Current practice in interpretable machine learning often focuses on explaining the final model trained from data, e.g., by using the Shapley additive explanations (SHAP) method. The recently developed Shapley variable importance cloud (ShapleyVIC) extends the current practice to a group of "nearly optimal models" to provide comprehensive and robust variable importance assessments, with estimated uncertainty intervals for a more complete understanding of variable contributions to predictions. ShapleyVIC was initially developed for applications with traditional regression models, and the benefits of ShapleyVIC inference have been demonstrated in real-life prediction tasks using the logistic regression model. However, as a model-agnostic approach, ShapleyVIC application is not limited to such scenarios. In this work, we extend ShapleyVIC implementation for machine learning models to enable wider applications, and propose it as a useful complement to the current SHAP analysis to enable more trustworthy applications of these black-box models.

Interpretable machine learning has been focusing on explaining final models that optimize performance. The current state-of-the-art is the Shapley additive explanations (SHAP) that locally explains variable impact on individual predictions, and it is recently extended for a global assessment across the dataset. Recently, Dong and Rudin proposed to extend the investigation to models from the same class as the final model that are "good enough", and identified a previous overclaim of variable importance based on a single model. However, this method does not directly integrate with existing Shapley-based interpretations. We close this gap by proposing a Shapley variable importance cloud that pools information across good models to avoid biased assessments in SHAP analyses of final models, and communicate the findings via novel visualizations.