Evaluation of Stacking on Biomedical Data

Abstract

Objectives: Stacking is a well-known  ensemble technique, but some of its aspects still need to be explored, e.g., there are few recommendations on which and how many algorithms should be used at level-0 or even which algorithm should be used to compose the level-1 meta-classifier. The literature indicates the meta-algorithm at level-1 should be simple, and Naive Bayes has been typically used in these studies. Methods: In this work, we have analyzed stacking on biomedical datasets, using three different paradigms of machine learning algorithms to compose the meta-classifier. Results: The experiments indicate simple meta-algorithms do not provide good results. Conclusion: the meta-classifier must have a degree of complexity to provide a nice performance.