Work

Extremely Fast Decision Tree

Year: 2018
Type: conference-paper
Abstract: We introduce a novel incremental decision tree learning algorithm, Hoeffding Anytime Tree, that is statistically more efficient than the current state-of-the-art, Hoeffding Tree. We demonstrate that an implementation of Hoeffding Anytime Tree---"Extremely Fast Decision Tree'', a minor modification to the MOA implementation of Hoeffding Tree---obtains significantly superior prequential accuracy on most of the largest classification datasets from the UCI repository. Hoeffding Anytime Tree produces the asymptotic batch tree in the limit, is naturally resilient to concept drift, and can be used as a higher accuracy replacement for Hoeffding Tree in most scenarios, at a small additional computational cost.
Institution: Monash University
Language: English
Open Access status: green
OpenAlex ID: W2788679216
FWCI: 4.795
Cites: 26
Cited by: 248
Related to: 10