Options, as an important financial derivative, are actively traded with huge trading volume and widely used for hedging, speculation and arbitrage. Spanning over a few decades, option pricing problem continues to intrigue scholars and practitioners in finance. Following our previous research (Shang and Byrne, 2019 & 2021), this research project will continue to explore and optimize valuation methods for American Options, Employee Stock Options and other Exotic Options. A variety of financial modelling techniques will be investigated and developed to optimize current lattice-based option pricing model. Machine Learning paradigms and Predictive Modelling will be examined and used to value options and discover optimal exercise boundary and classify options. Optimised option pricing models will be further applied to achieve real-time Implied Volatility and Delta hedging estimation that are required by trading platform. Relevant applications will be created using Python and ready for commercial usage. This research is positioned in the intersection between Finance and Technology, which can translate well across academia, industry and varying jurisdictions.
Minimum 2.1 BSc in a quantitative discipline (e.g. Quantitative Finance, Econometrics, Mathematics,
Data Science)
Experience in programming (e.g. Python, R, VBA, C/C++)
Scholarship not available. Fees & Materials to be paid by the student. Materials costs not significant
If you are interested in submitting an application for this project, please complete an Expression of Interest.
Applications submitted without an EOI form will not be considered.