Beyond Single-Feature Importance with ICECREAM

Michael Oesterle, Patrick Blöbaum, Atalanti A. Mastakouri, Elke Kirschbaum

Keywords: root cause analysis, causal contribution analysis, explainability, feature selection

TL;DR: We present ICECREAM, a new approach that can be used for root cause analysis and explainability by considering variables not only individually, but particularly when interacting in coalitions of variables.

Abstract: Which set of features was responsible for a certain output of a machine learning model? Which components caused the failure of a cloud computing application? These are just two examples of questions we are addressing in this work by Identifying Coalition-based Explanations for Common and Rare Events in Any Model (ICECREAM). Specifically, we propose an information-theoretic quantitative measure for the influence of a coalition of variables on the distribution of a target variable. This allows us to identify which set of factors is essential to obtain a certain outcome, as opposed to well-established explainability and causal contribution analysis methods that rank individual factors. In experiments with synthetic and real-world data, we show that ICECREAM outperforms state-of-the-art methods for explainability and root cause analysis, and achieves impressive accuracy in both tasks.

Submission Number: 23