Ensemble methods are one of the most influential developments in Machine Learning over the past decade. They perform extremely well in a variety of problem domains, have desirable statistical properties, and scale well computationally. By combining competing models into a committee, they can strengthen “weak” learning procedures.

This tutorial explains two recent developments with ensemble methods:

Importance Sampling reveals “classic” ensemble methods (bagging, random forests, and boosting) to be special cases of a single algorithm. This unified view clarifies the properties of these methods and suggests ways to improve their accuracy and speed.

Rule Ensembles are linear rule models derived from decision tree ensembles. While maintaining (and often improving) the accuracy of the tree ensemble, the rule-based model is much more interpretable.

This tutorial is aimed at both novice and advanced data mining researchers and practitioners especially in Engineering, Statistics, and Computer Science. Users with little exposure to ensemble methods will gain a clear overview of each method. Advanced practitioners already employing ensembles will gain insight into this breakthrough way to create next-generation models.

John Elder's lecture:

In a Nutshell, Examples & Timeline

Predictive Learning

Decision Trees

Giovanni Seni's lecture:

Model Selection (Bias-Variance Tradeoff , Regularization via shrinkage)

Ensemble Learning & Importance Sampling (ISLE)

Generic Ensemble Generation

Bagging, Random Forest, AdaBoost, MART

Rule Ensembles

Interpretation