Tools
Tools
Kang, Won Il (2022) Predicting Asian Stock Market Index Using U.S. Financial Market Indexes and Machine Learning Techniques. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (877kB) | Preview |
Preview |
PDF (Configuration manual)
Download (937kB) | Preview |
Abstract
Among many economic indicators, predictions for stock indices and stock prices are one of the most actively studied topics in economics and computer science. This is because the volatility of stock prices is affected by many variables, making it unpredictable. These variables are microscopically influenced by a company's performance and prospects. Conversely, it is macroscopically influenced by a large number of variables such as politics, diplomacy, security, exchange rates, and monetary policy. However, due to the development of computer hardware technology, computing power has been dramatically improved unlike before. Accordingly, many algorithms used for prediction are improving prediction accuracy. In particular, algorithms called machine learning provide more accurate prediction results that could not be obtained before. This is done by discovering patterns and features among countless data through advanced computing operations. In this study, Asian stock indices were predicted using machine learning algorithms and US financial market indicators. The reason why US financial market indicators were used to predict Asian stock indices is that economic cooperation between countries has been strengthened, and the economic situation of one country can easily spread to other countries. The study expected that the prediction accuracy of Asian stock indices would be improved by using the US financial market indices, which are the most influential in the world. In addition, since the operating times of the US financial market and the Asian financial market do not overlap, this time difference is expected to be easy to construct an actual prediction model in reality. The US financial indicators used in this forecast include the S&P 500, Nasdaq 100, and Dow, which are representative stock indices in the US. In addition, the VIX index, which is a volatility index, and the exchange rate with the country to be predicted were also used for this prediction. Lastly, to improve accuracy, predicted Asian stock indices were limited to the opening price. Those Asian stock indices were Korea's KOSPI, Hong Kong's Hang Seng, and Japan's Nikkei stock index.
| Item Type: | Thesis (Masters) |
|---|---|
| Subjects: | H Social Sciences > HG Finance Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science H Social Sciences > HG Finance > Investment > Stock Exchange |
| Divisions: | School of Computing > Master of Science in FinTech |
| Depositing User: | Clara Chan |
| Date Deposited: | 04 Nov 2022 18:25 |
| Last Modified: | 04 Nov 2022 18:25 |
| URI: | https://norma.ncirl.ie/id/eprint/5842 |
Actions (login required)
 |
View Item |