Forecasting the overnight return direction of stock market index combining global market indices: A multiple-branch deep learning approach
作者：
Highlights：
• We focus on the daily close-to-open return (RC−O) of stock market index (SMI).
• We propose a novel MBCNN to forecast the direction of daily RC−O.
• Multiple convolutional units are used to extract features from intraregional SMIs.
• GA is used to determine the optimal structure and hyper-parameters of MBCNN.
• Performance of the proposed MBCNN is better than other competing models.
摘要
•We focus on the daily close-to-open return (RC−O) of stock market index (SMI).•We propose a novel MBCNN to forecast the direction of daily RC−O.•Multiple convolutional units are used to extract features from intraregional SMIs.•GA is used to determine the optimal structure and hyper-parameters of MBCNN.•Performance of the proposed MBCNN is better than other competing models.
论文关键词：Stock market index,Overnight return,Deep learning,Genetic algorithm
论文评审过程：Received 27 July 2021, Revised 30 November 2021, Accepted 1 January 2022, Available online 19 January 2022, Version of Record 21 January 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116506
