Forecasting near-future Hang Sang [i.e. Seng] Index with data mining techniques

Pao Yue-kong Library Electronic Theses Database

Forecasting near-future Hang Sang [i.e. Seng] Index with data mining techniques

 

Author: Lui, Hing-nin.
Title: Forecasting near-future Hang Sang [i.e. Seng] Index with data mining techniques
Degree: M.Sc.
Year: 2002
Subject: Hong Kong Polytechnic University -- Dissertations
Stock price indexes -- China -- Hong Kong -- Forecasting
Stock index futures -- China -- Hong Kong -- Forecasting
Data mining
Department: Dept. of Computing
Pages: i, 91, [20] leaves : col. ill. ; 30 cm.
InnoPac Record: http://library.polyu.edu.hk/record=b1752353
URI: http://theses.lib.polyu.edu.hk/handle/200/5397
Abstract: This paper is to investigate ways to use data mining methods and neural networks to predict the movement of an index for the near future. Here, the near future is defined as the future in the fifteen minutes. Daily movement of stock prices and indexes are predicted as a complicated real-world problem, factors such as the nominal value movements of related stocks and indexes are taking into account. A comparison on the results derived from data mining and neural networks are plotted among all the selected stocks and indexes. The data set for this research is collected through a sponsored company with a direct data-feed line from the Hong Kong Stock Exchange. Detailed data collection is down to a minute. The use of data mining and neural networks is shown to be effective experimentally: the prediction accuracies for both approaches are as good as 97% and 99% respectively for most of the indexes and selected stocks and there is 99% accuracy by using Neural Networks for the prediction of HSI for the next 15 minutes. Finally, the system is proved to be accurate for the time interval up to 45 minutes which may imply the present movement of index having an influence for 45 minutes long.

Files in this item

Files Size Format
b17523539.pdf 9.235Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

     

Quick Search

Browse

More Information