Text-implied uncertainty in 10-K filings: Do investors get the message?
Oliver Budras et al.
What the paper says
We investigate the role of text-implied uncertainty in the cross-section of stock returns. We employ word embeddings to derive an uncertainty dictionary from 10-K annual company filings. Stocks in the highest uncertainty quintile generate a 0.281% higher monthly return compared to stocks in the lowest quintile. This outperformance survives risk-adjustment. Furthermore, uncertainty is negatively related to filing period abnormal returns. This information is priced within one day after filing. High-uncertainty companies have lower return-on-assets, unexpected earnings, and are less likely to increase dividends in the subsequent fiscal year. Uncertainty-averse investors demand a premium for holding high uncertainty stocks. • We use GloVe embeddings to derive an uncertainty metric in 10-K filings of companies. • Our uncertainty metric is orthogonalized towards risk and sentiment. • Uncertainty is priced with a significantly positive risk premium in the cross-section of stocks. • Filing period returns of high uncertainty stocks decrease within one day after the filing. • Finally, uncertainty is negatively related to future firm fundamentals.
Evidence weight
Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40
| F · citation impact | 0.50 × 0.4 = 0.20 |
| M · momentum | 0.50 × 0.15 = 0.07 |
| V · venue signal | 0.50 × 0.05 = 0.03 |
| R · text relevance † | 0.50 × 0.4 = 0.20 |
† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.