Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervals

Our working paper titled Unveil Sources of Uncertainty: Feature Contribution to Conformal Prediction Intervalst, co-authored with Marouane Il Idrissi, Agathe Fernandes Machado and Arthur Charpentier, is now online!

The working paper is available here: Working paper

Abstract

Cooperative game theory methods, notably Shapley values, have significantly enhanced machine learning (ML) interpretability. However, existing explainable AI (XAI) frameworks mainly attribute average model predictions, overlooking predictive uncertainty. This work addresses that gap by proposing a novel, model-agnostic uncertainty attribution (UA) method grounded in conformal prediction (CP). By defining cooperative games where CP interval properties—such as width and bounds—serve as value functions, we systematically attribute predictive uncertainty to input features. Extending beyond the traditional Shapley values, we use the richer class of Harsanyi allocations, and in particular the proportional Shapley values, which distribute attribution proportionally to feature importance. We propose a Monte Carlo approximation method with robust statistical guarantees to address computational feasibility, significantly improving runtime efficiency. Our comprehensive experiments on synthetic benchmarks and real-world datasets demonstrate the practical utility and interpretative depth of our approach. By combining cooperative game theory and conformal prediction, we offer a rigorous, flexible toolkit for understanding and communicating predictive uncertainty in high-stakes ML applications.

The codes will be available after the reviewing process.

Figure 1: LACP width-based vs. conditional mean-based importance rankings for RF and LGB models on the concrete dataset.