Neutrosophic AHP-TOPSIS Framework with Chain of Experts for Automobile Selection Under Uncertainty: A Case Study in Guayaquil, Ecuador

Abstract

The selection of an automobile represents a complex multi-criteria decision-making (MCDM) problem characterized by uncertainty, incomplete information, and contradictory expert opinions. This research presents a novel hybrid methodology that integrates Single-Valued Neutrosophic Sets (SVNS) with the Analytic Hierarchy Process (AHP) and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) for vehicle selection in Guayaquil, Ecuador. The decision process was supported by a Neutrosophic Chain of Experts (CoE) implemented through Large Language Models, which enabled systematic handling of expert disagreements and indeterminacy in criterion weighting and alternative evaluation. The proposed framework evaluates five automobile alternatives against six decision criteria including purchase cost, fuel consumption, safety features, maintenance costs, resale value, and environmental impact. Comparative analysis with classical AHP and TOPSIS demonstrates that the neutrosophic approach provides more robust rankings under uncertainty conditions. Sensitivity analysis through scenario comparison validates the stability of the recommended solution. Results indicate that the Chain of Experts mechanism significantly improves decision quality by explicitly modeling expert consensus levels and managing contradictory assessments. This methodology offers a replicable framework for complex consumer decisions in emerging market contexts.

Keywords