Stock trading and prediction using neural networks

• المؤلف الرئيسي: Liu, Mi.
• مؤلفون آخرون: Wang Lipo
• التنسيق: Final Year Project
• اللغة: English
• منشور في: 2012
• الموضوعات: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• الوصول للمادة أونلاين: http://hdl.handle.net/10356/50094
• المؤسسة: Nanyang Technological University

As the technical analysis is playing a more and more important role in today’s financial market, investors are seeking for an effective technical method to predict future stock price. Neural network is served as the main technique. This paper proposed a multiple-price model based on artificial neural network to forecast stock price. The architecture and related algorithm are introduced. The author trained the neural network with different models and selected the best prediction model among various input combinations and preprocessing techniques to construct a trading system. The trading system is proved to achieve a higher return than the buy & hold strategy, though, with high volatility.