Erdogan, MelikeKonurhan, ZekeriyaYucesan, MelihGul, Muhammet2025-10-112025-10-11202497898196717489789819664610978303202674397830320088319783032026712978981967177997830319494259789819666874978303193696897830319412071865-09371865-0929https://doi.org/10.1007/978-3-031-72284-4_1https://hdl.handle.net/20.500.12684/212642nd International Conference on Science -- Engineering Management and Information Technology -- SEMIT 2023 -- Ankara -- AX6318919With Agriculture 4.0, the use of techniques such as sensors, robots, artificial intelligence, and machine learning in agriculture has started. It is aimed to increase productivity in agriculture by reducing food loss and waste through Agriculture 4.0. It is a critical decision to determine which products should be handled first for Turkey to benefit from the advantages of Agriculture 4.0 as soon as possible compared to developed countries in the field of agriculture. At this point, the problem of which factors should be addressed in the determination of product & product groups arises. To handle this, in this study, a multi-criteria analysis has been applied to prioritize the factors that should be considered in the determination of the critical fruit and vegetable group for export, which should be considered as a priority within the scope of Agriculture 4.0. In this context, a multi-criteria analysis has been carried out by adopting the Bayesian Best Worst Method BWM (B-BWM), which is an improved version of a pairwise comparison-based BWM method and applied to group decisions. As a result of the analysis, the most important and least important criteria to be used in determining which products or product groups are more suitable for Agriculture 4.0 applications in Turkey and which should be invested in priority have been determined. © 2024 Elsevier B.V., All rights reserved.en10.1007/978-3-031-72284-4_1info:eu-repo/semantics/closedAccessAgriculture 4.0Bayesian Best Worst MethodEvaluation CriteriaMcdmAgriculture 4.0Artificial Intelligence LearningBad MethodsBayesianBayesian Best Bad MethodEvaluation CriteriaMachine-learningMcdmMulticriteria AnalysisProduct GroupsConference Object2198 CCIS3172-s2.0-85205096891Q3