Back

Speaker "Revant Nayar" Details Back

 

Topic

Can financial crashes be anticipated using physics?

Abstract

“The market has experienced large rallies and drawdowns over the last two years driven by uncertainties caused by the pandemic and inflationary fears. These ‘bubbles’ and ‘crashes’ are notoriously difficult to anticipate using AI and data-driven techniques due to non-stationarity and small sample sizes inherent in the problem. We turn to Sornette’s famous interacting spin model of investor interactions in which bubble-induced crashes result from phase transitions during which the dynamics of the market acquires a discrete scale invariance. We investigate if truly, these models or their extensions could have predicted some of the large drawdowns we have seen in the S&P 500 or the supposed ‘bursting of bubbles’ in ‘pandemic stocks’ such as Docusign, Teladoc and Zoom. 

Profile

Revant Nayar is CTO at FMI Tech and former Research Affiliate at IAS. He has published papers and given talks at many leading conferences and universities, with a special emphasis on physics-inspired approaches to financial modelling. He features in Wealth and Finance Magazine as well as CIO Outlook Capital Markets, as one of the chief developers of Field Machine Intelligence, which is a robust alternative to AI tailored for financial time series.“