Dynamic Integration of Regression Models

Abstract

In this paper we adapt the recently proposed Dynamic Integration ensemble techniques for regression problems and compare their performance to the base models and to the popular ensemble technique of Stacked Regression. We show that the Dynamic Integration techniques are as effective for regression as Stacked Regression when the base models are simple. In addition, we demonstrate an extension to both Stacked Regression and Dynamic Integration to reduce the ensemble set in size and assess its effectiveness.