TRAP@NCI

Data Analysis of Stock Exchanges

O'Shea, Joanna (2014) Data Analysis of Stock Exchanges. Diploma thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Diploma)
Download (3MB) | Preview

Abstract

The data analysis of the stock exchange share prices has existed for a long time and there are numerous empirical studies on the movement of stock prices. In recent years, with the introduction of machine learning programs and classification methodologies has meant that more extensive and efficient stock market prediction may be possible. In this project, there are three stock exchanges reviewed, namely the AMEX (American Stock Exchange), NASDAQ (National Association of Securities Dealers Automated Quotations) and NYSE (New York Stock Exchange). This project aims to review the trends in the data and review whether it complies with the empirical studies about the stock market. The project looks at forecasting models using different machine learning tools such as the R program and WEKA Explorer and analyses the effectiveness of these at predicting future stock prices. During the analysis process, the data analysis is tested and evaluated to ensure that the results are accurate and up to date.

From the stock exchanges, 10 of the world’s largest IT companies are retrieved from the original dataset (see Table 2 for list of IT Companies). Only this segment was chosen for the project as it was more effective to review one type of industry. The time series relationship is analysed using the correlation coefficient and the simple linear regression model. The final stage of the project will look at predictions using the R program and WEKA Explorer. These predictions are compared against the actual stock prices which have been extracted using the R Program. WEKA Explorer was found to be the better machine learning tool for forecasting future stock price for a short time in the future.

Item Type: Thesis (Diploma)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Divisions: School of Computing > Higher Diploma in Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 15 Dec 2014 11:51
Last Modified: 15 Dec 2014 11:51
URI: http://trap.ncirl.ie/id/eprint/1866

Actions (login required)

View Item View Item