Interview: using deep neural networks for derivatives pricing problems (Premium)

A recent academic paper showed how deep neural networks can be applied to derivative pricing problems, and in a way that appeases regulatory concerns about the use of such advanced tech.

The research team (Blanka Horvath from the Department of Mathematics at ETH Zurich, Aitor Muguruza from Imperial College London and Mehdi Tomas from Ecole Polytechnique) presented a consistent neural network based calibration method for a number of volatility models — including the rough volatility family — that performs the calibration task within a few milliseconds for the full implied volatility surface.

Fintech Capital Markets spoke with Blanka Horvath, who, among her appointments, is a lecturer at King’s College London in the Financial Mathematics group and an honorary lecturer in the Department of Mathematics at Imperial College London, as well as a theme lead in the Alan Turing Institute within the Finance and Economics programme, led by Lukasz Szpruch.

At the Alan Turing Institute, she is part of a group of academics, financial regulators, and buy- and sell-side participants that meet regularly to focus on the safe and ethical use of machine learning and artificial intelligence in finance.

This content requires a Finadium subscription. Articles with an unlocked symbol can be accessed with free registration. Log in or create a free account by signing up here..

Related Posts

Previous Post
Get the weekly SFM update – our April 26 newsletter is online
Next Post
Fed discussion paper: Liquidity Funding Shocks: The Role of Banks’ Funding Mix

Fill out this field
Fill out this field
Please enter a valid email address.


Reset password

Create an account