Machine learning (ML) offers a novel approach to the identification and selection of predictors in regression models. ML permits the consideration of large numbers of potential variables and the identification of a relevant and statistically workable feature set. ML methods are also well-suited for addressing multicollinearity in predictors, a common problem in financial time-series models. Furthermore, ML methods are well-suited to identifying general trends in data and thereby avoiding overfitting problems and thus yielding superior out-of-sample performance. While ML methods are widely employed in computer science and artificial intelligence, their application in finance is still limited and nascent.
This project will contribute to the existing literature by identifying and modelling information transmission processes across international stock markets. It aims to use a truly global representative sample of stock markets across different geographic regions to determine information leaders and information linkages. It also sets out to test the ability of ML techniques to predict stock market movements out-of-sample.
Throughout its execution, the project will compare mainstream machine learning techniques, such as ridge, LASSO and elastic net regularization etc., and will assess their applicability and usefulness relative to commonly used methods in feature identification. It will contribute to existing literature by presenting not only an overview of a novel methodology applied within the discipline of finance but also in assessing its applicability to (specifically) gaining insight and a better understanding of information transmission processes.
The successful candidate should possess advanced econometric skills (good knowledge and experience in constructing and estimating time series regression models and the ability to work with complex financial market databases, including high-frequency data) and be proficient in the use of statistical packages (Eviews, STATA, etc.). The candidate must have an understanding of and be familiar with ML methods and have knowledge of interactions between international financial markets.
This project is supervised by Prof Janusz Brzeszczyński and Dr Kuba Szczygielski.
Eligibility and How to Apply:
Please note eligibility requirement:
• Academic excellence of the proposed student i.e. 2:1 (or equivalent GPA from non-UK universities [preference for 1st class honours]); or a Masters (preference for Merit or above); or APEL evidence of substantial practitioner achievement.
• Appropriate IELTS score, if required.
For further details of how to apply, entry requirements and the application form, see: https://www.northumbria.ac.uk/research/postgraduate-research-degrees/how-to-apply/
Please note: Applications that do not include a research proposal of approximately 1,000 words (not a copy of the advert), or that do not include the advert reference (e.g. SF19/…) will not be considered.
Northumbria University takes pride in, and values, the quality and diversity of our staff. We welcome applications from all members of the community. The University holds an Athena SWAN Bronze award in recognition of our commitment to improving employment practices for the advancement of gender equality.