A data mining framework for financial prediction
作者：
Highlights：
• We proposed a novel data mining framework for the financial market.
• Interpretability, proper prediction metrics, and reporting methods were considered.
• The 3–10 year treasury spread in the Korean’s bond market was predicted.
• Predictor variables such as exchange rate were found to have significant influence.
• Our results can serve as a data-driven decision-making support tool in real world.
摘要
•We proposed a novel data mining framework for the financial market.•Interpretability, proper prediction metrics, and reporting methods were considered.•The 3–10 year treasury spread in the Korean’s bond market was predicted.•Predictor variables such as exchange rate were found to have significant influence.•Our results can serve as a data-driven decision-making support tool in real world.
论文关键词：Data mining framework,Financial prediction,Prediction metrics,Feature selection,Prediction modeling
论文评审过程：Received 21 May 2020, Revised 5 December 2020, Accepted 21 January 2021, Available online 4 February 2021, Version of Record 20 February 2021.
论文官网地址：https://doi.org/10.1016/j.eswa.2021.114651
