4 packages on CRAN
A basic, clear implementation of tree-based gradient boosting designed to illustrate the core operation of boosting models. Tuning parameters (such as stochastic subsampling, modified learning rate, or regularization) are not implemented. The only adjustable parameter is the number of training rounds. If you are looking for a high performance boosting implementation with tuning parameters, consider the 'xgboost' package.
Convenient functions for ensemble forecasts in R combining approaches from the 'forecast' package. Forecasts generated from auto.arima(), ets(), thetaf(), nnetar(), stlm(), tbats(), and snaive() can be combined with equal weights, weights based on in-sample errors (introduced by Bates & Granger (1969) <doi:10.1057/jors.1969.103>), or cross-validated weights. Cross validation for time series data with user-supplied models and forecasting functions is also supported to evaluate model accuracy.
The Patient Rule Induction Method (PRIM) is typically used for "bump hunting" data mining to identify regions with abnormally high concentrations of data with large or small values. This package extends this methodology so that it can be applied to binary classification problems and used for prediction.
Methods and tools for displaying and analysing univariate time series forecasts including exponential smoothing via state space models and automatic ARIMA modelling.