Uncertainty-Adjusted Sorting for Asset Pricing with Machine Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915704377180160 |
|---|---|
| author | Liu, Yan Luo, Ye Wang, Zigan Zhang, Xiaowei |
| author_facet | Liu, Yan Luo, Ye Wang, Zigan Zhang, Xiaowei |
| contents | Machine learning is central to empirical asset pricing, but portfolio construction still relies on point predictions and largely ignores asset-specific estimation uncertainty. We propose a simple change: sort assets using uncertainty-adjusted prediction bounds instead of point predictions alone. Across a broad set of ML models and a U.S. equity panel, this approach improves portfolio performance relative to point-prediction sorting. These gains persist even when bounds are built from partial or misspecified uncertainty information. They arise mainly from reduced volatility and are strongest for flexible machine learning models. Identification and robustness exercises show that these improvements are driven by asset-level rather than time or aggregate predictive uncertainty. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_00593 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Uncertainty-Adjusted Sorting for Asset Pricing with Machine Learning Liu, Yan Luo, Ye Wang, Zigan Zhang, Xiaowei Portfolio Management Machine Learning Machine learning is central to empirical asset pricing, but portfolio construction still relies on point predictions and largely ignores asset-specific estimation uncertainty. We propose a simple change: sort assets using uncertainty-adjusted prediction bounds instead of point predictions alone. Across a broad set of ML models and a U.S. equity panel, this approach improves portfolio performance relative to point-prediction sorting. These gains persist even when bounds are built from partial or misspecified uncertainty information. They arise mainly from reduced volatility and are strongest for flexible machine learning models. Identification and robustness exercises show that these improvements are driven by asset-level rather than time or aggregate predictive uncertainty. |
| title | Uncertainty-Adjusted Sorting for Asset Pricing with Machine Learning |
| topic | Portfolio Management Machine Learning |
| url | https://arxiv.org/abs/2601.00593 |