ViCE: Visual Counterfactual Explanations for Machine Learning Models
This addresses the need for interpretability in machine learning for domain experts and end-users, though it is incremental as it builds on existing counterfactual explanation methods.
The paper tackles the problem of verifying and understanding decisions made by machine learning models by introducing ViCE, an interactive visual analytics tool that generates counterfactual explanations to identify minimal changes needed to flip model outputs, demonstrated on a home equity line of credit dataset.
The continued improvements in the predictive accuracy of machine learning models have allowed for their widespread practical application. Yet, many decisions made with seemingly accurate models still require verification by domain experts. In addition, end-users of a model also want to understand the reasons behind specific decisions. Thus, the need for interpretability is increasingly paramount. In this paper we present an interactive visual analytics tool, ViCE, that generates counterfactual explanations to contextualize and evaluate model decisions. Each sample is assessed to identify the minimal set of changes needed to flip the model's output. These explanations aim to provide end-users with personalized actionable insights with which to understand, and possibly contest or improve, automated decisions. The results are effectively displayed in a visual interface where counterfactual explanations are highlighted and interactive methods are provided for users to explore the data and model. The functionality of the tool is demonstrated by its application to a home equity line of credit dataset.