Foster Provost

Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approach

arXiv (Cornell University) · 2020 · 54 citations

We examine counterfactual explanations for explaining the decisions made by model-based AI systems. The counterfactual approach we consider defines an explanation as a set of the system's data inputs that causally drives the decision (i.e., changing the inputs in the set changes the decision) and is irreducible (i.e., changing any subset of the inputs does not change the decision). We (1) demonstrate how this framework may be used to provide explanations for decisions made by general, data-drive…

Causal Decision Making and Causal Effect Estimation Are Not the Same…and Why It Matters

INFORMS Journal on Data Science · 2022 · 49 citations

Causal decision making (CDM) at scale has become a routine part of business, and increasingly, CDM is based on statistical models and machine learning algorithms. Businesses algorithmically target offers, incentives, and recommendations to affect consumer behavior. Recently, we have seen an acceleration of research related to CDM and causal effect estimation (CEE) using machine-learned models. This article highlights an important perspective: CDM is not the same as CEE, and counterintuitively, a…

Explaining Data-Driven Decisions made by AI Systems: The Counterfactual Approach

MIS Quarterly · 2022-09-01 · 42 citations

We examine counterfactual explanations for explaining the decisions made by model-based AI systems. The counterfactual approach we consider defines an explanation as a set of the system’s data inputs that causally drives the decision (i.e., changing the inputs in the set changes the decision) and is irreducible (i.e., changing any subset of the inputs does not change the decision). We (1) demonstrate how this framework may be used to provide explanations for decisions made by general data-driven…

A Comparison of Methods for Treatment Assignment with an Application to Playlist Generation

Information Systems Research · 2022-08-02 · 11 citations

This study presents a systematic comparison of methods for individual treatment assignment. We group the various methods proposed in the literature into three general classes of algorithms (or metalearners): learning models to predict outcomes (the O-learner), learning models to predict causal effects (the E-learner), and learning models to predict optimal treatment assignments (the A-learner). We discuss how the metalearners differ in their level of generality and their objective function, whic…

Node classification over bipartite graphs through projection

Machine Learning · 2020-07-28 · 5 citations