On the Art and Science of Machine Learning Explanations
It addresses the problem of improving interpretability in machine learning for practitioners, but it is incremental as it synthesizes existing methods without introducing new ones.
The paper reviews several explanatory methods for machine learning models, such as decision tree surrogates, ICE plots, LIME, partial dependence plots, and Shapley explanations, and provides real-world usage recommendations and software examples for reproducibility.
This text discusses several popular explanatory methods that go beyond the error measurements and plots traditionally used to assess machine learning models. Some of the explanatory methods are accepted tools of the trade while others are rigorously derived and backed by long-standing theory. The methods, decision tree surrogate models, individual conditional expectation (ICE) plots, local interpretable model-agnostic explanations (LIME), partial dependence plots, and Shapley explanations, vary in terms of scope, fidelity, and suitable application domain. Along with descriptions of these methods, this text presents real-world usage recommendations supported by a use case and public, in-depth software examples for reproducibility.