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{203665,
        author = {Mohammed Raihan Ahmed and Prof. Shruthi N M},
        title = {GenAI-RAG Based Intelligent Compliance Automation System for Indian Banking using RBI Regulatory Corpus},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {81-87},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=203665},
        abstract = {The Indian banking sector relies heavily on regulatory documents issued by the Reserve Bank of India (RBI), including circulars, master directions, notifications, and compliance rules. These documents are extensive, frequently updated, and difficult to search manually, causing significant delays in decision-making and compliance interpretation. This paper proposes a GenAI + Retrieval-Augmented Generation (RAG) based Intelligent Compliance Automation System specifically tailored for Indian banking. The system employs the all-MiniLM-L6-v2 sentence transformer for semantic embeddings and FAISS for high-speed vector similarity search over a curated RBI regulatory corpus. A Stream lit-based conversational interface enables compliance officers, auditors, and researchers to query regulations in natural language. Experimental results demonstrate a retrieval accuracy of 91.4%, Recall@5 of 0.88, and hallucination rate below 3%, significantly outperforming traditional keyword-based and manual approaches. The proposed system represents a scalable, evidence-grounded step toward modernising regulatory compliance in the Indian financial ecosystem.},
        keywords = {Retrieval-Augmented Generation, Generative AI, RBI Regulatory Compliance, Indian Banking, FAISS, LangChain, NLP, Document Intelligence, FinTech Automation, Vector Embeddings.},
        month = {June},
        }