J. Ramírez-Ayerbe, D. Romero Morales, E. Carrizosa
Due to the increasing use of complex machine learning models in high stakes decisions, post-hoc explanations have become crucial to be able to understand their behaviour. An effective class of post-hoc explanations are counterfactual explanations, i.e., minimal perturbations of the predictor variables to change the prediction for a specific instance. Most of the research on counterfactual explainability focuses on tabular and image data, and much less on models dealing with functional data. In this paper we propose a novel Mathematical Optimization formulation for constructing counterfactual explanations when dealing with functional data. Our approach can generate sparse and plausible counterfactuals and identify the samples of the dataset from which the counterfactual explanation is made of. We illustrate our methodology using two different real-world datasets, one univariate and another multivariate.
Keywords: Counterfactual Explanations, Mathematical Optimization, Random Forests, Functional Data
Scheduled
GT04 Multivariate Analysis and Classification IV. Latest Advances in Explainable Machine Learning
June 7, 2022 6:40 PM
Cloister room
