Working Paper: NBER ID: w31583
Authors: Turan G. Bali; Bryan T. Kelly; Mathis Mrke; Jamil Rahman
Abstract: We propose a statistical model of heterogeneous beliefs where investors are represented as different machine learning model specifications. Investors form return forecasts from their individual models using common data inputs. We measure disagreement as forecast dispersion across investor-models (MFD). Our measure aligns with analyst forecast disagreement but more powerfully predicts returns. We document a large and robust association between belief disagreement and future returns. A decile spread portfolio that sells stocks with high disagreement and buys stocks with low disagreement earns a value-weighted return of 14% per year. Further analyses suggest MFD-alpha is mispricing induced by short-sale costs and limits-to-arbitrage.
Keywords: belief disagreement; machine learning; future returns; forecasting; financial markets
JEL Codes: C15; C4; C45; C58; G1; G10; G17; G4; G40
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| machine forecast disagreement (MFD) (E17) | future stock returns (G17) |
| high machine forecast disagreement (MFD) (C53) | lower future returns (G12) |
| shortsale constraints (G33) | overpricing of high MFD stocks (G19) |
| shortsale costs (G33) | influence on MFD and returns (F23) |