College of Business and Law - Masters by Research Theses

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 5 of 29
  • Item
    Machine Learning and its application in the Portfolio Management industry
    (University College Cork, 2024) Murphy, Conor C; McAvoy, John; Kiely, Gaye Louise
    Machine Learning (ML) is a subdivision of Artificial Intelligence (AI). AI is a term used for technology that “enables machines to mimic human thoughts and behaviour” (Xu, 2021). Recently, there has been a significant increase in the use of ML techniques by finance professionals, primarily by the Portfolio Management industry (Perrin, 2019). This thesis reflects on ML’s application in the Portfolio Management industry. To further understand this relationship a literature review is carried out in Chapter 2 to identify the intersection of ML and Portfolio Management and to highlight key criteria required for ML’s application in the Portfolio Management industry. A key finding from Chapter 2 found that the lack of quality data is a critical barrier to ML’s application in the Portfolio Management industry. Chapter 2 examines the use of sentiment from unstructured data, in the main tweets, for stock market prediction in the Portfolio Management industry as alternative data source for ML. There are a variety of ML algorithms that can be applied for Twitter sentiment stock market prediction, Chapter 3 employs the Multilayer-Perceptron (MLP). MLP has been employed successfully in other studies for Twitter sentiment stock market prediction (Livingston, 2019; Turchenko, 2011). Before running the MLP prediction algorithm, EmoLex was employed to identify the underlying sentiment that may be apparent in the tweets. Subsequently, a prediction algorithm MLP Classifier was run to ascertain daily sentiment stock price predictions for the data. For the prediction analysis section the Vader Sentiment Analyser from the Natural Language Tool Kit (NLTK) in python was employed to split the Twitter sentiment into three categories (positive/neutral/negative), while the MLP classifier was run through SickIt-learn package in python. Interestingly, the performance of the MLP in Chapter 3 is not as accurate as other studies including, Kolasani (2020), Usmani (2016) & Khan (2020). Following the same guidelines as Pagolu (2016) and Mittal (2012) incorporating a new algorithm (the Random Forest algorithm) using the same methodology outlined in Chapter 3 may outperform the MLP. Studies such as Bollen (2011) indicate that positive Twitter sentiment will be reflected in the stock market by a positive increase in stock price and negative Twitter sentiment will result in a fall in stock price. The use of the Random Forest regressor in this study found that in the case of Black Swan events, Twitter sentiment has the same predictive power as a chance model. These results are integral to the Portfolio Management industry as it clearly indicates that Twitter sentiment cannot be used to gauge the severity of Black Swan events nor can it be used as a method to predict it. Only one of the Tweets in the database collected referenced that China allowed one of its banks to go into liquidation, indicating that the speed of stock price drop was ahead of the Twitter sentiment.
  • Item
    Soccer and CO2: air travel at international football tournaments from 1990 to 2024
    (University College Cork, 2024) McCarthy, Conor J.; Butler, Robert; Butler, David
    This research explores the impact of football air travel on the environment for all men’s World Cup and UEFA European Football Championships hosted between 1990-2024. These tournaments required qualifying teams to travel to a host country and attract tens of thousands of supporters to stadiums throughout the host country. The supporter of teams and players travel across the host nation during their stay in the competition. Depending on the success of the team this can range from about 10 days up to 5 weeks.
