EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

2096. Choice and the Machine: overcoming the challenge in the selection of multiple criteria decision analysis method through the use of large language model.

Invited abstract in session TA-45: Multiple-Criteria Decision Support, stream Decision Support Systems.

Tuesday, 8:30-10:00
Room: 30 (building: 324)

Authors (first author is the speaker)

1. Aritad Choicharoon
Leeds University Business School, University of Leeds
2. Richard Hodgett
Leeds University Business School, University of Leeds

Abstract

Multiple Criteria Decision Analysis (MCDA) methods are widely used in various disciplines as a logical solution to a complex decision-making problem. The majority of the research to date has been focused on the development of new MCDA methods for different decision-making challenges. However, given this large number of potential solutions, there is an accessibility challenge in identifying an appropriate method, especially for people who are unfamiliar with them. There has been work which proposed a framework to help select a MCDA method, but the challenge with this is that it requires an understanding of MCDA terminology.

We propose a decision support system to solve such a challenge, utilising artificial intelligence in the form of a large language model (LLM) as an interface between the decision-maker and a framework for the selection of MCDA methods from a pool of 56 potential options. The decision-maker would briefly describe their decision-making problem in a natural language format which would then undergo a LLM reasoning process to extract the necessary information and align them with the choice framework model. It will identify and interact with decision-makers to provide and justify a method that is most appropriate to their problem.

Keywords

Status: accepted

Back to the list of papers