Document Type
Dissertation
Degree
Doctor of Philosophy (PhD)
Major/Program
Applied Mathematical Sciences
First Advisor's Name
Zhongming Wang
First Advisor's Committee Title
Co-Committee Chair
Second Advisor's Name
Svetlana Roudenko
Second Advisor's Committee Title
Co-Committee Chair
Third Advisor's Name
Hakima Bessaih
Third Advisor's Committee Title
Committee Member
Fourth Advisor's Name
Enrique Villamor
Fourth Advisor's Committee Title
Committee Member
Fifth Advisor's Name
Arun Upadhyay
Fifth Advisor's Committee Title
Committee Member
Keywords
Machine Learning, Bitcoin, Financial Markets
Date of Defense
6-19-2023
Abstract
This research delves deep into the application of machine learning techniques in the realm of cryptocurrency markets, with a specific focus on Bitcoin. The work explores forecasting Bitcoin prices, identifying patterns in Bitcoin transactions, and the innovative use of reinforcement learning for algorithmic trading.
In the initial segment, we develop a comprehensive framework for forecasting Bitcoin prices. Through meticulous experimentation and optimization, we demonstrate the effectiveness of various machine learning models in predicting the notoriously volatile Bitcoin market. The validity of the chosen methods is established through statistical significance and model performance metrics.
In the following section, the research identifies unique patterns and behaviors in Bitcoin transactions by applying advanced machine learning algorithms to cluster transactional data. The findings derived from this analysis can enhance our understanding of Bitcoin transaction dynamics, providing valuable insights for investors, regulators, and other market participants.
In the culminating phase of the research, we introduce a novel approach using reinforcement learning, a dynamic subset of machine learning, to improve algorithmic trading strategies and decision-making processes in the high-frequency world of cryptocurrency trading.
Collectively, this research provides valuable insights into the growing field of cryptocurrency trading and investment by applying machine learning techniques. The potential implications of the research findings could affect future market analysis, algorithmic trading strategies, and even broader financial technologies.
Identifier
FIDC011188
Recommended Citation
Sanchez, Giancarlo, "Machine Learning Techniques for Quantitative Finance in Cryptocurrency Markets" (2023). FIU Electronic Theses and Dissertations. 5376.
https://digitalcommons.fiu.edu/etd/5376
Rights Statement
In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/
This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).