Problem Statement: "Given the historical data of a number of stock or index prices at different points in time, design an algorithm that would predict their values in the future. Some factors the algorithm can take into consideration include the day in month, weekday of day, time of day and various other financial indicators and correlations between data from different time series. Time series data of at least 15 stocks, futures or indices are expected to be analyzed."

After developing such an algorithm along these lines, the aim is to incorporate this into a fully functional, user-friendly, tested software that allows end users to input historical data (via Excel) with other parameters which can help simulate market volatility and display appropriate information on expected value for chosen date with a smartly designed user interface.

Technical concepts explored include Data Mining and Artificial Neural Networks. The high-level idea is that if a sufficient amount of data is harvested, then mined, from some data source, then this can be used to "train" a Neural Network which can go on to forecast future prices. For more information, please refer to project documentation as they are updated on the website.

I would like to thank Professor Yip Chi Lap for superivising my work, and mentoring me over the past year. Also thanks to the Department of Computer Science, HKU, for giving me this opportunity.