# Stellenangebot

## PhD position in Improving Machine Learning Methods for Contingent Claim Pricing and Hedging

PhD position in Improving Machine Learning Methods for
Contingent Claim Pricing and Hedging at the University of Amsterdam

The Stochastics group at the Korteweg de Vries Institute at the University of Amsterdam and the Actuarial Science and Mathematical Finance group at the Amsterdam School of Economics are pleased to announce a joint open PhD position in Improving Machine Learning Methods for Contingent Claim Pricing and Hedging.

The project will focus on, but will not necessarily be limited to, a promising relatively new mathematical characterization of uncertainty in financial time series (using the sequences of iterated integrals known as signatures) and a particular application for which classical modelling tools seem particularly hard to apply (the infinite-dimensional structure in forward prices for energy markets). We expect that insights for this particular theoretical method and practical problem may also help to design improvements for other applications of machine learning in the financial context, such as the generation of stochastic scenarios used in risk management for insurance companies and trading strategies that use derivatives to hedge payoffs of other exotic derivatives (such as forward prices in energy markets) and regime switching in stochastic modelling of asset prices.

We are looking for a candidate with a strong theoretical and computational background (e.g. functional analysis, measure theoretic probability, mathematics of Machine Learning, mathematical and computational finance). The candidate also needs to be genuinely interested in real world applications.

The application deadline is June 7. For more information and to apply, please see:

https://www.mathjobs.org/jobs/list/24580

The Stochastics group at the Korteweg de Vries Institute at the University of Amsterdam and the Actuarial Science and Mathematical Finance group at the Amsterdam School of Economics are pleased to announce a joint open PhD position in Improving Machine Learning Methods for Contingent Claim Pricing and Hedging.

The project will focus on, but will not necessarily be limited to, a promising relatively new mathematical characterization of uncertainty in financial time series (using the sequences of iterated integrals known as signatures) and a particular application for which classical modelling tools seem particularly hard to apply (the infinite-dimensional structure in forward prices for energy markets). We expect that insights for this particular theoretical method and practical problem may also help to design improvements for other applications of machine learning in the financial context, such as the generation of stochastic scenarios used in risk management for insurance companies and trading strategies that use derivatives to hedge payoffs of other exotic derivatives (such as forward prices in energy markets) and regime switching in stochastic modelling of asset prices.

We are looking for a candidate with a strong theoretical and computational background (e.g. functional analysis, measure theoretic probability, mathematics of Machine Learning, mathematical and computational finance). The candidate also needs to be genuinely interested in real world applications.

The application deadline is June 7. For more information and to apply, please see:

https://www.mathjobs.org/jobs/list/24580