Speeding up Pricing and Calibration in the Rough Bergomi Model Using Deep Learning

Student: Zavid nikita Mahbub

Supervisor: Alexey Akhmetshin

Faculty: International College of Economics and Finance

Educational Programme: International Programme in Economics and Finance (Bachelor)

Final Grade: 9

Year of Graduation: 2024

In this paper, we verify that the properties of log-increments of realized volatility of the S&P 500 are similar to those of a fractional Brownian motion process on recent market data, indicating that rough stochastic volatility models such as the rough Bergomi model are a natural way to model volatility dynamics. We then compare the accuracy in predicting the rough Bergomi implied volatilities with neural networks trained on just the implied volatilities against models trained additionally on the delta and vega of the rough Bergomi European call prices. Finally, we provide a flexible deep calibration routine that can be used over a range of maturities, values of moneyness and market interest rates.

Full text (added June 9, 2024)

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses