Abstract
•We propose a novel method for obtaining interpretable multi-class models.•We use confidence thresholds at each node of the Nested Dichotomies structure.•Thresholds are fit using differential evolution.•Interpretability is improved in the inference phase whereas performance is maximized.•The new method is more interpretable and presents a competitive performance versus the state-of-the-art methods.
The success of Artificial Intelligence at solving real-world problems poses the need for interpretable models, especially in human-centered applications. The multi-class scenario is often present in these environments; however, the majority of research on interpretability has focused on binary classification. In this work, a novel method based on hierarchical decompositions to obtain interpretable multi-class models is introduced. The proposal, named Threshold Control for Nested Dichotomies (TC-ND) method, creates a binary-based hierarchical class structure. Then, it discards meta-classes at each dichotomy of the structure according to a certain level of confidence, pursuing a modular and more comprehensible decomposition of the multi-class problem. The approach presents internal parameters that are optimized using the Differential Evolution algorithm. The goodness of our proposal is assessed using a twofold approach: performance is evaluated by comparing against other state-of-the-art multi-class methods; interpretability is supported by practical examples with counterfactual explanations and a discussion of the advantages that the TC-ND method presents regarding its transparency and auditability.