Disentangled Attribution Curves for Interpreting Random Forests and Boosted Trees

Abstract

Tree ensembles, such as random forests and AdaBoost, are ubiquitous machine learning models known for achieving strong predictive performance across a wide variety of domains. However, this strong performance comes at the cost of interpretability (i.e. users are unable to understand the relationships a trained random forest has learned and why it is making its predictions). In particular, it is challenging to understand how the contribution of a particular feature, or group of features, varies as their value changes. To address this, we introduce Disentangled Attribution Curves (DAC), a method to provide interpretations of tree ensemble methods in the form of (multivariate) feature importance curves. For a given variable, or group of variables, DAC plots the importance of a variable(s) as their value changes. We validate DAC on real data by showing that the curves can be used to increase the accuracy of logistic regression while maintaining interpretability, by including DAC as an additional feature. In simulation studies, DAC is shown to out-perform competing methods in the recovery of conditional expectations. Finally, through a case-study on the bike-sharing dataset, we demonstrate the use of DAC to uncover novel insights into a dataset.

Under review

References in corpus (12)

• A Survey on Deep Learning in Medical Image Analysis
• Towards A Rigorous Science of Interpretable Machine Learning
• Interpretable machine learning: definitions, methods, and applications
• European Union regulations on algorithmic decision-making and a "right to explanation"
• Predictive learning via rule ensembles
• Consistent Individualized Feature Attribution for Tree Ensembles
• Iterative Random Forests to detect predictive and stable high-order interactions
• Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs
• Hierarchical interpretations for neural network predictions
• Quantifying Model Complexity via Functional Decomposition for Better Post-Hoc Interpretability
• Detecting Statistical Interactions from Neural Network Weights
• Signed iterative random forests to identify enhancer-associated transcription factor binding

Cited by in corpus (5)

• Interpretable machine learning: definitions, methods, and applications
• The impact of feature importance methods on the interpretation of defect classifiers
• Interpretable Anomaly Detection with DIFFI: Depth-based Isolation Forest Feature Importance
• Transformation Importance with Applications to Cosmology
• Purifying Interaction Effects with the Functional ANOVA: An Efficient Algorithm for Recovering Identifiable Additive Models