Title: Beyond the Pareto front: A TOPSIS-based framework for multi-criteria design with the multiDoE R Package Authors:  Matteo Borrotti - University of Milan-Bicocca (Italy) [presenting]
Abstract: Optimizing a single criterion, such as D-optimality or A-optimality, is no longer sufficient in many experimental scenarios. Real-world applications often involve conflicting design criteria that must be jointly balanced. A novel application of the TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method is introduced within the multi-criteria design of experiments framework, as implemented in the CRAN-published R package multiDoE (https://cran.r-project.org/web/packages/multiDoE/index.html). After a brief overview of classical selection strategies on the Pareto front, we present the TOPSIS-based ranking approach regarding interpretability, stability, and performance. The methodology is illustrated through real and simulated case studies involving multiple optimality criteria. How the multiDoE package can facilitate reproducible workflows in multi-criteria DoE scenarios is also discussed.