arXiv：cs.LG· Dexin Peng, Xiaoyu Wang·· 4 小时前AI 评分30
残差学习让资产定价模型更深：深度残差模型样本外夏普比率达 2.07
Residual Learning in Empirical Asset Pricing
AI 导读
残差学习可让资产定价神经网络在保留并精炼浅层模型的基础上做得更深，深度残差模型的价值加权多空组合样本外夏普比率为 2.07，高于对应浅层模型的 1.92，也是深度前馈模型 0.89 的两倍以上。研究表明模型深度是资产定价中额外经济价值的来源，只要模型含中间层，该方法可用于加深其他基于神经网络的资产定价模型，并为打造原生“大型资产定价模型”提供了一种规模化路径。
正文
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.
| Comments: | 58 pages, 8 figures |
| Subjects: | Statistical Finance (q-fin.ST); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.09613 [q-fin.ST] |
| (or arXiv:2610.09613v1 [q-fin.ST] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09613 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Xiaoyu Wang [view email]
[v1]
Wed, 7 Oct 2026 07:55:38 UTC (454 KB)
来源：arXiv：cs.LG · arxiv.org