In Silicon Valley, sentiment is close to a currency: optimism moves hiring, funding and stock prices long before it shows up in the official statistics. A new paper from the Federal Reserve Bank of San Francisco suggests that intuition has real forecasting power, at least when it comes to spotting recessions.
Released July 17, the working paper by SF Fed economists Nicolas Petrosky-Nadeau, Yeji Sung and Daniel J. Wilson asks a blunt question in its title, "Do Vibes Predict Recessions?" To test it, the authors compared "soft" data, measures of consumer sentiment, policy uncertainty and the mood of the news, against the "hard" data of employment, output and inflation.
The soft data more than held its own. One month out, a model using only sentiment and narratives was more accurate than one using hard statistics alone and nearly matched a combined model on a standard forecasting benchmark. Sentiment reacted faster to building risk, identifying a larger share of the run-up months to past recessions, though at the cost of more false alarms.
The point, the authors stress, is not that mood is a crystal ball. Soft data partly anticipates what later shows up in the hard numbers, they write, but also carries "distinct information about recession risk" the hard data misses. Used together, the two did best, which is why the paper casts sentiment as a complement to conventional gauges rather than a substitute.
AcadeResearch, a research-analysis site that highlighted the paper, wrote in its assessment that the study "puts a defensible number on the marginal recession-forecasting content of soft data at short horizons, and shows that content survives careful controls for publication lags, revisions, and overfitting."
To keep the test fair, the researchers used real-time data vintages, the figures as they actually stood each month from August 1999 through May 2026, covering three recessions, so the models could not lean on later revisions. Their sentiment inputs included the University of Michigan consumer surveys, an economic-policy uncertainty index, the SF Fed's Daily News Sentiment Index and a Beige Book sentiment measure.