文章基本信息

标题：Using A Trainable Neural Network Ensemble for Trend Prediction of Tehran Stock Exchange
作者：Hossein Nikoo ; Mahdi Azarpeikan ; Mohammad Reza Yousefi 等
期刊名称：International Journal of Computer Science and Network Security
印刷版ISSN：1738-7906
出版年度：2007
卷号：7
期号：12
页码：287-293
出版社：International Journal of Computer Science and Network Security
摘要：This paper represents a study of neural network ensembles for stock price trend prediction. The historical data available in this case study are from Kharg petrochemical company in TSE (Tehran stock Exchange). This company is a big producer of petrochemicals, including methanol, in Iran and its stock price is very much dependent on world methanol price. The results show how neural network ensembles can overcome just a Multi-layered Perceptrons (MLPs), as a Non-parametric combinatorial forecasting method. This study also demonstrates how we can bit the market without the use of extensive market data or knowledge.
关键词：Trainable neural network ensemble; Stock price trend prediction; Tehran Stock Exchange; Iran