Visualizing the Feature Importance for Black Box Models
This work addresses the need for transparency in machine learning for practitioners, but it is incremental as it builds on existing model-agnostic and visualization techniques.
The paper tackles the problem of interpreting black box models by introducing local feature importance and visual tools (PI and ICI plots) to show how feature changes affect model performance, with methods extending global importance and linking to Shapley values for fair comparison across models.
In recent years, a large amount of model-agnostic methods to improve the transparency, trustability and interpretability of machine learning models have been developed. We introduce local feature importance as a local version of a recent model-agnostic global feature importance method. Based on local feature importance, we propose two visual tools: partial importance (PI) and individual conditional importance (ICI) plots which visualize how changes in a feature affect the model performance on average, as well as for individual observations. Our proposed methods are related to partial dependence (PD) and individual conditional expectation (ICE) plots, but visualize the expected (conditional) feature importance instead of the expected (conditional) prediction. Furthermore, we show that averaging ICI curves across observations yields a PI curve, and integrating the PI curve with respect to the distribution of the considered feature results in the global feature importance. Another contribution of our paper is the Shapley feature importance, which fairly distributes the overall performance of a model among the features according to the marginal contributions and which can be used to compare the feature importance across different models.