Exploring the Impact of Preference Functions on Risk Perceptions in Promethee Method

Abstract

This paper investigates the relationship between various PROMETHEE preference functions and risk attitudes in decision making. By employing a simulation-based approach, we varied preference function parameters across a range of alternatives to examine their effects on net flow and corresponding risk perceptions. The study aligns PROMETHEE outputs with theoretical models of rational, risk-neutral behaviour to compare how different settings influence decision-maker risk attitudes. Initial findings reveal that specific preference functions can significantly shape perceptions of risk, promoting either risk-averse or risk-seeking behaviours depending on the function configuration and the number of alternatives. The results contribute to an understanding of how multicriteria decision-making methods like PROMETHEE can be tailored to align with decision-makers’ risk preferences, thereby enhancing decision quality.

Sandro Radovanović

Assistant Professor at University of Belgrade

My research interests include machine learning, development and design of decision support systems, decision theory, and fairness and justice concepts in algorithmic decision making.