AlphaPROBE: Alpha Mining via Principled Retrieval and On-graph biased evolution

2026-02-12

AI Summary

This work addresses the limitations of existing automated alpha factor mining methods, which often suffer from search redundancy and insufficient diversity due to a lack of global structural awareness. To overcome this, the authors propose a novel DAG-aware factor evolution framework that models the factor pool as a dynamic, interconnected directed acyclic graph (DAG) ecosystem. The framework jointly optimizes a Bayesian posterior retriever and an ancestor-path-aware generator, enabling a balanced exploration–exploitation trade-off guided by global topological information. Extensive experiments on three Chinese stock market datasets demonstrate that the proposed method significantly outperforms eight baseline models in terms of predictive accuracy, return stability, and training efficiency.

Technology Category

• Data Mining & Knowledge Management: Intelligent Query Processing
• Machine Learning: Probabilistic Circuits and Graphical Models
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Extracting signals through alpha factor mining is a fundamental challenge in quantitative finance. Existing automated methods primarily follow two paradigms: Decoupled Factor Generation, which treats factor discovery as isolated events, and Iterative Factor Evolution, which focuses on local parent-child refinements. However, both paradigms lack a global structural view, often treating factor pools as unstructured collections or fragmented chains, which leads to redundant search and limited diversity. To address these limitations, we introduce AlphaPROBE (Alpha Mining via Principled Retrieval and On-graph Biased Evolution), a framework that reframes alpha mining as the strategic navigation of a Directed Acyclic Graph (DAG). By modeling factors as nodes and evolutionary links as edges, AlphaPROBE treats the factor pool as a dynamic, interconnected ecosystem. The framework consists of two core components: a Bayesian Factor Retriever that identifies high-potential seeds by balancing exploitation and exploration through a posterior probability model, and a DAG-aware Factor Generator that leverages the full ancestral trace of factors to produce context-aware, nonredundant optimizations. Extensive experiments on three major Chinese stock market datasets against 8 competitive baselines demonstrate that AlphaPROBE significantly gains enhanced performance in predictive accuracy, return stability and training efficiency. Our results confirm that leveraging global evolutionary topology is essential for efficient and robust automated alpha discovery. We have open-sourced our implementation at https://github.com/gta0804/AlphaPROBE.

Problem

• alpha mining
• factor generation
• Directed Acyclic Graph
• quantitative finance
• evolutionary topology

Innovation

• Alpha Mining
• Directed Acyclic Graph (DAG)
• Bayesian Retrieval
• On-graph Evolution
• Factor Generation