A Simple and Effective Model-Based Variable Importance Measure

Abstract

In the era of "big data", it is becoming more of a challenge to not only build state-of-the-art predictive models, but also gain an understanding of what's really going on in the data. For example, it is often of interest to know which, if any, of the predictors in a fitted model are relatively influential on the predicted outcome. Some modern algorithms---like random forests and gradient boosted decision trees---have a natural way of quantifying the importance or relative influence of each feature. Other algorithms---like naive Bayes classifiers and support vector machines---are not capable of doing so and model-free approaches are generally used to measure each predictor's importance. In this paper, we propose a standardized, model-based approach to measuring predictor importance across the growing spectrum of supervised learning algorithms. Our proposed method is illustrated through both simulated and real data examples. The R code to reproduce all of the figures in this paper is available in the supplementary materials.

References in corpus (1)

• Predictive learning via rule ensembles

Cited by in corpus (12)

• Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challenges
• Sampling, Intervention, Prediction, Aggregation: A Generalized Framework for Model-Agnostic Interpretations
• Bayesian Non-parametric Quantile Process Regression and Estimation of Marginal Quantile Effects
• VINE: Visualizing Statistical Interactions in Black Box Models
• Deep Fundamental Factor Models
• A Quantitative Perspective on Values of Domain Knowledge for Machine Learning
• WATCH: A Workflow to Assess Treatment Effect Heterogeneity in Drug Development for Clinical Trial Sponsors
• Better Model Selection with a new Definition of Feature Importance
• Group Heterogeneity Assessment for Multilevel Models
• Uncertainty-aware Sensitivity Analysis Using Rényi Divergences
• Interpretabilité des modèles : état des lieux des méthodes et application à l'assurance
• Achieving Transparency Report Privacy in Linear Time