analiza aiqbench
This research applies residual learning techniques to deepen neural networks in empirical asset pricing, demonstrating that increased model depth yields superior out-of-sample Sharpe ratios compared to shallow or standard deep feedforward architectures. By preserving information from intermediate layers, the study validates model depth as a source of additional economic value and offers a scalable path toward constructing native "large asset pricing models."
Residual Learning in Empirical Asset Pricing
arXiv:2610.09613v1 Announce Type: cross Abstract: Shallow models are special cases of deep models, and deep models theoretically have the potential to outperform the shallow ones. However, the existing empirical asset pricing literature provides strong benchmarks for shallow models. Residual learning allows neural network models in asset pricing to go deeper by preserving and refining their shallow counterparts. The out-of-sample Sharpe ratio for value-weighted long-short portfolios of deep residual models (2.07) is higher than that for the corresponding shallow ones (1.92) and more than twice that of the deep feedforward models (0.89). We show that model depth is a source of additional economic value in asset pricing. Residual learning can be used to deepen other neural-network-based asset pricing models if they contain intermediate layers. Our design also provides one way to scale asset pricing models, making native "large asset pricing models" more feasible.
Abstract:Shallow models are special cases of deep models, and deep models theoretically have the potential to outperform the shallow ones. However, the existing empirical asset pricing literature provides strong benchmarks for shallow models. Residual learning allows neural network models in asset pricing to go deeper by preserving and refining their shallow counterparts. The out-of-sample Sharpe ratio for value-weighted long-short portfolios of deep residual models (2.07) is higher than that for the corresponding shallow ones (1.92) and more than twice that of the deep feedforward models (0.89). We show that model depth is a source of additional economic value in asset pricing. Residual learning can be used to deepen other neural-network-based asset pricing models if they contain intermediate layers. Our design also provides one way to scale asset pricing models, making native "large asset pricing models" more feasible.
Statistical Finance (q-fin.ST); Machine Learning (cs.LG)
arXiv:2610.09613 [q-fin.ST]
(or arXiv:2610.09613v1 [q-fin.ST] for this version)
https://doi.org/10.48550/arXiv.2610.09613 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 234 cuvinte
Subiecte conexe
DualCast: A Dual-Path Language Model for Bimodal Financial Time-Series Forecasting
arXiv · 1 oct. 2026
Agentic Empirical Asset Pricing: Methodological Foundations
arXiv · 2 sept. 2026
The Virtue of Sparsity in Complexity
arXiv · 23 sept. 2026
DisclosureBeta: A Measurement-Channel Theory for Regime-Conditioned Betas from LLM-Read Risk Disclosures
arXiv · 4 sept. 2026