When Alpha Breaks: Two-Level Uncertainty for Safe Deployment of Cross-Sectional Stock Rankers

Computer Science > Artificial Intelligence [Submitted on 24 Feb 2026] When Alpha Breaks: Two-Level Uncertainty for Safe Deployment of Cross-Sectional Stock Rankers Ursina Sanderink Cross-sectional ranking models are often deployed as if point predictions were sufficient: the model outputs scores and the portfolio follows the induced ordering. Under non-stationarity, rankers can fail during regime shifts. In the AI Stock Forecaster, a LightGBM ranker performs well overall at a 20-day horizon, yet the 2024 holdout coincides with an AI thematic rally and sector rotation that breaks the signal at longer horizons and weakens 20d. This motivates treating deployment as two decisions: (i) whether the strategy should trade at all, and (ii) how to control risk within active trades. We adapt Direct Epistemic Uncertainty Prediction (DEUP) to ranking by predicting rank displacement and defining an epistemic uncertainty signal ehat relative to a point-in-time (PIT-safe) baseline. Empirically, ehat is structurally coupled with signal strength (median correlation between ehat and absolute score is about 0.6 across 1,865 dates), so inverse-uncertainty sizing de-levers the strongest signals and degrades performance. To address this, we propose a two-level deployment policy: a strategy-level regime-trust gate G(t) that decides whether to trade (AUROC around 0.72 overall and 0.75 in FINAL) and a position-level epistemic tail-risk cap that reduces exposure only for the most uncertain predictions. The operational policy, trade only when G(t) is at least 0.2, apply volatility sizing on active dates, and cap the top epistemic tail, improves risk-adjusted performance in the 20d policy comparison and indicates DEUP adds value mainly as a tail-risk guard rather than a continuous sizing denominator. Comments: 34 pages, 14 tables. Cross-sectional equity ranking; uncertainty-based abstention and tail-risk capping under regime shifts Subjects: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Portfolio Management (q-fin.PM) Cite as: arXiv:2603.13252 [cs.AI]   (or arXiv:2603.13252v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.13252 Focus to learn more Submission history From: Ursina Sanderink [view email] [v1] Tue, 24 Feb 2026 14:02:24 UTC (40 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-03 Change to browse by: cs cs.LG q-fin q-fin.PM References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)