Hyperparameters and tuning strategies for random forest. (28th January 2019)

• Record Type: Journal Article
• Authors: Probst, Philipp; Wright, Marvin N.; Boulesteix, Anne‐Laure
• Is Part Of: Wiley interdisciplinary reviews. Volume 9:Number 3(2019)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-01-28
• Subjects: ensemble -- literature review -- out‐of‐bag -- performance evaluation -- ranger -- sequential model‐based optimization -- tuning parameter; Data mining -- Periodicals; 006.31205
• DOI: 10.1002/widm.1301
• Languages: English
• ISSNs: 1942-4787

Abstract

Abstract : The random forest (RF) algorithm has several hyperparameters that have to be set by the user, for example, the number of observations drawn randomly for each tree and whether they are drawn with or without replacement, the number of variables drawn randomly for each split, the splitting rule, the minimum number of samples that a node must contain, and the number of trees. In this paper, we first provide a literature review on the parameters' influence on the prediction performance and on variable importance measures. It is well known that in most cases RF works reasonably well with the default values of the hyperparameters specified in software packages. Nevertheless, tuning the hyperparameters can improve the performance of RF. In the second part of this paper, after a presenting brief overview of tuning strategies, we demonstrate the application of one of the most established tuning strategies, model‐based optimization (MBO). To make it easier to use, we provide the tuneRanger R package that tunes RF with MBO automatically. In a benchmark study on several datasets, we compare the prediction performance and runtime of tuneRanger with other tuning implementations in R and RF with default hyperparameters. This article is categorized under: Algorithmic Development > Biological Data Mining Algorithmic Development > Statistics Algorithmic Development > Hierarchies and Trees Technologies > Machine Learning Abstract : Random forest has several hyperparameters that have to be set by the user. In this paper, we provide a literature review on the parameters' influence on the prediction performance and on variable importance measures. Moreover, we compare different tuning strategies and algorithms in R. The trees for this picture are taken from the website https://plants.swtexture.com, the water can is from Jstein and the chainsaw from Henry Mühlpfordt, both from the website https://commons.wikimedia.org .