Can ChatGPT Serve as a Multi-Criteria Decision Maker? A Novel Approach to Supplier Evaluation

Multi-Criteria Decision Making (MCDM) has found extensive applications across various domains such as business, engineering, education, and academia, with supplier evaluation being a quintessential task among them. Traditional MCDM models typically gather quantitative and qualitative data through methods like questionnaire surveys administered to industry experts. Subsequently, experts proficient in MCDM techniques employ methods like the Analytic Hierarchy Process (AHP) and Fuzzy Comprehensive Evaluation (FCE) to conduct objective and scientific evaluations of suppliers. However, with the advent of large language models (LLMs) like ChatGPT, these models are now capable of assisting or even replacing human experts in tasks such as writing, consulting, and code generation. Bridging these two paradigms, this paper introduces a novel expert-level supplier evaluation method based on ChatGPT. Initially, a supplier dataset was collected and organized, followed by evaluations using traditional MCDM models to obtain expert assessment results. Thereafter, the ChatGPT model was employed to generate evaluations for this supplier dataset, which were then compared with the expert evaluations from the previous step. The final results indicate that the supplier evaluations based on the ChatGPT model closely align with those of human experts, underscoring the capability of ChatGPT to serve as a Multi-Criteria Decision Maker. Furthermore, this method proves to be faster and more cost-effective.