https://www.um.edu.mt/library/oar/handle/123456789/137676 Sat, 04 Apr 2026 08:07:23 GMT 2026-04-04T08:07:23Z https://www.um.edu.mt/library/oar/handle/123456789/143458 Title: Complex environments, simple strategies : an in-depth profitability analysis of MACD, RSI and Bollinger bands for technological equities Abstract: This study focused on technical analysis through Moving Average Convergence Divergence (MACD), Relative Strength Index (RSI) and Bollinger Bands, both individually as well as their combination, to test their performance compared to the Buy-and-Hold strategy, using it as a benchmark. This research, unlike many previous studies, had a specific targeted sector which was the technological one. It also tried to bridge the gap between different research results regarding whether simple indicators were able to outperform the passive Buy-and-Hold strategy. This was done on high performing stocks from the NASDAQ stock exchange and was taken on 5- year and 20-year periods. The results showed that these indicators, as well as their combinations, severely underperformed the Buy-and-Hold strategy, reaching to just 50% of its profits in the 5- year period and 25% in the 20-year period. Description: M.A.(Melit.) Mon, 01 Jan 2024 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/143458 2024-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/138256 Title: Statistical arbitrage in commodity markets through PCA and OPTICS clustering Abstract: This thesis explored the application of statistical arbitrage strategies on commodity related assets. The asset universe consisted of a diversified basket of 55 assets spanning three asset classes: commodity futures, commodity-linked equities, and commodity currencies. Two strategies were employed: a traditional PCA-based approach and a method that additionally involved clustering the assets using OPTICS. Over the period from 2014 to 2024, both strategies generated slight yet consistent returns. Notably, the strategy incorporating OPTICS clustering outperformed, both in absolute returns and also risk adjusted performance, suggesting that the inclusion of a clustering step may provide additional benefits in such strategies. Moreover, when tested on a post COVID-19 period, the PCA approach failed to generate returns, while the OPTICS strategy remained slightly profitable. Additional results are presented on the characteristics of the residual parametrisation, as well as a insights into which asset clusters and sectors performed the best. Any returns attributable to both strategies proved to be uncorrelated both with a broad based commodity index and also the S&P500. Description: M.A.(Melit.) Mon, 01 Jan 2024 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/138256 2024-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/138255 Title: A study on whether quantitative trading strategies can continuously outperform humans using different strategies Abstract: Gone are the days when traders on Wall Street chaotically shouted bids and offers across trading floors, giving way to advanced trading systems that execute trades almost instantly as exponential technological growth has reshaped the financial industry. This study conducts a comprehensive comparative analysis of modern quantitative, rule-based autonomous investment strategies against more traditional, fund manager-led strategies within ETFs across three distinct markets: equities, fixed-income, and foreign exchange. Quantitative strategies utilise algorithms to make data-driven decisions, minimising human biases and emotions. In contrast, discretionary strategies rely on fund managers’ proprietary research, market insights, and intuition from experience. The two strategies were tested over a five-year period encompassing both stable and volatile markets arising from the unpredictability of the COVID-19 pandemic, ensuring a robust analysis of varied market conditions. While discretionary ETFs did, at times, achieve higher returns, they did so with higher volatility. This indicates that the prospect of higher returns is significantly influenced by the fund manager's skill, making consistent performance less predictable compared to algorithmic approaches. Quantitative strategies consistently outperformed their discretionary counterparts in a multifaceted series of tests focusing on risk-adjusted returns. The findings support the growing popularity of quantitative strategies in an increasingly automated environment, offering insights to investors and investment managers alike. Challenges to more traditional financial concepts also emerge, suggesting that markets might not be as efficient as previously believed, contributing to ongoing academic debates. Despite being limited by a five-year time frame since the legislative changes took place, this study lays a foundation for future research as the longer-term effects become observable. To conclude, the balance between algorithmic efficiency and human insight will shape the future of fund management, and the level of optimal oversight over the models remains to be determined. This work illustrates the benefits and potential provided by quantitative strategies and suggests a need for a fresh perspective on traditional investment approaches, hinting at a well-developed hybrid of the two. The era of traders shouting orders across trading floors may be over, but the drive to secure the best investment strategies has only grown more intense, propelled by technology’s continuous evolution. Description: M.A.(Melit.) Mon, 01 Jan 2024 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/138255 2024-01-01T00:00:00Z https://www.um.edu.mt/library/oar/handle/123456789/138253 Title: Empirical analysis of cryptocurrency price movements and their relationship to other assets : a VAR & rolling VaR approach Abstract: Cryptocurrency is a relatively new digital instrument often referred to "digital gold," yet our understanding of its behaviour remains limited. The scarcity of both data and research makes it difficult to study its dynamics and implications which poses challenges for this emerging asset class, especially when compared to gold, which benefits from extensive scholarly attention. Existing studies in circulation delve into the interconnectedness of Bitcoin with various asset classes such as commodities, currencies, and Equities focusing on themes such as volatility spillovers, returns, and hedging strategies. These papers utilize modelling techniques such as DY models, GARCH models, regression analysis, and VAR-based models in which most papers do not consider the efficiency of different cryptocurrencies along with the dynamic relationships in a post- recession period & economic expansion period, resulting in literature gaps. A blend of methodologies was implemented within this research to enhance the analysis effectiveness. This incorporates a mixed methodology approach of VAR, Rolling VaR, the Diebold-Yilmaz Connectedness Framework, Rolling VAR, GFEVD, Granger Causality, IRF’s and Correlation Analysis with respect to volatility spillovers, dynamic correlation patterns, and responses to economic shocks across various periods. The findings confirm Hypothesis 1, showing volatility spillovers between cryptocurrencies, blockchain equities are high with the DY suggesting a higher spillover effect in periods of systematic events such as COVID 19 & lower spillover during post-recession periods. Hypothesis 2 is partially accepted, as dynamic correlation being lower post-recession with Granger causality results showing Blockchain Equities holding predictive power of cryptos for 3-4 Year periods & Other Cryptos holding predictive power for LT (7 Years). Hypothesis 3 is partially accepted, indicating cryptocurrencies shock reaction are most impactful with other sectoral-adjacent assets & recessionary periods containing more instability and volatility. Impacts in post- Recession periods for non-crypto adjacent was identified to be lower. These results hold regulatory importance in terms of highlighting the potential for volatility mitigation strategies in cryptocurrencies. Policymakers may consider promoting legislation in favour of stablecoins, regulating specific cryptocurrency disclosures & regulating Defi Finance as if they were banks. Additionally, the research could serve as a valuable guide for individual and institutional investors in managing their cryptocurrency based on economic cycles & interpreting them as a hedge or a diversifier accordingly. Description: M.A.(Melit.) Mon, 01 Jan 2024 00:00:00 GMT https://www.um.edu.mt/library/oar/handle/123456789/138253 2024-01-01T00:00:00Z