• Graduate Program
    • Why study Business Data Science?
    • Research Master
    • Admissions
    • Course Registration
    • Facilities
  • Research
  • News
  • Events
  • Alumni
  • Magazine
Home | Events Archive | On the Universality of the Volatility Formation Process: when Machine Learning and Rough Volatility Agree
Seminar

On the Universality of the Volatility Formation Process: when Machine Learning and Rough Volatility Agree


  • Series
    Erasmus Econometric Institute Series
  • Speakers
    Matheu Rosenbaum (Ecole Polytechnique, France)
  • Field
    Econometrics
  • Location
    Erasmus University Rotterdam, E building, room ET-18
    Rotterdam
  • Date and time

    April 06, 2023
    12:00 - 13:00

Abstract
We train a universal LSTM network based on a pooled dataset made of hundreds of liquid stocks aiming at forecasting next day realized volatility. Showing its consistently superior performance compared to asset-specific parametric models, we uncover nonparametric evidences of universal volatility formation mechanism across assets relating past market realizations, including daily returns and volatilities, to current volatilities. A simple blended forecast combining the rough fractional stochastic volatility and quadratic rough Heston models with fixed parameters results in the same level of performance as the universal LSTM, which confirms the universal volatility formation process from a parametric perspective. This is joint work with Jianfei Zhang.

About Mathieu Rosenbaum
Mathieu Rosenbaum is a full professor at École Polytechnique, where he holds the chair “Analytics and Models for Regulation” and is co-head of the quantitative finance (El Karoui) master program. His research mainly focuses on statistical finance problems, regulatory issues and risk management of derivatives. He published more than 75 articles on these subjects in the best international journals and supervised about 20 PhD students. He is notably one of the most renowned experts on the quantitative analysis of market microstructure and high frequency trading. On this topic, he co-organizes every two years in Paris the conference "Market Microstructure, Confronting Many Viewpoints". He is also at the origin (with Jim Gatheral and Thibault Jaisson) of the development of rough volatility models.

Mathieu Rosenbaum has collaborations with various financial institutions (investment banks, hedge funds, regulators, exchanges...), notably BNP-Paribas since 2004. He also has several editorial activities as he is one of the editors in chief of the journal “Market Microstructure and Liquidity“ and is associate editor for 10 other journals. He received the Europlace Award for Best Young Researcher in Finance in 2014, the European Research Council Grant in 2016, the Louis Bachelier prize in 2020 and the Quant of the Year award in 2021.

You can sign up for a meeting with the speaker in the separate worksheet in the Excel file.

Seminars2023Spring.xlsx