Webinar: Jay Cao, Jacky Chen, John Hull, Zissis Poulos: Deep Hedging Using RL
Webinar
Wednesday, September 9, 2020 - 06:30 PM
Until: Wednesday, September 9, 2020 - 08:30 PM
(Adjusted for timezone: Europe/London)
Categories
PLEASE NOTE THAT THIS WEBINAR WILL START ON WEDNESDAY, 9 SEPTEMBER, 2020, AT 6:30 PM ***BST (LONDON TIME)*** (1.30 PM ***EDT (NEW YORK TIME)***)
TITLE: Deep Hedging of Derivatives using Reinforcement Learning
ABSTRACT:
We show how reinforcement learning can be used to derive optimal hedging strategies for derivatives when there are transaction costs. We illustrate our approach by showing the difference between using delta hedging and optimal hedging for a short position in a call option when the objective is to minimize a function equal to the mean hedging cost plus a constant times the standard deviation of the hedging cost. Two situations are considered. In the first, the asset price follows a geometric Brownian motion. In the second, the asset price follows a stochastic volatility process. The basic reinforcement learning approach is extended in a number of ways. First, it uses two different Q-functions so that both the expected value of the cost and the expected value of the square of the cost are tracked for different state/action combinations. This approach increases the range of objective functions that can be used. Second, it uses a learning algorithm that allows for continuous state and action space. Third, it compares the accounting P&L approach (where the hedged position is valued at each step) and the cash flow approach (where cash inflows and outflows are used). We find that a hybrid approach involving the use of an accounting P&L approach that incorporates a relatively simple valuation model works well. The valuation model does not have to correspond to the process assumed for the underlying asset price.
BIOGRAPHIES
Jay Cao is a Senior Research Associate at the Rotman TD Management Data and Analytics Lab. He holds a Ph.D. in Economics from University of Toronto. His current research interest is in the area of applied machine learning in finance.
Jacky Chen is a senior analyst at OPTrust and a research assistant at the Rotman Financial Innovation Hub(FinHub). He has experience in systematic investment strategy development, trade execution, and risk management. His current research with FinHub focuses on applying machine learning to derivative pricing and risk management. He graduated from University of Toronto with a B.Sc in financial economics and statistics and a master degree in financial risk management.
John Hull is the Maple Financial Professor of Derivatives and Risk Management at the Joseph L. Rotman School of Management, University of Toronto. His research has considered many different aspects of the pricing and hedging of derivatives. He has written four books: “Risk Management and Financial Institutions” (now in its 5th edition); "Options, Futures, and Other Derivatives" (now in its 10th edition); "Fundamentals of Futures and Options Markets" (now in its 9th edition); and “Machine Learning in Business: An Introduction to the World of Data Science” (now in its 2nd edition). The books have been translated into many languages and are widely used by practicing managers as well as in the classroom.
Zissis Poulos received a Diploma in Electrical and Computer Engineering from the National Technical University of Athens in 2011, an M.A.Sc. degree in Electrical and Computer Engineering from the University of Toronto in 2014, and a Ph.D. degree in Electrical and Computer Engineering from the University of Toronto in 2018. He is currently a Postdoctoral Fellow at Rotman School of Management at the University of Toronto. His research interests include applied machine learning in finance, deep learning acceleration, statistical diagnosis and debugging of VLSI systems, modeling and optimization of information/influence diffusion in social graphs, and distributed ledger technologies. He is a member of IEEE and ACM.
For more information, visit https://www.meetup.com/thalesians/events/272161608/
TITLE: Deep Hedging of Derivatives using Reinforcement Learning
ABSTRACT:
We show how reinforcement learning can be used to derive optimal hedging strategies for derivatives when there are transaction costs. We illustrate our approach by showing the difference between using delta hedging and optimal hedging for a short position in a call option when the objective is to minimize a function equal to the mean hedging cost plus a constant times the standard deviation of the hedging cost. Two situations are considered. In the first, the asset price follows a geometric Brownian motion. In the second, the asset price follows a stochastic volatility process. The basic reinforcement learning approach is extended in a number of ways. First, it uses two different Q-functions so that both the expected value of the cost and the expected value of the square of the cost are tracked for different state/action combinations. This approach increases the range of objective functions that can be used. Second, it uses a learning algorithm that allows for continuous state and action space. Third, it compares the accounting P&L approach (where the hedged position is valued at each step) and the cash flow approach (where cash inflows and outflows are used). We find that a hybrid approach involving the use of an accounting P&L approach that incorporates a relatively simple valuation model works well. The valuation model does not have to correspond to the process assumed for the underlying asset price.
BIOGRAPHIES
Jay Cao is a Senior Research Associate at the Rotman TD Management Data and Analytics Lab. He holds a Ph.D. in Economics from University of Toronto. His current research interest is in the area of applied machine learning in finance.
Jacky Chen is a senior analyst at OPTrust and a research assistant at the Rotman Financial Innovation Hub(FinHub). He has experience in systematic investment strategy development, trade execution, and risk management. His current research with FinHub focuses on applying machine learning to derivative pricing and risk management. He graduated from University of Toronto with a B.Sc in financial economics and statistics and a master degree in financial risk management.
John Hull is the Maple Financial Professor of Derivatives and Risk Management at the Joseph L. Rotman School of Management, University of Toronto. His research has considered many different aspects of the pricing and hedging of derivatives. He has written four books: “Risk Management and Financial Institutions” (now in its 5th edition); "Options, Futures, and Other Derivatives" (now in its 10th edition); "Fundamentals of Futures and Options Markets" (now in its 9th edition); and “Machine Learning in Business: An Introduction to the World of Data Science” (now in its 2nd edition). The books have been translated into many languages and are widely used by practicing managers as well as in the classroom.
Zissis Poulos received a Diploma in Electrical and Computer Engineering from the National Technical University of Athens in 2011, an M.A.Sc. degree in Electrical and Computer Engineering from the University of Toronto in 2014, and a Ph.D. degree in Electrical and Computer Engineering from the University of Toronto in 2018. He is currently a Postdoctoral Fellow at Rotman School of Management at the University of Toronto. His research interests include applied machine learning in finance, deep learning acceleration, statistical diagnosis and debugging of VLSI systems, modeling and optimization of information/influence diffusion in social graphs, and distributed ledger technologies. He is a member of IEEE and ACM.
For more information, visit https://www.meetup.com/thalesians/events/272161608/