arXiv：cs.LG· Zhuohan Wang, Carmine Ventre·· 5 小时前AI 评分35
FactorBench：面向组合的自动化因子挖掘基准
FactorBench: A Portfolio-Aware Benchmark for Automated Factor Mining
AI 导读
FactorBench 是一个面向组合的自动化因子挖掘基准，对比了 9 种自动化挖掘方法在 5 个股票市场产出的约 5000 个因子。
正文
Abstract:Factor mining seeks to discover signals from financial data that predict future asset returns and guide portfolio construction. Automated factor mining now spans genetic programming, reinforcement learning, generative models, and large language model agents. Yet it remains unclear whether advances across these paradigms yield more generalizable, distinct, and economically useful financial signals. We introduce FactorBench, a portfolio-aware benchmark comparing roughly five thousand mined factors from nine automated mining methods across five equity markets. A shared data and evaluation contract supports both symbolic expressions and executable Python factors, connecting heterogeneous discovery algorithms to common signal combination and portfolio construction procedures. FactorBench traces the outputs of mining systems across three levels: factor validity, temporal generalization, and predictiveness beyond measured risk and style exposures; within- and across-method pool distinctness, including similarity to the benchmark Alpha101; and composite-signal quality and after-cost long-only and long--short portfolio performance. After systematically assessing whether advances in factor mining translate into signal quality and portfolio performance, FactorBench finds that no paradigm consistently dominates.
| Comments: | 30 pages, 21 figures, 8 tables |
| Subjects: | Portfolio Management (q-fin.PM); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.06947 [q-fin.PM] |
| (or arXiv:2610.06947v1 [q-fin.PM] for this version) | |
| https://doi.org/10.48550/arXiv.2610.06947 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhuohan Wang [view email]
[v1]
Sat, 3 Oct 2026 10:57:37 UTC (15,731 KB)
来源：arXiv：cs.LG · arxiv.org