Ensemble of ML-KNN for classification algorithm recommendation

作者：

Highlights：

• Achieve better generalization and recommendation performance by ensemble of ML-KNN.

• Take advantage of the diversity among different types of meta-features.

• Recommend varied proper number of algorithms for different classification problems.

摘要

•Achieve better generalization and recommendation performance by ensemble of ML-KNN.•Take advantage of the diversity among different types of meta-features.•Recommend varied proper number of algorithms for different classification problems.

论文关键词：Classification algorithm,Recommendation method,Ensemble learning

论文评审过程：Received 18 August 2020, Revised 2 March 2021, Accepted 4 March 2021, Available online 15 March 2021, Version of Record 23 March 2021.

论文官网地址：https://doi.org/10.1016/j.knosys.2021.106933