Model free Deep Hedging

Deep Hedging is a simple machine learning inspired algorithm, which produces risk management strategies, which is built upon a given market environment and a given preference structure. In this talk we introduce a novel algorithm inspired by Moritz Duembgen’s and Chris Rogers’ Bayesian approach, which can additionally deal with
model uncertainty. We discuss a machine learning implementation of it, and provide a universality proof when it can be successful (joint work with Matteo Gambara and Thorsten Schmidt).

Join Zoom Meeting
https://maths-cam-ac-uk.zoom.us/j/98775083754?pwd=aUhteExxNEgrWW5mMkd0TGw2SlhQUT09
Meeting ID: 987 7508 3754
Passcode: 837932

• Speaker: Josef Teichmann (ETH Zurich)
• Wednesday 09 March 2022, 14:00–15:00
• Venue: Virtual (Zoom details under abstract).
• Series: CCIMI Seminars; organiser: Randolf Altmeyer.