A Portfolio Management System for the Hong Kong Market
(L. W. Chan)

Application of neural networks to financial forecasting has been shown to be a promising approach. In recent years, neural networks have been successfully applied to stock price and trend prediction, exchange rate forecasting, bond rating, mortgage risk assessment etc. In this project, we apply neural networks to portfolio management of Hong Kong stocks. We use data mining techniques to find the correlations among various stocks. Based on this information, we select stocks to be included in our portfolio. This would not only give us a portfolio with proper diversification, but also enable us to have a better understanding of the correlations among the Hong Kong stocks.