Scenario-Based Sensitivity Analysis of Ranking Robustness in the TODIM Family: Behavioral Parameters and Normalization Choices

Vol 57, 2025 - 341096
Extended Abstracts (EA)
Favorite this paper
How to cite this paper?
Abstract

A scenario-based sensitivity framework for assessing ranking robustness across five crisp TODIM-family dominance functions is presented, using ExpTODIM as reference configuration. Normalization is examined because it changes the scale of pairwise differences before their nonlinear transformation and may therefore alter behavioral dominance. The framework combines a Python implementation, an interactive dashboard, and ranking indicators for stability and ordinal agreement. In a travel-destination problem with five alternatives and eight heterogeneous criteria, 580 method-specific scenarios vary normalization, loss aversion λ, exponential or logarithmic sensitivity ρ, and other value-function parameters. The leading alternative is preserved throughout the main experiment, whereas full-ranking stability ranges from 0.000 for classical and inverse-weight generalized TODIM to 0.950 for Logarithmic TODIM; ExpTODIM attains 0.880.
Synthetic stress cases yield top-one stability between 0.31 and 0.92, showing that the baseline result is instance-dependent. These findings distinguish recommendation stability from complete ordinal robustness and show how normalization, behavioral assumptions, and method choice should be audited jointly in behavioral MCDA.

Share your ideas or questions with the authors!

Did you know that the greatest stimulus in scientific and cultural development is curiosity? Leave your questions or suggestions to the author!

Sign in to interact

Have a question or suggestion? Share your feedback with the authors!

Institutions
  • 1 Universidade Federal do Rio Grande
Track
  • MCD – Multicriteria Decision Support Methods
Keywords
TODIM family
ExpTODIM
Robustness analysis
Behavioral MCDA
Sensitivity analysis