Paper: arXiv 2611.04555

Authors: Zhan-He Wang, Zi-Yang Lang, Yi-Yang Li, Qing-Yu Lan, Yun-Song Piao

Abstract

Discovering predictive alpha factors from noisy financial data is a fundamental yet challenging problem in quantitative finance. LLM-driven formulaic alpha mining offers an attractive paradigm by combining interpretable symbolic expressions with iterative generation and refinement guided by quantitative feedback. However, existing generation-centric and tree-based search strategies primarily organize factors through generation lineage, leaving structural and statistical relationships across search branches underutilized. Consequently, information remains localized along parent–child trajectories, which can confine exploration to redundant regions. Moreover, effective factor discovery must account for multiple distinct objectives that cannot be adequately captured by a single search criterion. We introduce CosmosAlpha, a graph-based LLM factor-mining framework that represents discovered factors as a multi-relational graph encoding generation lineage, expression-structure similarity, and cross-sectional exposure correlation. A Graph Flow mechanism propagates search utilities across the graph, allowing each factor to be assessed using relational evidence from nearby factors rather than in isolation. Pareto-guided selection jointly considers quality, fertility and diversity, explicitly modeling their trade-offs within a multi-objective search framework. Across CSI 300 and CSI 500, CosmosAlpha-Graph achieves the best mean rank over seven predictive and portfolio metrics and outperforms its controlled CosmosAlpha-MCTS counterpart on every reported metric, showing a consistent advantage for relational graph search in LLM-driven factor mining. The source code is available at https://github.com/wzhmtldswz/CosmosAlpha

Complexity vs Empirical Score

  • Math Complexity: 7.5/10
  • Empirical Rigor: 6.0/10 (capped from 8.0: transaction costs not modelled; see penalty flags)
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper introduces a novel graph-based LLM framework for alpha mining, demonstrating strong empirical performance across multiple metrics and datasets. The methodology is well-articulated, and the provision of source code enhances reproducibility.

Research Flowchart

  flowchart TD
    A[Research Goal: Discover Predictive Alpha Factors from Noisy Financial Data] --> B{LLM-Driven Formulaic Alpha Mining};
    B --> C[Methodology: CosmosAlpha Framework];
    C --> D{Multi-Relational Graph: Lineage, Expression Similarity, Exposure Correlation};
    D --> E[Computational Process: Graph Flow Mechanism + Pareto-Guided Selection];
    E --> F[Data/Inputs: CSI 300 & CSI 500 Equities Data];
    F --> G[Key Findings: Best Mean Rank over 7 Metrics, Outperforms MCTS];
    G --> H[Outcome: Improved Alpha Factor Discovery in Quantitative Finance];