An ICA design of intraday stock prediction models with automatic variable selection

Independent component analysis (ICA) provides a mechanism of decomposing non-Gaussian data signals into statistically independent components. In this paper, ICA is used to extract the underlying news factors from intraday stock data. A, prediction algorithm is developed to improve stock index predictions using such extracted "news". Both linear regression model and nonlinear artificial neural network model are proposed to predict stock indexes of Open, Close, High and Low using the ICA extracted "news". These models are compared with models using only raw intraday data as "news". It is demonstrated that ICA helps in extracting market underlying affecting "news", and thus improves the stock prediction accuracy. It shows that the proposed ICA prediction algorithm is a simple to use and versatile algorithm that automatically extracts the most relevant news for different stock index predictions.