Robust Directional Counterfactual Explanations for Black-Box Models

J. Martín-Chávez, E. Carrizosa, C. Molero-Río

We propose a framework for directional counterfactual explanations to interpret black-box models.
This approach identifies an optimal direction of change that maximizes robust predictive improvement.
By ranking directions through a lower-tail CVaR functional, the method focuses on reliable gains under unfavorable realizations.
We establish regularity guarantees, derive exact evaluation schemes for common model classes, and propose vMF--VNS, a derivative-free stochastic optimizer.

Keywords: Machine Learning, Optimization Models and Methods, Robust Optimization

Scheduled

GT AMyC III: Mathematical Optimization for Transparent Decision Making
September 4, 2026 3:30 PM
Aula 28

Other papers in the same session

Explainable Multi-Task Clustering: A Mathematical Optimization Approach

E. Carrizosa, J. C. Castro Gómez, V. Guerrero

Enhancing the interpretability of GPLSIMs through Counterfactual Explanations

M. Alonso-Pena, E. Carrizosa, A. Navas-Orozco

On Diverse Explanations (Prior to and After Predicting)

E. Carrizosa, R. DE LEONE, M. MAGAGNINI

On Building Optimal Risk Scores through Mathematical Optimization

C. Molero-Río, C. D'Ambrosio

Robust Directional Counterfactual Explanations for Black-Box Models

Other papers in the same session

Cookie policy