Accepted at Elsevier’s Intelligent Medicine journal
Supplier selection is a critical aspect of purchase management within the supply chain, particularly for a Bangladeshi jute company. This process involves the complex evaluation of both qualitative and quantitative criteria. Identifying and engaging the most suitable suppliers is essential to ensure the procurement of high-quality jute yarns and optimize supply chain operations. This research introduces an innovative approach by integrating machine learning (ML) techniques, the fuzzy Analytic Hierarchy Process (AHP), and Bayesian Belief Networks (BBNs) into a user friendly interface (UI). Through expert interviews and a comprehensive literature review, key selection criteria were identified and weighted using fuzzy AHP. Supplier performance was evaluated based on these weighted criteria, while BBNs were used to assess and analyze risk factors, which were incorporated with the ML model. This approach not only streamlines supplier selection but also provides an accurate, risk-informed decision-making tool within the UI. The results show the model achieves an accuracy rate of over 95% in selecting the most suitable suppliers based on user-defined requirements. The combined use of fuzzy AHP, BBNs and ML effectively measures supplier risk and performance, offering a highly efficient, precise solution that can be easily implemented through the developed UI.