  • Item
    A study on the correlation between future economic conditions and stock returns under China's A-share market
    (University College Cork, 2023) Wang, Zitong; Gao, Jun; Sherman, Meadhbh
    Our study aims to investigate the explanatory power of future economic conditions on the returns of individual stocks in the Chinese A-share market. We use an integrated research methodology to study this topic scientifically and systematically. All A-share stocks in the Shanghai Stock Exchange and Shenzhen Stock Exchange are selected as the primary research objects, and data representing China's real economic activity are widely collected. With these data, we analyze a new trading strategy based on a reasonable prediction of future real activities using the capital asset pricing model and the Fama-French three-factor model. In addition, we have specifically examined the performance of this trading strategy on two different types of stocks (pro-cyclical and counter-cyclical stocks). Particularly noteworthy is that, unlike previous studies, we innovatively adopt the producer price index (PPI) as a measure of China's real economic activity based on the largest possible selection of sample intervals. This innovative approach provides a new perspective for us to deeply understand the operating mechanism of China's A-share market and the impact of economic conditions on the performance of individual stocks. The study results show no significant relationship between future economic conditions and individual stock returns in China's A-share market. Besides, those investors who want to get excess returns can short the pro-cyclical stocks and/or long the counter-cyclical stocks if production growth in the following month is anticipated to be above the steady state and vice versa. Our new trading strategy demonstrates potential advantages and gives investors a unique decision-making perspective. This finding not only provides investors with a more reliable basis for decision-making but also helps us to gain a deeper understanding of the operating rules of the Chinese stock market. This new perspective sheds light on the potential impact mechanism of economic activities on the Chinese stock market, which sheds important light on the optimization of investment strategies and risk management. Meanwhile, our trading strategy research provides an innovative way for investors to seek better returns among different classes of stocks. However, some things could be improved in this study. Future research can be further deepened and expanded to understand the relationship between China's A-share market and economic conditions more comprehensively and continuously optimize trading strategies' practicality and robustness. Overall, the findings of this thesis fill a research gap in the academic field and provide new perspectives and methods for investment decision-making and risk management. These findings will provide valuable references for relevant scholars and practitioners and contribute to a deeper understanding of China's macroeconomic conditions and their relationship with the A-share market.
  • Item
    The information needs of prospective postgraduate students: a data placemats approach
    (University College Cork, 2023) Patton, Aaron; Sammon, David; Nagle, Tadhg
    This is an exploratory study into the information needs of final year students when considering a postgraduate offering. There is little academic evidence on such information needs in the Higher Education Institution (HEI) context, yet the challenges that HEIs face to design effective data-driven recruitment and marketing strategies, and the variability in information currently provided to prospective postgraduate students presents a real opportunity for further investigation. For the purposes of this research, we are focusing on final year business school students only (Cork University Business School) and their interest in postgraduate programmes within the business school and beyond. This allows the research to focus on the information needs for recruitment but also retention. Hearing the final year student voice in this research but also comparing it to the HEI recruitment personnel voice will highlight the alignment of the respective positions on information needs. It is expected that this research will lend itself to the prescription of design guidelines for information needs. These design guidelines would be of practical value to HEIs.
  • Item
    The efficient market hypothesis applied to greyhound racing
    (University College Cork, 2022) Gaine, Bill; Butler, Robert; Butler, David
    Despite a growing amount of literature applying the Efficient Market Hypothesis (EMH) in sports betting markets (Angelini, Angelis, Singleton, 2019, Brechot and Flepp, 2020). Many sports, like horse racing, could be subject to corruption through shirking (Goodwin and Corral, 1996). Greyhound racing provides a unique sporting environment when testing betting market efficiency, where shirking is almost impossible. This study applies EMH to anecdotal evidence from the greyhound racing industry. A longstanding anecdotal belief in greyhound racing is that a dog placed in Trap Four of the six possible traps is the coffin trap. This belief implies that being in Trap Four reduces the chance of success in any given contest. This study used multiple iterations of a Poisson regression to perform three distinctive groups of regressions. This first included Pre-Race variables; the second included the determinants of finishing position: within-race bends, and finally, the third factored in the determinants of finishing position: trap dummies. The “coffin trap” theory holds weight; Trap Four significantly predicted race outcomes across each regression. Trap Three was also significant across most regressions, showing that it could also be considered a coffin trap. Interestingly, when either Trap Three or Trap Four were removed, either trap came out with an advantage over the other traps, indicating that avoiding crowding was crucial in determining race outcome. Greyhound racing provides a unique area to further investigate the EMH in sports betting markets without corruption through shirking. This study could be furthered in the future by incorporating the jurisdictions of Ireland and Australia and diverse types of races from different distances, hurdles or handicap races.