Model Interpretation: A Unified Derivative-based Framework for Nonparametric Regression and Supervised Machine Learning
This work addresses the problem of model interpretability for users of machine learning algorithms, but it is incremental as it builds upon existing tools.
The paper tackles the challenge of interpreting nonparametric regression models with many predictors by developing a unified derivative-based framework for existing tools and proposing a new technique called accumulated total derivative effects plot, demonstrating its use for insights in complex models with correlated predictors through simulation results.
Interpreting a nonparametric regression model with many predictors is known to be a challenging problem. There has been renewed interest in this topic due to the extensive use of machine learning algorithms and the difficulty in understanding and explaining their input-output relationships. This paper develops a unified framework using a derivative-based approach for existing tools in the literature, including the partial-dependence plots, marginal plots and accumulated effects plots. It proposes a new interpretation technique called the accumulated total derivative effects plot and demonstrates how its components can be used to develop extensive insights in complex regression models with correlated predictors. The techniques are illustrated through simulation results.