Mathematical Finance & Financial Data Science Seminar

Learning The Pricing Kernel: Applications To Option Pricing

Speaker: Daniel Bloch, Head of Quant at Blu Analytics

Location: Online Zoom access provided to registrants

Date: Tuesday, May 9, 2023, 5:30 p.m.


We propose to identify the pricing kernel from option prices on both the natural probability measure 
and the risk-neutral one. We use Machine Learning to generate consistent synthetic data closely related to 
the original time series, and use it for computing conditional expectations, under the historical measure, 
with Reinforcement Learning in a model independent way. We are interested in estimating a portfolio of 
option prices at any future time for trading and risk management purposes. However, we do not know the 
model driving the dynamics of the actual stock prices, but only observe discretely their evolution. 
We use these subjective option prices, under the historical measure, to compute the adjusted pricing kernel, 
which maps the option prices from the historical measure to the risk-neutral measure. We use it to modify the 
discretely observed stock prices into a risk-adjusted process, which we use for computing the expected value 
of the contingent claims in the risk-neutral measure. Finally, we illustrate our approach in a simple model 
where the market price of risk is driven by an Ornstein-Uhlenbeck process.

Speaker Bio:

Daniel Bloch is head of quantitative strategies at Blu, a systematic event trading fund using NLP to anticipate large market moves 
based on news.  Prior to working at Blu, Daniel managed teams of quant researchers in top tier banks, developing and 
implementing option pricing and risk models. He was also a portfolio manager on multi-strategies systematic trading 
across continents, using multifractal analysis and machine learning. Daniel conducts research on mathematical finance 
and AI, focusing on dynamical models applied to forecasting the stock and option market in order to maximise return 
and minimise risk.


QF Kernel Presentation -Revised