Working Paper: NBER ID: w31348
Authors: David Hirshleifer; Dat Mai; Kuntara Pukthuanthong
Abstract: A war-related factor model derived from textual analysis of media news reports explains the cross section of expected stock returns. Using a semi-supervised topic model to extract discourse topics from 7,000,000 New York Times stories spanning 160 years, the war factor predicts the cross section of returns across test assets derived from both traditional and machine learning construction techniques, and spanning 138 anomalies. Our findings are consistent with assets that are good hedges for war risk receiving lower risk premia, or with assets that are more positively sensitive to war prospects being more overvalued. The return premium on the war factor is incremental to standard effects.
Keywords: war risk; expected returns; asset pricing; media discourse; disaster risk
JEL Codes: G0; G02; G1; G10; G11; G4; G41
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| war factor (H56) | expected asset returns (G12) |
| good hedges against war risk (H56) | lower risk premia (G19) |
| positively sensitive to war prospects (H56) | more overvalued (D46) |
| war factor (H56) | return premium (G22) |
| disaster risk (H84) | negative risk premium (G12) |
| war factor (H56) | variance in test assets (C52) |