Wavelet neural network for stock trading and prediction

• Main Author: Huang, Le
• Other Authors: Wang Lipo
• Format: Final Year Project
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• Online Access: http://hdl.handle.net/10356/61432
• Institution: Nanyang Technological University

Wavelet neural networks (WNN) have been applied successfully into many fields. The main purpose of this report is to study the application of WNNs in the field of stock price prediction. Some background knowledge, including wavelets analysis, Artificial Neural Network (ANN) and some related work done by previous researchers in the field of WNN is reviewed. And the whole process of designing a WNN is presented. The constructed WNN is tested for prediction of S&P 500 Index and stock price of Apple Inc. It is concluded that WNN has a strong predicting power in terms of accuracy. Some suggestions are given at last for further improvement of the implementation.