期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2019
卷号：19
期号：1
页码：213-222
出版社：International Journal of Computer Science and Network Security
摘要：Predicting the stock prices is very much challenging job due to the volatility of the stock market. In this paper, we have proposed a model to predict the future prices of the stock market using Gated Recurrent Units (GRUs) neural networks. We have changed the internal structure of GRUs in order to remove local minima problem, reduce time complexity and others problem of stochastic gradient descent as well as improve the efficiency. We used mini-batch gradient descent, is a good trade-off between stochastic gradient descent and batch gradient descent. We evaluated our result by calculating the root mean square error on the various dataset. After extensive experiments on the real-time dataset, our proposed method predicted the future prices successfully with good accuracy.
关键词：Stock Market Prediction; Gated Recurrent Units (GRUS) Neural Networks; Artificial Neural Network; and Deep Learning
