Extreme learning machine based financial prediction

• Main Author: Liu, Yishan.
• Other Authors: Huang Guangbin
• Format: Final Year Project
• Language: English
• Published: 2012
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• Online Access: http://hdl.handle.net/10356/49837
• Institution: Nanyang Technological University

Stock Prediction is important for making sound investment decisions. Various machine learning approaches have been suggested for stock forecasting. However, due to the complexity and randomness of stock market, a precise prediction method remain unsolved now and highly demanded. In the Final Year Project (FYP), a new learning algorithm called Extreme Learning Machine (ELM) was utilized in the Financial Prediction System. Various technical indicators were employed to further study the trends and assist the prediction. From input selections, trading signaling, ELM filter, any stock can be selected as target; and the outputs will be next-days trend, buy or sell signal, trading profit results and recommendation.The experimental results show the training and prediction accuracy of the model are generally above 60% respectively, which concludes that leaning abilities of ELM (the acceptable prediction accuracy) and ELM based Financial Prediction System are excellent and which can meet the requirements of financial profit generation