Date: Wednesday, 3 April 2024, at 12:30pm (Paris) and 7:30pm (Singapore)

Dual format: ESSEC Paris La Défense (CNIT), Room TBA
and via Zoom, please click here

We model high-frequency cryptocurrency returns with a Markov-Switching Multifractal process (MSM; Calvet and Fisher 2001). We use Approximate Maximum Likelihood (AML; Czellar, Frazier, and Renault 2022) to estimate all the parameters of the MSM model, including the number k of hidden states. The MSM model accurately predicts major cryptocurrency returns and its prediction power is largely superior to those of GARCH-type alternatives. Furthermore, we propose a trading strategy based on dynamic Sharpe ratio signals generated through the MSM model at high-frequency. The strategy generates substantial returns, proving resilient to the high trading fees and execution delays common in cryptocurrency exchanges.

Kind regards,
Jeremy Heng, Olga Klopp, Roberto Reno, and Marie Kratz
https://crear.essec.edu/crear-events/working-group-on-risk
and Riada Djebbar (Singapore Actuarial Society - ERM)