Presentation Type
Poster
Presentation Type
Submission
Keywords
volatility forecasting, risk management, deep learning, time series analysis, GARCH, LSTM, transformer
Department
Computer Science
Major
Finance
Abstract
Volatility forecasting in the financial market plays a pivotal role across a spectrum of disciplines, such as risk management, option pricing, and market making. However, volatility forecasting is challenging because volatility can only be estimated, and different factors influence volatility, ranging from macroeconomic indicators to investor sentiments. While recent works suggest advances in machine learning and artificial intelligence for volatility forecasting, a comprehensive benchmark of current statistical and learning-based methods for such purposes is lacking. Thus, this paper aims to provide a comprehensive survey of the historical evolution of volatility forecasting with a comparative benchmark of key landmark models. We open-source our benchmark code to further research in learning-based methods for volatility forecasting.
Faculty Mentor
Clemens Kownatzki, Fabien Scalzo, Eun Sang Cha
Funding Source or Research Program
Keck Scholars Program
Location
Waves Cafeteria
Start Date
22-3-2024 1:30 PM
End Date
22-3-2024 2:30 PM
Historical Perspectives in Volatility Forecasting Methods with Machine Learning
Waves Cafeteria
Volatility forecasting in the financial market plays a pivotal role across a spectrum of disciplines, such as risk management, option pricing, and market making. However, volatility forecasting is challenging because volatility can only be estimated, and different factors influence volatility, ranging from macroeconomic indicators to investor sentiments. While recent works suggest advances in machine learning and artificial intelligence for volatility forecasting, a comprehensive benchmark of current statistical and learning-based methods for such purposes is lacking. Thus, this paper aims to provide a comprehensive survey of the historical evolution of volatility forecasting with a comparative benchmark of key landmark models. We open-source our benchmark code to further research in learning-based methods for volatility forecasting.