New Zealand Stock Market prediction using sentiment analysis

Loading...
Thumbnail Image
Supplementary material
Other Title
Authors
Bangar, Varinder Jot
Author ORCID Profiles (clickable)
Degree
Master of Computing
Grantor
Unitec Institute of Technology
Date
2022
Supervisors
Sharifzadeh, Hamid
Varastehpour, Soheil
Type
Masters Thesis
Ngā Upoko Tukutuku (Māori subject headings)
Keyword
New Zealand Stock Exchange (NZX)
stock markets
stock movement prediction
deep-learning algorithms
computer modelling
algorithms
New Zealand
sentiment analysis (SA)
Citation
Bangar, V. J. (2022). New Zealand Stock Market prediction using sentiment analysis. (Unpublished document submitted in partial fulfilment of the requirements for the degree of Master of Computing). Unitec Institute of Technology, New Zealand. https://hdl.handle.net/10652/5917
Abstract
In this research, I addressed this gap and tried to focus on the New Zealand Stock Exchange (NZX). For the proposed model, I used the financial news only, for the SA and for the stock data I took five of the biggest New Zealand organisations. The reason for choosing these organisations was that the textual data contains more mentions about these companies than others and hence, the sentiment scores can reflect the changes that take place. This research was conducted to provide a picture of how accurately NZX trends can be predicted using DL algorithms with and without taking into considerations the SA. Also, the purpose of this research was to draw a picture of how different NZX is from the rest of the bigger stock markets and if the same tools and techniques apply for the prediction of trends. The findings of this research adds to the knowledge that the similar tools and techniques that are used for bigger stock markets, can also be applied to predict the trends of NZX. It further adds that the length and quality of the textual data available for the sentiment analysis also plays an important role in the accuracy of the prediction model. This research also examines the impact of Covid-19 on the accuracy of the prediction model by including and excluding the timelines of data related to this global pandemic.
Publisher
Link to ePress publication
DOI
Copyright holder
Author
Copyright notice
All rights reserved
Copyright license
Available online at