Symbolic Regime Laws: Automated Discovery of Time-Varying Alpha Factor Equations via Symbolic Regression
A 2026 paper by Merlini on machine learning return prediction in equities, using symbolic search on a 1963–2024 sample: the abstract mentions alpha and leaves out a benchmark, an out-of-sample test, transaction costs, multiple testing and the size of the universe.
“Temporal stability is partial (50% of years, dynamic reestimation), consistent with the Adaptive Markets Hypothesis.”
AssetEquities
StrategyMachine learningmomentum
TechniqueSymbolic searchlinear factor model
GeographyEurope
Also stated: 1963–2024, Alpha
Missing from abstract: benchmark, out-of-sample test, 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 neighbourhoodMachine learning return prediction by year
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 | |
|---|---|---|---|---|---|
| Spatiotemporal Signals in Residuals: A Two-Stage Boosting Graph Neural Network for Stock Return Prediction by Liu et al. | 2026 | ||||
| Empirical Asset Pricing via Machine Learning: Evidence from Indian Equity Markets by Sharma | 2026 | ||||
| Cross-Sectional Return Prediction Using Machine Learning: A Practitioner Pipeline by Lama | 2026 | ||||
| Feature Scope and Cross-Sectional Return Prediction: Evidence from US Large-Cap Equities by Rocchi | 2026 | ||||
| The Geometry of Alpha Manifold Learning, Topological Data Analysis, and Non-Linear Factor Structures in Global Equity Markets by Kholia | 2026 |