Nonstationarity-Complexity Tradeoff in Stock Return Prediction
Published:Dec 29, 2025 16:49
•1 min read
•ArXiv
Analysis
This paper addresses a crucial challenge in financial time series prediction: the balance between model complexity and the impact of non-stationarity. It proposes a novel model selection method to overcome this tradeoff, demonstrating significant improvements in out-of-sample performance, especially during economic downturns. The economic impact, as evidenced by improved trading strategy returns, further validates the significance of the research.
Key Takeaways
- •Identifies a fundamental tradeoff between model complexity and non-stationarity in stock return prediction.
- •Proposes a novel model selection method to address this tradeoff.
- •Demonstrates significant outperformance compared to standard benchmarks, especially during recessions.
- •Shows economic impact through improved trading strategy returns.
Reference
“Our method achieves positive $R^2$ during the Gulf War recession while benchmarks are negative, and improves $R^2$ in absolute terms by at least 80bps during the 2001 recession as well as superior performance during the 2008 Financial Crisis.”