A Bayesian best-worst approach with blockchain integration for optimizing supply chain efficiency through supplier selection

Supplier selection is a complex Multi-Criteria Decision-Making (MCDM) problem where decision-maker (DM) preferences heavily influence decision criteria and outcomes. Suitable suppliers capable of meeting performance criteria are central to successful Blockchain Technology (BT) implementation. Numerous qualitative factors influence blockchain adoption within organizations, particularly in the communication between retailers and suppliers via Blockchain, where qualitative uncertainties abound. This study aims to develop a robust system within a probabilistic and fuzzy framework to integrate DMs' judgments amidst uncertainty effectively. Leveraging the Bayesian best-worst method (BWM), optimal weights for evaluating supplier criteria are determined. This method employs Markov-chain Monte Carlo (MCMC) to calculate the probability of preferring one criterion over another, facilitating confidence level elucidation between criterion pairs and enhancing criteria rankings. Supplier ranking is performed using the Fuzzy Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method. The efficacy of the proposed approach is demonstrated through a case study utilizing real data from the railway supply chain. Results indicate the model's effectiveness in optimizing supplier selection and enhancing supply chain performance.