Evaluating multiple classifiers for stock price direction prediction
作者：
Highlights：
• We predict long term stock price direction.
• We benchmark three ensemble methods against four single classifiers.
• We use five times twofold cross-validation and AUC as a performance measure.
• Random Forest is the top algorithm.
• This study is the first to make such an extensive benchmark in this domain.
摘要
•We predict long term stock price direction.•We benchmark three ensemble methods against four single classifiers.•We use five times twofold cross-validation and AUC as a performance measure.•Random Forest is the top algorithm.•This study is the first to make such an extensive benchmark in this domain.
论文关键词：Ensemble methods,Single classifiers,Benchmark,Stock price direction prediction
论文评审过程：Available online 13 May 2015, Version of Record 2 June 2015.
论文官网地址：https://doi.org/10.1016/j.eswa.2015.05.013
