Cohort Shapley value for algorithmic fairness
This provides a tool for assessing fairness in algorithmic decisions, particularly in criminal justice, but is incremental as it builds on existing Shapley value concepts.
The authors tackled the problem of evaluating algorithmic fairness by introducing Cohort Shapley value, a model-free method for variable importance based on game theory, and applied it to the COMPAS recidivism data to identify individual-level impacts of protected attributes like race, even when race is not a predictor or the algorithm is proprietary.
Cohort Shapley value is a model-free method of variable importance grounded in game theory that does not use any unobserved and potentially impossible feature combinations. We use it to evaluate algorithmic fairness, using the well known COMPAS recidivism data as our example. This approach allows one to identify for each individual in a data set the extent to which they were adversely or beneficially affected by their value of a protected attribute such as their race. The method can do this even if race was not one of the original predictors and even if it does not have access to a proprietary algorithm that has made the predictions. The grounding in game theory lets us define aggregate variable importance for a data set consistently with its per subject definitions. We can investigate variable importance for multiple quantities of interest in the fairness literature including false positive predictions.