Tree Space Prototypes: Another Look at Making Tree Ensembles Interpretable
This provides an alternative interpretability method for tree ensembles, addressing the need for human-understandable models in machine learning applications.
The paper tackles the problem of making tree ensemble classifiers interpretable by introducing prototypes as representative points for each class, demonstrating that prototypes can match or exceed the original ensemble's performance as a nearest-prototype classifier and outperform Shapley values in a user study for human prediction accuracy.
Ensembles of decision trees perform well on many problems, but are not interpretable. In contrast to existing approaches in interpretability that focus on explaining relationships between features and predictions, we propose an alternative approach to interpret tree ensemble classifiers by surfacing representative points for each class -- prototypes. We introduce a new distance for Gradient Boosted Tree models, and propose new, adaptive prototype selection methods with theoretical guarantees, with the flexibility to choose a different number of prototypes in each class. We demonstrate our methods on random forests and gradient boosted trees, showing that the prototypes can perform as well as or even better than the original tree ensemble when used as a nearest-prototype classifier. In a user study, humans were better at predicting the output of a tree ensemble classifier when using prototypes than when using Shapley values, a popular feature attribution method. Hence, prototypes present a viable alternative to feature-based explanations for tree ensembles.