Essays on Crypto-Finance - Machine Learning Forecasts, Causal Network Dynamics, and Informed Option Trading

Aug 2, 2026

Upload by Violet

Crypto-finance, an emerging field at the intersection of financial technology and blockchain applications, is transforming traditional financial markets by introducing cryptocurrencies. This thesis presents a comprehensive exploration of crypto-finance, leveraging machine learning (ML) techniques to forecast cryptocurrency volatility, analyze market structure and dynamics through causal network analysis, and evaluate whether cryptocurrency options can predict market movements. The work delivers three contributions: ML-driven volatility forecasting with tuned LSTM and interpretability tools, network-based spillover and information diffusion analysis emphasizing stablecoin roles, and an assessment of informed crypto options trading on Bitcoin using Deribit data.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages228

Reading Time9 h 35 min

AccessFree to download

Acknowledgements

Abstract

Machine learning for volatility forecasting

Causal network dynamics and information diffusion

Informed option trading and predictive power

This thesis has been submitted in fulfilment of the requirements for a postgraduate degree (e. g. PhD, MPhil, DClinPsychol) at the University of Edinburgh. Please note the following terms and conditions of use: This work is protected by copyright and other intellectual property rights, which are retained by the thesis author, unless otherwise stated. A copy can be downloaded for personal non-commercial research or study, without prior permission or charge. This thesis cannot be reproduced or quoted extensively from without first obtaining permission in writing from the author. The content must not be changed in any way or sold commercially in any format or medium without the formal permission of the author. When referring to this work, full bibliographic details including the author, title, awarding institution and date of the thesis must be given. Essays on Crypto-Finance: Machine Learning Forecasts, Causal Network Dynamics, and Informed Option Trading Yijun Wang A thesis submitted in fulfilment of the requirements for the degree of Doctor of Philosophy The University of Edinburgh 2024 Acknowledgements I am deeply grateful for the guidance and support I received during my PhD journey, and I would like to express my deepest gratitude to those whose contributions were invaluable. First and foremost, I extend my heartfelt thanks to my PhD supervisor, Prof. Galina Andreeva, whose expertise, trust, and patience added considerably to my graduate experience. I am equally grateful to my co-supervisor, Dr. Belen MartinBarragan, whose insights and attention to detail have greatly enhanced my research. Their encouragement and trust were very important to the completion of my PhD. They are truly the best supervisors I have ever met. I appreciate the University of Edinburgh’s financial support throughout my PhD study. The collaborative environment and resources offered by the university have been helpful to my research. Additionally, the opportunities provided by the business school as a Research Assistant and Teaching Assistant have improved my communication and teaching skills, which are invaluable for my academic career. A special acknowledgement goes to the Cryptocurrency Research Conference, organised by Dr. Larisa Yarovaya from the University of Southampton and Prof. Andrew Urquhart from the University of Reading. Receiving the Best Doctoral Student Paper award was a significant encouragement to me. I am also grateful for the conference’s role in fostering collaboration opportunities and facilitating the exchange of ideas about cryptocurrency and FinTech. Special thanks to my coauthor, Bastien Buchwalter from SKEMA Business School, for his collaboration and for providing the crypto option trading data. I would like to express my deepest gratitude to my family—my parents and grandparents—for their unwavering support and love throughout my academic journey and personal development. I hold a special place in my heart for my grandparents and hope they are finding peace and joy in heaven. Additionally, Iowe a heartfelt thank you to my partner, Xiao Han, and my friends, especially Yujia Chen. Their encouragement, joy, and steadfast support helped me navigate the most challenging times. Lastly, I would like to thank myself for being brave and curious to explore new things. This PhD journey has been one of profound experience, harvest, and growth. Abstract Crypto-finance, an emerging field at the intersection of financial technology and blockchain applications, is transforming traditional financial markets by introducing cryptocurrencies. This thesis presents a comprehensive exploration of crypto-finance, leveraging machine learning (ML) techniques to forecast cryptocurrency volatility, assess the structure and dynamics of the cryptocurrency market through causal network analysis, and examine the predictive power of cryptocurrency options on market movements. Consequently, this thesis makes three

FAQs

What does the thesis aim to explore in crypto-finance?

It explores crypto-finance by using machine learning to forecast cryptocurrency volatility, analyze market dynamics via causal network analysis, and test whether cryptocurrency options can predict market movements.

How are machine learning models used for volatility forecasting?

Random Forest and LSTM models forecast cryptocurrency volatility using internal market determinants and external uncertainty factors, with genetic algorithms and artificial bee colony methods tuning LSTM hyperparameters.

What is examined in the options trading contribution?

The thesis investigates informed crypto options trading focused on Bitcoin using Deribit data, finding that ML models (especially Random Forest) outperform a traditional linear method and reveal nonlinear interactions affecting returns.

Aug 2, 2026

Upload by Violet