND CUSTOMER INTELLIGENCE FOR SUSTAINABLE ECONOMIC GROWTH Rishabh Vinod Kumar Dubey; Dr. Ravinder Singh Madhan
International Conference on Health Science, Green Economics, Educational Review and Technology Vol. 7 No. 2 (2025): 10th IHERT (2025): IHERT (2025) SECOND ISSUE: International Conference on Healt
Publisher : Universitas Efarina

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The integration of machine learning (ML) into banking and financial services represents one of the most consequential technological transformations of the twenty-first century. This paper presents a comprehensive, multi-dimensional analysis of ML applications across five core banking domains: credit risk modelling, real-time fraud detection, algorithmic trading, customer relationship management (CRM), and regulatory compliance (RegTech). Drawing on a systematic literature review of 187 peer-reviewed studies published between 2015 and 2025—supplemented by empirical data from 34 global financial institutions spanning North America, Europe, Southeast Asia, and the Gulf Cooperation Council—we evaluate the performance trajectories of classical statistical models against contemporary deep learning architectures including long short-term memory (LSTM) networks, transformer-based models, and graph neural networks (GNNs). Our findings demonstrate that ensemble-based ML models reduce non-performing loan (NPL) ratios by an average of 23.4%, while convolutional neural network (CNN) pipelines achieve fraud-detection precision exceeding 97.8% at sub-millisecond latency. We critically examine regulatory compliance under the EU AI Act (2024) and Basel IV, algorithmic fairness, and federated learning for cross-institutional privacy-preserving collaboration. The paper additionally maps ML innovation onto the green economics agenda ESG scoring, green bond verification, and climate-risk stress testing themes central to the ICHSGEET mandate. We conclude with a forward-looking roadmap identifying quantum-ML hybridisation, causal inference, and large language models as the next frontier of financial intelligence.
Co-Authors Dr. Ravinder Singh Madhan