We propose a statistical model of heterogeneous beliefs wherein 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 13% per year. Further analyses suggest MFD-alpha is mispricing induced by short-sale costs and limits-to-arbitrage. (JEL G10, G11, G12, G14)

We document that foreign economic policy uncertainty (EPU^F) has significant incremental predictive power for excess U.S. stock returns in the presence of domestic EPU, both in aggregate and for returns of portfolios constructed on firm characteristics, for 6 to 12-months-ahead horizons. We find that EPU^F shocks primarily transmit to equity prices through cash flow news rather than the discount rate news channel. We examine whether responses of select macro-financial variables to an adverse EPU^F shock are consistent with this transmission mechanism. Corporate investment outlays, payouts, and aggregate credit demand decline in response to such a shock.