Intraday prediction of Borsa Istanbul using convolutional neural networks and feature correlations
作者：
Highlights：
• We have extracted different types of indicator, price and temporal features.
• Previous instances and correlation between features are used to design CNN.
• We predict the hourly direction of 100 Stocks Borsa Istanbul Stock Market.
• Proposed method outperforms the CNN that uses randomly ordered features.
• On average we perform 56.3% Macro Average F-Measure rate on 100 stocks.
摘要
•We have extracted different types of indicator, price and temporal features.•Previous instances and correlation between features are used to design CNN.•We predict the hourly direction of 100 Stocks Borsa Istanbul Stock Market.•Proposed method outperforms the CNN that uses randomly ordered features.•On average we perform 56.3% Macro Average F-Measure rate on 100 stocks.
论文关键词：Stock market prediction,Deep learning,Borsa Istanbul,Convolutional neural networks,CNN,Feature selection,Feature correlations
论文评审过程：Received 29 April 2017, Revised 13 September 2017, Accepted 16 September 2017, Available online 19 September 2017, Version of Record 18 October 2017.
论文官网地址：https://doi.org/10.1016/j.knosys.2017.09.023
