Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{198619,
        author = {Gautam Mishra and Prof. Dr. Gurjeet Singh and Prof. Dr. Sudhir Pathak},
        title = {Artificial Intelligence–Driven Predictive Models for Financial Fraud Prevention and Cyber Risk Management: Enhancing Infrastructure Resilience in the Indian Banking Industry},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {10825-10842},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198619},
        abstract = {The Indian banking industry operates within an increasingly complex threat landscape characterized by fraud convergence, cyber-enabled financial crime, third-party dependencies, and growing operational interdependence across digital payment systems, cloud infrastructures, and identity platforms. With the rapid expansion of digital banking services such as UPI, mobile banking, and fintech integration, financial institutions face heightened exposure to sophisticated and coordinated cyber threats. Traditional control mechanisms, while still essential, rely heavily on static rules and fragmented monitoring systems that often fail to respond effectively to fast-evolving, large-scale, and cross-channel attacks (Ngai et al., 2011; Abdallah et al., 2016).
This study develops a predictive analytics framework that integrates Artificial Intelligence (AI) and Machine Learning (ML) with resilience-oriented governance to achieve three core objectives: early detection of financial fraud, adaptive cyber risk management, and enhanced protection of banking infrastructure. The research synthesizes a wide range of academic and policy literature and is grounded in publicly available Indian regulatory and industry data up to 2024, including reports and guidelines from the Reserve Bank of India, National Payments Corporation of India, and Indian Computer Emergency Response Team.
The paper argues that effective fraud detection and cyber risk mitigation in Indian banks require multimodal analytical architectures that integrate transaction-level data, customer behavioural patterns, alert histories, entity linkages, authentication signals, and external threat intelligence. Furthermore, the study emphasizes that financial fraud prevention and cyber resilience should be treated as an integrated challenge, as threats such as payment fraud, account takeovers, phishing, business email compromise, ransomware, identity theft, and third-party service disruptions are increasingly interconnected. This study presents an AI-driven framework to enhance fraud detection and cyber risk management in the Indian banking sector. Aligned with guidelines of the Reserve Bank of India, the model integrates techniques such as anomaly detection, graph analytics, gradient boosting, and natural language processing within a risk-based approach. It focuses on improving detection accuracy, transparency, and operational resilience without relying on proprietary data. The framework offers a practical implementation roadmap and policy insights to help Indian banks effectively address evolving cyber-financial threats while maintaining trust and regulatory compliance.},
        keywords = {},
        month = {April},
        }