Interacting with Predictions: Visual Inspection of Black-box Machine Learning Models
Josua Krause, Adam Perer, Kenney Ng
Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems — ACM CHI 2016
Understanding predictive models, in terms of interpreting and identifying actionable
insights, is a challenging task. Often the importance of a feature in a model is only a rough estimate
condensed into one number. However, our research goes beyond these naïve estimates through the design
and implementation of an interactive visual analytics system, Prospector. By providing interactive
partial dependence diagnostics, data scientists can understand how features affect the prediction overall.
In addition, our support for localized inspection allows data scientists to understand how and why
specific datapoints are predicted as they are, as well as support for tweaking feature values and seeing
how the prediction responds. Our system is then evaluated using a case study involving a team of data
scientists improving predictive models for detecting the onset of diabetes from electronic medical records.