Advancing MCDM with ChatGPT-4: AI-Powered Decision-Making

Kevser Arman () and Arzu Organ ()
Additional contact information
Kevser Arman: Pamukkale University
Arzu Organ: Pamukkale University

A chapter in Artificial Intelligence of Everything and Sustainable Development, 2025, pp 55-65 from Springer

Abstract: Abstract This study explores the integration of ChatGPT-4 as a decision-making tool and evaluates its effectiveness in comparison with traditional Multi-Criteria Decision-Making (MCDM) methods. In particular, it examines ChatGPT-4’s potential to generate weighting, ranking, and clustering outcomes that align with MCDM methods’ assessments through the use of chain-of-thought and few-shot prompting techniques. by employing a structured methodology and prompt-engineering strategies, this research investigates how AI-assisted decision-making can enhance transparency, efficiency, and accuracy in multi-criteria selections. Building on existing literature regarding AI’s role in MCDM, the study specifically focuses on grouping EU member and candidate countries based on their logistics performance. The findings highlight few-shot prompting as a strong alternative to conventional MCDM methods, particularly in scenarios that demand speed and flexibility. Results further indicate that the few-shot prompting technique outperforms the chain-of-thought technique. Moreover, the study suggests that AI-powered tools can serve as a practical substitute for traditional MCDM approaches, especially in fast and adaptive decision-making processes. The incorporation of AI into established decision-making frameworks has the potential to substantially enhance outcomes, particularly in data-driven and rapidly evolving environments.

Keywords: MCDM; MEREC; CoCoSo; Artificial intelligence; Prompt engineering (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-981-96-7202-8_4

Ordering information: This item can be ordered from
http://www.springer.com/9789819672028

DOI: 10.1007/978-981-96-7202-8_4

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().