Interpreting Complex Regression Models
This addresses the need for interpretability in machine learning for feature engineering and compliance, though it appears incremental as it builds on existing interpretation methods.
The paper tackles the problem of interpreting complex machine learning models by introducing a method that provides simple interpretations grounded in actual learning examples, validated on tasks like predicting song recording years and mail user churn.
Interpretation of a machine learning induced models is critical for feature engineering, debugging, and, arguably, compliance. Yet, best of breed machine learning models tend to be very complex. This paper presents a method for model interpretation which has the main benefit that the simple interpretations it provides are always grounded in actual sets of learning examples. The method is validated on the task of interpreting a complex regression model in the context of both an academic problem -- predicting the year in which a song was recorded and an industrial one -- predicting mail user churn.