A graph‐based convolutional neural network stock price prediction with leading indicators. (25th October 2020)

• Record Type: Journal Article
• Authors: Wu, Jimmy Ming‐Tai; Li, Zhongcui; Srivastava, Gautam; Tasi, Meng‐Hsiun; Lin, Jerry Chun‐Wei
• Other Names: Baker Thar guestEditor.; Al‐Jumeily Dhiya guestEditor.; Maamar Zakaria guestEditor.; Tari Zahir guestEditor.
• Is Part Of: Software, practice & experience. Volume 51:Number 3(2021)
• Page Start: 628
• Page End: 644
• Publication Date: 2020-10-25
• Subjects: convolutional neural network -- options and futures of stocks -- prediction -- stock history; Computer software -- Periodicals; Computer programming -- Periodicals; Computer programs -- Periodicals; 005.3
• DOI: 10.1002/spe.2915
• Languages: English
• ISSNs: 0038-0644

Abstract

Abstract: The stock market is a capitalistic haven where the issued shares are transferred, traded, and circulated. It bases stock prices on the issue market, however, the structure and trading activities of the stock market are much more complicated than the issue market itself. Therefore, making an accurate prediction becomes an intricate as well as highly difficult task. On the other hand, because of the potential benefits of stock prediction, it attracts generation after generation of scholars as well as investors to continuously develop various prediction methods from different perspectives, a myriad of theories, a multitude of investment strategies, and different practical experiences. In this article, aiming at the task of time series (financial) feature extraction and prediction of price movements, a new convolutional novel neural network that can be called a framework to improve the prediction accuracy of stock trading is proposed. The method that is proposed is called SSACNN, a short form of stock sequence array convolutional neural network. SSACNN collects data including historical data of prices and its leading indicators (options/futures) for a stock to take an array as the input graph of the convolutional neural network framework. In our experimental results, five Taiwanese and American stocks were used as a benchmark to compare with the previous algorithms and proposed algorithm, the motion prediction performance of SSACNN has been improved significantly and proved that it has the potential to be applied in the real financial market.