English

Alpha Discovery via Grammar-Guided Learning and Search

Computational Finance 2026-01-30 v1 Artificial Intelligence Machine Learning

Abstract

Automatically discovering formulaic alpha factors is a central problem in quantitative finance. Existing methods often ignore syntactic and semantic constraints, relying on exhaustive search over unstructured and unbounded spaces. We present AlphaCFG, a grammar-based framework for defining and discovering alpha factors that are syntactically valid, financially interpretable, and computationally efficient. AlphaCFG uses an alpha-oriented context-free grammar to define a tree-structured, size-controlled search space, and formulates alpha discovery as a tree-structured linguistic Markov decision process, which is then solved using a grammar-aware Monte Carlo Tree Search guided by syntax-sensitive value and policy networks. Experiments on Chinese and U.S. stock market datasets show that AlphaCFG outperforms state-of-the-art baselines in both search efficiency and trading profitability. Beyond trading strategies, AlphaCFG serves as a general framework for symbolic factor discovery and refinement across quantitative finance, including asset pricing and portfolio construction.

Keywords

Cite

@article{arxiv.2601.22119,
  title  = {Alpha Discovery via Grammar-Guided Learning and Search},
  author = {Han Yang and Dong Hao and Zhuohan Wang and Qi Shi and Xingtong Li},
  journal= {arXiv preprint arXiv:2601.22119},
  year   = {2026}
}

Comments

24 pages, 10 figures

R2 v1 2026-07-01T09:26:24.260Z