Retrieval-Augmented Intelligent Data Warehousing for Decision Support Systems

  • Authors

    • N. Seshagiri Information Technology Pioneer, National Informatics Centre, India. Author

    DOI:

    https://doi.org/10.67228/30715717/IJDEIC-2025PI8M4W

    Published 02-05-2025

  • Retrieval-Augmented Generation (RAG), Intelligent Data Warehouse, Decision Support System (DSS), Business Intelligence, Enterprise Analytics, Artificial Intelligence, Machine Learning, Vector Database, Knowledge Retrieval, Large Language Models, Semantic Search, Data Integration, Explainable AI

    Issue

    Vol. 8 No. 1 (2025)

    Section

    Articles

    How to Cite

    [1]
    S. N, “Retrieval-Augmented Intelligent Data Warehousing for Decision Support Systems”, IJDEIC, vol. 8, no. 1, pp. 01–16, Feb. 2025, doi: 10.67228/30715717/IJDEIC-2025PI8M4W.

  • Abstract

    Organizations are increasingly challenged by massive volumes of structured, semi-structured, and unstructured data generated from enterprise systems, cloud platforms, IoT devices, social media, and industrial applications. Traditional data warehouses are effective for historical analytics but lack the ability to provide semantic understanding, dynamic knowledge retrieval, and real-time decision support. This study proposes a Retrieval-Augmented Intelligent Data Warehousing (RAIDW) framework that integrates Retrieval-Augmented Generation (RAG), vector databases, knowledge graphs, semantic search, machine learning, and large language models with conventional data warehousing. The framework combines ETL pipelines, vector indexing, retrieval ranking, and transformer-based reasoning to deliver context-aware, explainable, and accurate analytical insights. Machine learning improves retrieval relevance, while feedback mechanisms continuously enhance system performance. Experimental results demonstrate significant improvements in retrieval precision, analytical accuracy, semantic consistency, query efficiency, and decision confidence compared to traditional OLAP-based systems. The proposed architecture supports diverse domains, including healthcare, finance, supply chain, manufacturing, cybersecurity, and education, while ensuring governance, scalability, transparency, and security. By grounding AI-generated responses in trusted enterprise knowledge, the framework minimizes hallucinations and enables reliable, intelligent enterprise decision support.

  • References

    [1] P. Lewis et al., "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks," Advances in Neural Information Processing Systems, vol. 33, pp. 9459–9474, 2021.

    [2] S. Izacard and E. Grave, "Leveraging Passage Retrieval with Generative Models for Open-Domain Question Answering," International Conference on Learning Representations (ICLR), 2021.

    [3] J. Guu, K. Lee, Z. Tung, P. Pasupat, and M. Chang, "REALM: Retrieval-Augmented Language Model Pre-Training," Journal of Machine Learning Research, vol. 22, no. 1, pp. 1–48, 2021.

    [4] T. Brown et al., "Large Language Models in Enterprise Artificial Intelligence: Opportunities and Challenges," IEEE Computer, vol. 56, no. 8, pp. 48–57, 2023.

    [5] J. Gao, Y. Xiong, and X. Liu, "Knowledge Graph Enhanced Intelligent Decision Support Systems: A Survey," IEEE Access, vol. 10, pp. 124512–124530, 2022.

    [6] M. Stonebraker and A. Pavlo, "Cloud Data Warehousing: Architecture, Performance, and Future Trends," Proceedings of the VLDB Endowment, vol. 15, no. 12, pp. 4100–4113, 2022.

    [7] J. Chen, H. Wang, and L. Zhang, "Semantic Data Integration Using Knowledge Graphs for Enterprise Analytics," IEEE Access, vol. 11, pp. 48672–48686, 2023.

    [8] R. Johnson, S. Gupta, and P. Kumar, "Artificial Intelligence Techniques for Intelligent Decision Support Systems: A Review," IEEE Access, vol. 11, pp. 92310–92334, 2023.

    [9] M. L. Kohn, A. F. M. Olwal, and J. Wang, "Vector Databases for Large-Scale Semantic Search Applications," IEEE Internet Computing, vol. 28, no. 1, pp. 40–49, 2024.

    [10] Y. Li, X. Zhou, and H. Chen, "Explainable Artificial Intelligence for Enterprise Decision Support: Recent Advances and Challenges," IEEE Access, vol. 12, pp. 13541–13562, 2024.

    [11] A. Singh and P. Sharma, "Machine Learning-Based Query Optimization in Cloud Data Warehouses," IEEE Transactions on Cloud Computing, vol. 12, no. 2, pp. 612–625, 2024.

    [12] X. Zhao, L. Wang, and M. Huang, "Retrieval-Augmented Large Language Models for Enterprise Knowledge Management," IEEE Access, vol. 13, pp. 12015–12034, 2025.

    [13] H. Kim, J. Park, and S. Lee, "Hybrid Relational and Vector Database Architectures for Intelligent Enterprise Analytics," IEEE Transactions on Knowledge and Data Engineering, vol. 37, no. 1, pp. 98–112, 2025.

    [14] S. Verma, R. Gupta, and N. Patel, "Generative AI and Retrieval-Augmented Analytics for Business Intelligence Applications," IEEE Access, vol. 13, pp. 84210–84231, 2025.

  • Downloads