Creating and Exploiting Coverage and Diversity

In this paper, we illustrate that increasing coverage through diversity is not enough to ensure increased prediction accuracy|if the integration method does not utilize the coverage, then no beneet arises from integrating multiple models. We compare four criteria for selecting base-level classiiers and demonstrate that informed selection can lead to more accurate meta-level classi-ers than random selection. In addition, we illustrate empirically that straightforward integration methods fail to utilize the diversity of the base-level classiiers.