Working Paper: CEPR ID: DP15003
Authors: Francesco Bianchi; Sydney Ludvigson; Sai Ma
Abstract: 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.
Keywords: beliefs; biases; machine learning; expectations
JEL Codes: E7; E27; E32; E17; G4
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Belief distortions (D83) | Systematic expectational errors (C51) |
| Overweighting own beliefs (D91) | Systematic expectational errors (C51) |
| Survey forecasts (G17) | Mean squared forecast errors (C53) |
| Machine learning processing (C45) | Mean squared forecast errors (C53) |
| Professional forecasters (F37) | Systematic expectational errors (C51) |
| Machine learning model (C45) | Belief distortions (D83) |
| Cyclical shocks (E32) | Biases in forecasts (C53) |
| Machine learning model efficiency (C52) | Accuracy of forecasts (C53) |