Selecting Food Loss and Waste Mitigation Technologies under Preference Uncertainty: An Explainable Multicriteria Decision Support Framework

The global food supply chain (FSC) wastes nearly one-third of all food produced—over 2 billion tonnes annually—highlighting the need for technologies to reduce food loss and waste (FLW). Simultaneously, existing solutions are often evaluated in isolation, limiting cross-comparison and informed decision-making. This research develops an explainable decision support system (XDSS) that combines the Best–Worst Method (BWM) and Stochastic Multi-criteria Acceptability Analysis for Group Decision-Making (SMAA-2), providing probabilistic rankings that incorporate preference uncertainty. The framework assesses 100 technology-based strategies for reducing FLW across five criteria: geographic fit, product category, FSC stage, stakeholder role, and technology used. Each scenario undergoes 50,000 Monte Carlo simulations with a fixed seed of 12345 to enable reproducibility. Trade-offs are formalised through penalty functions and weight vectors, while hit-and-run sampling explores feasible weight regions. Example user queries demonstrate how qualitative preferences translate into rank-acceptability profiles: Query 1's maximum rank-1 acceptability is 62%, and Query 2's is 74%. The XDSS provides transparent, robust, and context-sensitive recommendations that support evidence-based technology adoption by SMEs and local authorities. By enabling reproducible and explainable prioritisation, the system advances UN’s Sustainable Development Goal (SDG) 12.3, which aims to reduce FLW along the FSC.