Mathematical Finance & Financial Data Science Seminar

Empirical deep hedging

Speaker: Juho Kanniainen, Tampere University, Finland

Location: Online Zoom access provided to registrants

Date: Tuesday, March 21, 2023, 5:30 p.m.


Existing hedging strategies are typically based on specific financial models: either the strategies are directly based on a given option pricing model or stock price and volatility models are used indirectly by generating synthetic data on which an agent is trained with reinforcement learning. In this paper, we train an agent in a pure data-driven manner. Particularly, we do not need any specifications on volatility or jump dynamics but use large empirical intra-day data from actual stock and option markets. The agent is trained for the hedging of derivative securities using deep reinforcement learning (DRL) with continuous actions. The training data consists of intra-day option price observations on S&P500 index over 6 years, and top of that, we use other data periods for validation and testing. We have two important empirical results. First, a DRL agent trained using synthetic data generated from a calibrated stochastic volatility model outperforms the classic Black–Scholes delta hedging strategy. Second, and more importantly, we find that a DRL agent, which is empirically trained directly using actual intra-day stock and option prices without the prior specification of the underlying volatility or jump processes, has superior performance compared with the use of synthetic data. This implies that DRL can capture the dynamics of S&P500 from the actual intra-day data and to self-learn how to hedge actual options efficiently.

Link to the paper:

Speaker Bio:

Dr Juho Kanniainen is Full Professor in Quantitative Finance at Tampere University, Finland, where he is heading a research group Financial Computing and Data Analytics. He has previously coordinated two EU projects HPCFinance (GA 289032) and BigDataFinance (GA 675044, Totally, these two networks secured 7.5 Meur of EU funding and trained 26 PhD students and 2 post-docs. He has organized several conferences and he has served as a co-editor for a book “High-Performance Computing in Finance” (Chapman & Hall). His papers on financial market research with different methods have been published in top-tier journals, including Review of Finance (IF 5.059) and IEEE Transactions on Neural Networks and Learning Systems (IF 14.255). He has supervised and co-supervised 10 PhD students and 2 are ongoing. His main research focus lies on financial markets research with methods on machine learning and network science.


This event is free, but requires registration. You will then receive the Zoom link by email about a day or so before the event.

Upcoming Events

VIEW ALL events


Alumni Feature


The proof of our program is in the placement of our students in leading financial industry positions in New York and beyond. Read more about some of our Alumni, where they work, and what aspects of the program they found most valuable through questions and answers interviews.


All set to go? Start the application now.