Show simple item record

AdvisorFetais, Noora
AuthorFEZOONI, ABDULHADY YOUNES
Available date2024-07-08T07:23:48Z
Publication Date2024-06
URIhttp://hdl.handle.net/10576/56479
AbstractThis study evaluates the use of deep reinforcement learning (DRL) in market-making, specifically in the Bitcoin market. DRL has shown promise in providing robust market-making capabilities, including enhanced market liquidity and risk management, which may lead to more efficient price discovery and lower volatility. The study also discusses the historical perspective of market-making techniques and explains how agents can use DL algorithms and RL principles to improve preset objectives in financial markets. It also reviews essential DRL algorithms like Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), and Deep Q-Network (DQN) and their specialized applications and the possible effect of DRL-based market-making on market dynamics. This project uses data science and machine learning to study Bitcoin market data. It's important for financial market analysis, especially in volatile and speculative cryptocurrency markets. The models' effectiveness is evaluated with spread capture ratio, market impact, and profitability. The findings can help academics and financial institutions understand how DRL can improve market efficiency and stability.
Languageen
SubjectDeep Reinforcement Learning (DRL)
Market Making
Bitcoin Market
Financial Markets
Machine Learning
Data Science
Market Efficiency
Market Stability
TitleSTRONG MARKET-MAKING USING DEEP REINFORCEMENT LEARNING: BITCOIN MARKET ANALYSIS
TypeMaster Thesis
DepartmentComputer Science and Engineering
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record