Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach

Satoshi Hara, Kohei Hayashi
Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, PMLR 84:77-85, 2018.

Abstract

Tree ensembles, such as random forests, are renowned for their high prediction performance. However, their interpretability is critically limited due to the enormous complexity. In this study, we propose a method to make a complex tree ensemble interpretable by simplifying the model. Specifically, we formalize the simplification of tree ensembles as a model selection problem. Given a complex tree ensemble, we aim at obtaining the simplest representation that is essentially equivalent to the original one. To this end, we derive a Bayesian model selection algorithm that optimizes the simplified model while maintaining the prediction performance. Our numerical experiments on several datasets showed that complicated tree ensembles were approximated interpretably.

Cite this Paper


BibTeX
@InProceedings{pmlr-v84-hara18a, title = {Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach}, author = {Satoshi Hara and Kohei Hayashi}, booktitle = {Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics}, pages = {77--85}, year = {2018}, editor = {Amos Storkey and Fernando Perez-Cruz}, volume = {84}, series = {Proceedings of Machine Learning Research}, month = {09--11 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v84/hara18a/hara18a.pdf}, url = { http://proceedings.mlr.press/v84/hara18a.html }, abstract = {Tree ensembles, such as random forests, are renowned for their high prediction performance. However, their interpretability is critically limited due to the enormous complexity. In this study, we propose a method to make a complex tree ensemble interpretable by simplifying the model. Specifically, we formalize the simplification of tree ensembles as a model selection problem. Given a complex tree ensemble, we aim at obtaining the simplest representation that is essentially equivalent to the original one. To this end, we derive a Bayesian model selection algorithm that optimizes the simplified model while maintaining the prediction performance. Our numerical experiments on several datasets showed that complicated tree ensembles were approximated interpretably.} }
Endnote
%0 Conference Paper %T Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach %A Satoshi Hara %A Kohei Hayashi %B Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2018 %E Amos Storkey %E Fernando Perez-Cruz %F pmlr-v84-hara18a %I PMLR %P 77--85 %U http://proceedings.mlr.press/v84/hara18a.html %V 84 %X Tree ensembles, such as random forests, are renowned for their high prediction performance. However, their interpretability is critically limited due to the enormous complexity. In this study, we propose a method to make a complex tree ensemble interpretable by simplifying the model. Specifically, we formalize the simplification of tree ensembles as a model selection problem. Given a complex tree ensemble, we aim at obtaining the simplest representation that is essentially equivalent to the original one. To this end, we derive a Bayesian model selection algorithm that optimizes the simplified model while maintaining the prediction performance. Our numerical experiments on several datasets showed that complicated tree ensembles were approximated interpretably.
APA
Hara, S. & Hayashi, K.. (2018). Making Tree Ensembles Interpretable: A Bayesian Model Selection Approach. Proceedings of the Twenty-First International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 84:77-85 Available from http://proceedings.mlr.press/v84/hara18a.html .

Related Material