Hybrid Deep Learning Based Stock Market Prediction with both Sentiment and Historic Trend Data
Guruprasad S1, Sahilverma2, H Chandramouli3
1Mr. Guruprasad S*, Assistant Professor, Department of Computer Science and Engineering. BMS Institute of Technology &management, Bangalore, India.
2Mr. Sahil Verma, Software Development Engineer Trainee, Tally Solutions PVT Ltd. Bangalore, India.
3Dr. Chandramouli H, Professor, Department of Computer Science and Engineering. East Point College of Engineering and Technology, Bangalore, India.
Manuscript received on January 12, 2020. | Revised Manuscript received on January 26, 2020. | Manuscript published on February 10, 2020. | PP: 1166-1171 | Volume-9 Issue-4, February 2020. | Retrieval Number: D1505029420/2020©BEIESP | DOI: 10.35940/ijitee.D1505.029420
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Stock market is highly volatile and it is necessary for investors to have an accurate prediction of stock prices for a better profitability. Towards this need many methods have been proposed for stock market prediction with aim to provide a higher prediction accuracy. Current methods for stock market prediction are in two categories of machine learning and statistics based. Considering the need for accurate prediction in short term and long term, the merits of both methods must be combined for accurate prediction. This work proposes a hybrid deep learning approach for stock market prediction which combines the historic price-based trend forecasting along with stock market sentiments expressed in twitter to predict the stock price trend.
Keywords: Machine Learning, Statistics Based.
Scope of the Article: Machine Learning