We developed a news-based machine learning framework for finding what themes are driving the FX vols. The framework also complements traditional techniques of judging if FX vol is rich or cheap and is currently suggesting that FX vol as an aggregate is mildly cheap.

The framework currently identifies inflation as the most significant concern that investors remain most sensitive to, with commodities, central banks, market conditions and rates also been notable factors on that cross-section of news flows and FX vol beta to that news, but jobs only nominal / negligible.

We monitor 28 SmartTag categories of macro risk across global news reports and capture their changes in volume and anxiety (inverted tone). We test the sensitivity of each category against the VXY (as a proxy to FX risk) and identify what investors seem to be currently most sensitive to. Any category that tests significantly positive we mark as a “Category of Concern” (CoC) and measure how much it is contributing to (or reducing) our inferred risk.

 

This podcast was recorded on March 8, 2023.

This communication is provided for information purposes only. Institutional clients can view the related report at https://www.jpmm.com/research/content/GPS-4335589-0 for more information; please visit www.jpmm.com/research/disclosures for important disclosures. © 2023 JPMorgan Chase & Co. All rights reserved.