Copyright © 2025 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{185560,
        author = {P.sai kiran and M.srinivasa rao},
        title = {A Hybrid AI-MCDM Framework for Explainable supplier selection : A case study in the oil and gas sector},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {5},
        pages = {1829-1838},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=185560},
        abstract = {Supplier selection is a strategic function in procurement, directly influencing cost,quality, and operational efficiency. Traditional Multi-Criteria Decision-Making (MCDM)methods such as AHP and TOPSIS provide transparency but struggle with large-scale, data-rich environments. Meanwhile, Machine Learning (ML) offers predictive power but often lacks interpretability. To address this gap, we propose two hybrid frameworks that integrate interpretable ML with MCDM. The first combines Decision Trees (DT) with AHP to reduce selection complexity and enhance ranking transparency. The second integrates FUCOM and TOPSIS with a DT classifier for improved adaptability. Using real datasets from the oil and gas sector, the DT+AHP model achieved up to 90% precision, while FUCOM+TOPSIS+DT improved F1-score by 5% compared to standalone ML models. The results demonstrate that hybrid approaches balance accuracy with explainability, making supplier decisions both data-driven and transparent. These findings highlight the potential of hybrid AI– MCDM systems for procurement in dynamic industrial environments.},
        keywords = {Supplier Selection, Hybrid AI–MCDM, Decision Tree, AHP, FUCOM, TOPSIS, Procurement},
        month = {October},
        }