Hong Kong Stock Markets Prediction Using Neural Networks: The Case of HENDERSON LAND Monthly Stock Price

Wang, Han (2016) Hong Kong Stock Markets Prediction Using Neural Networks: The Case of HENDERSON LAND Monthly Stock Price. [Dissertation (University of Nottingham only)]

[img] PDF - Registered users only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1MB)

Abstract

Owing the fact that stock markets is accessible as a significant economic activity, predicting the stock price is considerably regarded.This study aims at evaluating the effectiveness of using ANN (artificial neural network) in predicting stock price movements. Technical and fundamental indicators were combined as the network inputs, the accurate rate of POCID (Prediction of Change in Direction) and mean profit were evaluated as the main performance indicators. HENDERSON LAND, traded in Hong Kong stock exchange, was used as a case study. The methodology presented could be adapted to other stocks. Data were achieved from Bloomberg, neural network was built by MATLAB.

The experiment results was good enough to show the possibility of using ANN to predict the trends of stocks and make profit in real trading. Besides this, two additional experiments were conducted and provided some ideas on how to improve the performance of neural network in the future.

Item Type: Dissertation (University of Nottingham only)
Depositing User: Wang, Han
Date Deposited: 13 Mar 2017 10:44
Last Modified: 12 Oct 2017 14:09
URI: http://eprints.nottingham.ac.uk/id/eprint/36592

Actions (Archive Staff Only)

Edit View Edit View