Functional relevance based on the continuous Shapley value

P. Delicado, C. Pachón García

The presence of Artificial Intelligence (AI) in our society is increasing, which brings with it the need to understand the behaviour of AI mechanisms, including machine learning predictive algorithms fed with tabular data, text, or images, among other types of data. This work focuses on interpretability of predictive models based on functional data. Designing interpretability methods for functional data models implies working with a set of features whose size is infinite. In the context of scalar on function regression, we propose an interpretability method based on the Shapley value for continuous games, a mathematical formulation that allows to fairly distribute a global payoff among a continuous set of players. The method is illustrated through a set of experiments with simulated and real data sets. The open source Python package ShapleyFDA is also presented.

Keywords: Interpretability, explainability, functional data analysis, Shapley value, continuous game theory, machine learning, artificial intelligence

FENStatS-SEIO: Statistics and Data Science
June 11, 2025  10:30 AM
Auditorio 1. Ricard Vinyes

P. Lacroix, B. Michel, F. Picard, V. Rivoirard

R. Verde, A. Balzanella, G. Borrata

I. Pereira, M. Monteiro

I. Willems, J. Beyhum, I. Van Keilegom