Slides from talks are beside some of the articles. More talks are here.
Google scholar and arxiv update faster than this page.
The most popular methods for measuring importance of the variables in a black-box prediction algorithm make use of synthetic inputs that combine predictor variables from multiple observations. These inputs can be unlikely, physically impossible, or even logically impossible. As a result, the predictions for such cases can be based on data very unlike any the black box was trained on. We think that users cannot trust an explanation of the decision of a prediction algorithm when the explanation uses such values. Instead, we advocate a method called cohort Shapley, which is grounded in economic game theory and uses only actually observed data to quantify variable importance. Cohort Shapley works by narrowing the cohort of observations judged to be similar to a target observation on one or more features. We illustrate it on an algorithmic fairness problem where it is essential to attribute importance to protected variables that the model was not trained on.
Cohort Shapley can evaluate variable importance based on given data without access to a possibly proprietary function. It can also evaluate importance on residuals where by definition there is no computable function outside the data.
The three papers below grew out of MCQMC 2012 and the 2012 MASCOT NUM meeting.