Multi-objective decision trees with fuzzy TOPSIS: Application to refugee resettlement planning

Abstract

This study combines the use of multi-objective decision trees (MODT) and a fuzzy TOPSIS approach to cope with sequential decision-making under uncertainty with multiple conflicting objectives. To this aim, the MODT generates a Pareto-optimal frontier of solutions for competing objectives, while fuzzy TOPSIS helps assess the noninferior solutions and assign weights to the objectives by considering possible uncertainties in outcomes as well as potential linguistic expression. The proposed approach is illustrated with a temporal decision problem concerning climate-driven refugee resettlement, taking into consideration the challenges of global warming and system interdependencies in an uncertain context. The fuzzy TOPSIS approach was illustrated using two different procedures, and the procedure based on vector normalisation graphically depicts the fuzzy triangular representation of the final ranking.