Rational Shapley Values
This work addresses the problem of providing interpretable explanations for high-stakes decisions in domains like healthcare and finance, offering a novel but incremental improvement over existing XAI methods.
The paper tackles the challenge of explaining opaque machine learning predictions by introducing rational Shapley values, a method that synthesizes feature attributions and counterfactuals to address context insensitivity and summarization difficulties, showing favorable comparisons to state-of-the-art XAI tools in experiments.
Explaining the predictions of opaque machine learning algorithms is an important and challenging task, especially as complex models are increasingly used to assist in high-stakes decisions such as those arising in healthcare and finance. Most popular tools for post-hoc explainable artificial intelligence (XAI) are either insensitive to context (e.g., feature attributions) or difficult to summarize (e.g., counterfactuals). In this paper, I introduce $\textit{rational Shapley values}$, a novel XAI method that synthesizes and extends these seemingly incompatible approaches in a rigorous, flexible manner. I leverage tools from decision theory and causal modeling to formalize and implement a pragmatic approach that resolves a number of known challenges in XAI. By pairing the distribution of random variables with the appropriate reference class for a given explanation task, I illustrate through theory and experiments how user goals and knowledge can inform and constrain the solution set in an iterative fashion. The method compares favorably to state of the art XAI tools in a range of quantitative and qualitative comparisons.