A Notion of Feature Importance by Decorrelation and Detection of Trends by Random Forest Regression

Abstract

In many studies, we want to determine the influence of certain features on a dependent variable. More specifically, we are interested in the strength of the influence – i.e., is the feature relevant? And, if so, how the feature influences the dependent variable. Recently, data-driven approaches such as random forest regression have found their way into applications (Boulesteix et al. 2012). These models allow researchers to directly derive measures of feature importance, which are a natural indicator of the strength of the influence. For the relevant features, the correlation or rank correlation between the feature and the dependent variable has typically been used to determine the nature of the influence. More recent methods, some of which can also measure interactions between features, are based on a modeling approach. In particular, when machine learning models are used, SHAP scores are a recent and prominent method to determine these trends (Lundberg et al. 2017). In this paper, we introduce a novel notion of feature importance based on the well-studied Gram-Schmidt decorrelation method. Furthermore, we propose two estimators for identifying trends in the data using random forest regression, the so-called absolute and relative traversal rate. We empirically compare the properties of our estimators with those of well-established estimators on a variety of synthetic and real-world datasets.

Keywords

• data science
• explainable artificial intelligence
• feature importance
• gram-schmidt decorrelation
• random forest regression
• shapley value
• trend estimation