Feature-Selection Risk
“Empirically, I find that using an estimation strategy that explicitly accounts for traders’ joint inference problem increases out-of-sample return predictability at the monthly horizon by 144.3%, from R2 = 3.65% to R2 = 9.35%, suggesting that this feature-selection problem is important to real-world traders.”
StrategyEvent-driven strategiesmachine learning
FrequencyMonthly
InputsFundamentals
Also stated: out-of-sample test
Missing from abstract: benchmark, costs, multiple testing, universe
Institutional-grade audit of this strategy.
£5 — Request the audit- Audit of the paper claims accounting for costs, luck, crises, originality, geography, etc.
- Reproduction code integratable into Bloomberg, IBKR, etc.
- Bias-free datasets for backtesting included
- Delivered in 2 working days
The paper's neighbourhoodEvent-driven strategies by year
FamilyEvent-driven strategies52Momentum and trend following289Factor investing240Machine learning return prediction15318 more · 950
AssetEquities40
The family is counted across the whole universe. Asset, method and authors are counted inside the family.
| Similar papers | citation | same method | same asset | same authors | |
|---|---|---|---|---|---|
| Firm Characteristics and Empirical Factor Models: A Model-Mining Experiment by Kogan and Tian | 2012 | ||||
| Firm Characteristics and the Cross-Sectional Variation in Post-Earnings Announcement Drift by DiPasquale | 2026 | ||||
| Buy and Fold by Scherer and Steliaros | 2026 | ||||
| Listening to the Tape Does Earnings Press-Release Language Predict Post-Announcement Returns? by Nag | 2026 | ||||
| When Early Reporters Are Late: Reporting Delay Decomposition, Analyst Disagreement, and Return Predictability by C | 2026 |