|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
Abstract
The stock market offers traders a place to invest and trade in shares since it is a dynamic and volatile marketplace. There are various factors that affect a stock's price. Features that are static and dynamic. For traders, being able to forecast the future value of a specific company's stock can be quite advantageous. An input sequence can be mapped to an output sequence using seq2seq modelling. In this research, we propose a method that uses Bi-Directional LSTM based on sequential Modelling to forecast the future Open, High, Close, Low, Volume (OHCLV) value of a stock.Each OHCLV pricing is a separate sequence, and multitask learning aids in illustrating their connections. It is also suggested to use shared workloads and subtasks in a multitasking system to model prices. Stock prices of APPLE from the Yahoo Finance is used. To evaluate the efficiency of the proposed systems, they are compared against various machine learning algorithms. The proposed Sequential multitasking systems comfortably outperform the existing algorithms
Keyword
Stock market,Stock prediction, LSTM, BiLSTM, Sequential modeling, Multitasking.
PDF Download (click here)
|
|
|
|
|