Generalized Boosted Regression Models

An implementation of extensions to Freund and Schapire's AdaBoost algorithm and Friedman's gradient boosting machine. Includes regression methods for least squares, absolute loss, t-distribution loss, quantile regression, logistic, multinomial logistic, Poisson, Cox proportional hazards partial likelihood, AdaBoost exponential loss, Huberized hinge loss, and Learning to Rank measures (LambdaMart). Originally developed by Greg Ridgeway. Newer version available at < https://github.com/gbm-developers/gbm3>.

gbm

Overview

The gbm package, which stands for generalized boosted models, provides extensions to Freund and Schapire’s AdaBoost algorithm and Friedman’s gradient boosting machine. It includes regression methods for least squares, absolute loss, t-distribution loss, quantile regression, logistic, multinomial logistic, Poisson, Cox proportional hazards partial likelihood, AdaBoost exponential loss, Huberized hinge loss, and Learning to Rank measures (i.e., LambdaMart).

Documentation and vignettes are available at https://gbm-developers.github.io/gbm/.

Installation

# The easiest way to get gbm is to it install from CRAN:
install.packages("gbm")

# Alternatively, you can install the development version from GitHub:
if (!requireNamespace("remotes")) {
  install.packages("remotes")
}
remotes::install_github("gbm-developers/gbm")

Lifecycle

The gbm package is no longer under active development. We will only make the necessary changes to ensure that gbm remains on CRAN. For the most part, no new features will be added, and only the most critical of bugs will be fixed.

This is a maintained version of gbm back compatible to CRAN versions of gbm 2.1.x. It exists mainly for the purpose of reproducible research and data analyses performed with the 2.1.x versions of gbm. For newer development, and a more consistent API, try out the gbm3 package!