Lusha Xu

I work at the intersection of empirical macroeconomics and machine learning, with particular emphasis on what corporate disclosures reveal about aggregate economic activity.

My job market paper uses large language models to extract forward-looking firm-level signals from more than 20,000 SEC 10-K and 10-Q filings, and shows that the resulting “textual factors” improve out-of-sample forecasts of GDP growth. I also study how central bank digital currencies reshape bank intermediation and lending risk.

I teach across the Ph.D. macroeconomics core and the undergraduate curriculum, and I serve as Lead Consultant at UC Riverside’s Graduate Quantitative Methods Center.