A5058547618- Stock Market Forecasting Methods
- Neural Networks and Applications
- Energy Load and Power Forecasting
- Financial Markets and Investment Strategies
- Time Series Analysis and Forecasting
- Advanced Text Analysis Techniques
- Complex Systems and Time Series Analysis
University of Technology Sydney
2021-2023
Nanyang Technological University
2013-2014
Forecasting stock price with traditional time series methods has proven to be difficult. An artificial neural network is probably more suitable for this task, since no assumption of a mathematical model made prior the forecasting process. Furthermore, ability extract main influential factors from large sets data, which often required successful prediction task. In paper, we explore one-step ahead and multi-step predictions compare previous work.
This paper improves stock market prediction based on genetic algorithms (GA) and wavelet neural networks (WNN) reports significantly better accuracies compared to existing approaches prediction, including the hierarchical GA (HGA) WNN. Specifically, we added information such as trading volume inputs used Morlet function instead of Morlet-Gaussian in our model. We also employed a smaller number hidden nodes WNN other research work. The system is tested using Shenzhen Composite Index data.
This paper explores the application of a wavelet neural network (WNN), whose hidden layer is comprised neurons with adjustable wavelets as activation functions, to stock prediction. We discuss some basic rationales behind technical analysis, and based on which, inputs prediction system are carefully selected. tested Istanbul Stock Exchange National 100 Index compared traditional networks. The results show that WNN can achieve very good accuracy.