Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Bulletin of Engineering Science, Technology and Industry
Rishabh Vinod Kumar Dubey
Computer Science & Engineering IEC University Baddi, H.P., India
Civil Engineering, Building, Construction & Architecture Computer Science & IT Electrical & Electronics Engineering Engineering

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

Found 1 Documents
Search

 1 
Intelligence at the Vault: How Machine Learning is Revolutionizing Banking, Credit Risk & Fraud Detection. An In-Depth Analysis of Machine Learning Applications for Banking and FinanceThe financial services sector stands at an inflection point, driven by Rishabh Vinod Kumar Dubey; Dr. Ravinder Singh Madhan
Bulletin of Engineering Science, Technology and Industry Vol. 4 No. 1 (2026): March
Publisher : PT. Radja Intercontinental Publishing

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

Abstract

The financial services sector stands at an inflection point, driven by the rapid proliferation of machine learning (ML) technologies that are fundamentally reshaping how banks and financial institutions operate. This research paper presents a comprehensive in-depth analysis of the integration of machine learning in banking and finance, with a focused examination of two primary objectives: (1) enhancing credit risk assessment mechanisms, and (2) improving fraud detection and prevention systems. Drawing on data from over 120 global financial institutions, peer-reviewed literature, and empirical case studies spanning 2018 to 2024, this paper investigates how ML algorithms — including Random Forest, Neural Networks, Support Vector Machines, Gradient Boosting, and Deep Learning architectures — have transformed traditional banking paradigms. Our findings indicate that ML-powered credit risk models achieve accuracy rates of up to 92%, outperforming conventional statistical models by 15-20 percentage points. In fraud detection, ML systems demonstrate detection accuracy of 96%, with false-positive rates reduced by up to 60%. The paper further explores implementation challenges such as data quality issues, model interpretability, regulatory compliance under Basel III/IV frameworks, and ethical considerations including algorithmic bias. Recommendations for responsible ML deployment are provided, alongside projections for future developments including explainable AI (XAI) and federated learning in financial contexts.
Co-Authors Dr. Ravinder Singh Madhan