Automatic recommendation of feature selection algorithms based on dataset characteristics
作者：
Highlights：
• A novel meta-feature engineering model recommends feature selection algorithms.
• The proposal obtains promising results from 213 datasets with hit rates of up to 90%.
• Some simple, landmarking, image, and graph-based input meta-features highlighted.
• A multi-criteria performance measure rigorously assesses candidate algorithms.
• Chains of binary or multiclass classifiers can efficiently rank candidate algorithms.
摘要
•A novel meta-feature engineering model recommends feature selection algorithms.•The proposal obtains promising results from 213 datasets with hit rates of up to 90%.•Some simple, landmarking, image, and graph-based input meta-features highlighted.•A multi-criteria performance measure rigorously assesses candidate algorithms.•Chains of binary or multiclass classifiers can efficiently rank candidate algorithms.
论文关键词：Feature engineering,Characterization measures,Algorithm selection,Recommendation system,Filter,Wrapper
论文评审过程：Received 27 July 2020, Revised 24 June 2021, Accepted 8 July 2021, Available online 13 July 2021, Version of Record 20 July 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.115589
