This paper combines a data rich environment with a machine learning algorithm to provide new estimates of time-varying systematic expectational errors ("belief distortions") embedded in survey responses. We find that distortions are large even for professional forecasters, with all respondent-types over-weighting their own beliefs relative to publicly available information. Forecasts of inflation and GDP growth oscillate between optimism and pessimism by large margins, with biases in expectations evolving dynamically in response to cyclical shocks. The results suggest that artificial intelligence algorithms can be productively deployed to correct errors in human judgement and improve predictive accuracy.Institutional subscribers to the NBER working paper series, and residents of developing countries may download this paper without additional charge at www.nber.org.

We document large, longer term, joint regime shifts in asset valuations and the real federal funds rate‐ spread. To interpret these findings, we estimate a novel macrofinance model of monetary transmission and find that the documented regimes coincide with shifts in the parameters of a policy rule, with long‐term consequences for the real interest rate. Estimates imply that two‐thirds of the decline in the real interest rate since the early 1980s is attributable to regime changes in monetary policy. The model explains how infrequent changes in the stance of monetary policy can generate persistent changes in asset valuations and the equity premium.