Author

Eddie Conti

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Nov 2025

CID: Measuring Feature Importance Through Counterfactual Distributions

This paper introduces a novel post-hoc local feature importance method called Counterfactual Importance Distribution (CID), which generates two sets of positive and negative counterfactuals, model their distributions using Kernel Density Estimation, and rank features based on a distributional dissimilarity measure.

Eddie Conti, Álvaro Parafita, Axel Brando · arXiv.org · 1 citation

#artificial intelligence Preprint Aug 2026

Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence

A novel perspective is introduced by embedding FIMs within a hypothesis-testing framework based on Weight of Evidence (WoE), which quantifies how strongly the observed evidence supports any given hypothesis on feature importance.

Eddie Conti, Claudio Daka, Álvaro Parafita et al. · 0 citations