Interpretable stock price forecasting model using genetic algorithm-machine learning regressions and best feature subset selection
作者：
Highlights：
• Capturing the collective behavior of features with good forecasting accuracy.
• Providing a timely flexible interpretation over a short data period.
• Improving forecasting performance through machine learning competition.
• Overcoming technical indicators’ subjectivity and self-fulfilling prophecy.
摘要
•Capturing the collective behavior of features with good forecasting accuracy.•Providing a timely flexible interpretation over a short data period.•Improving forecasting performance through machine learning competition.•Overcoming technical indicators’ subjectivity and self-fulfilling prophecy.
论文关键词：Interpretable stock forecasting,Collective behavior of features,Timely flexible interpretation,ML regression competition,Piecewise optimal curve fitting,Savitzky–Golay smoothing,Genetic algorithm feature selection
论文评审过程：Received 9 March 2022, Revised 28 August 2022, Accepted 6 September 2022, Available online 24 September 2022, Version of Record 30 September 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.118803
