Ensemble of ML-KNN for classification algorithm recommendation

With the mountains of classification algorithms proposed in the literature, the study of how to select suitable classifier(s) for a given problem is important and practical. Existing methods rely on a single learner built on one type of meta-features or a simple combination of several types of meta-features to address this problem. In this paper, we propose a two-layer classification algorithm recommendation method called EML (Ensemble of ML-KNN for classification algorithm recommendation) to leverage the diversity of different sets of meta-features. The proposed method can automatically recommend different numbers of appropriate algorithms for different dataset, rather than specifying a fixed number of appropriate algorithm(s) as done by the ML-KNN, SLP-based and OBOE methods. Experimental results on 183 public datasets show the effectiveness of the EML method compared to the three baseline methods.