Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

FactorEngine: A Program-level Knowledge-Infused Factor Mining Framework for Quantitative Investment

Qinhong Lin, Ruitao Feng, Yinglun Feng, Zhenxin Huang, Yukun Chen, Zhongliang Yang, Linna Zhou, Binjie Fei, Jiaqi Liu, Yu Li

Abstract

We study alpha factor mining, the automated discovery of predictive signals from noisy, non-stationary market data-under a practical requirement that mined factors be directly executable and auditable, and that the discovery process remain computationally tractable at scale. Existing symbolic approaches are limited by bounded expressiveness, while neural forecasters often trade interpretability for performance and remain vulnerable to regime shifts and overfitting. We introduce FactorEngine (FE), a program-level factor discovery framework that casts factors as Turing-complete code and improves both effectiveness and efficiency via three separations: (i) logic revision vs. parameter optimization, (ii) LLM-guided directional search vs. Bayesian hyperparameter search, and (iii) LLM usage vs. local computation. FE further incorporates a knowledge-infused bootstrapping module that transforms unstructured financial reports into executable factor programs through a closed-loop multi-agent extraction-verification-code-generation pipeline, and an experience knowledge base that supports trajectory-aware refinement (including learning from failures). Across extensive backtests on real-world OHLCV data, FE produces factors with substantially stronger predictive stability and portfolio impact-for example, higher IC/ICIR (and Rank IC/ICIR) and improved AR/Sharpe, than baseline methods, achieving state-of-the-art predictive and portfolio performance.

FactorEngine: A Program-level Knowledge-Infused Factor Mining Framework for Quantitative Investment

Abstract

We study alpha factor mining, the automated discovery of predictive signals from noisy, non-stationary market data-under a practical requirement that mined factors be directly executable and auditable, and that the discovery process remain computationally tractable at scale. Existing symbolic approaches are limited by bounded expressiveness, while neural forecasters often trade interpretability for performance and remain vulnerable to regime shifts and overfitting. We introduce FactorEngine (FE), a program-level factor discovery framework that casts factors as Turing-complete code and improves both effectiveness and efficiency via three separations: (i) logic revision vs. parameter optimization, (ii) LLM-guided directional search vs. Bayesian hyperparameter search, and (iii) LLM usage vs. local computation. FE further incorporates a knowledge-infused bootstrapping module that transforms unstructured financial reports into executable factor programs through a closed-loop multi-agent extraction-verification-code-generation pipeline, and an experience knowledge base that supports trajectory-aware refinement (including learning from failures). Across extensive backtests on real-world OHLCV data, FE produces factors with substantially stronger predictive stability and portfolio impact-for example, higher IC/ICIR (and Rank IC/ICIR) and improved AR/Sharpe, than baseline methods, achieving state-of-the-art predictive and portfolio performance.
Paper Structure (37 sections, 14 equations, 5 figures, 3 tables)

This paper contains 37 sections, 14 equations, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Traditional Alpha Mining
  4. LLM in Finance
  5. Problem Formulation
  6. Methodology
  7. Bootstrapping Module
  8. Evolution Module
  9. Integration Module
  10. Experiment Setup
  11. Results Analysis
  12. Main Result
  13. Factor Diversity Analysis
  14. Alpha Decay Analysis
  15. Token Efficiency and Executability
  16. ...and 22 more sections

Figures (5)

  • Figure 1: Overview of FactorEngine (FE).Left: Bootstrapping extracts factor ideas and converts pseudocode into executable Python to seed a knowledge-infused pool. Center: Evolution performs macro--micro co-evolution: LLM agents propose macro mutations guided by chains of experience, and Bayesian search conducts micro-level parameter tuning with fast validation and feedback updates. Right: Integration selects elite factors to train models for backtesting, producing portfolio-level feedback.
  • Figure 2: Overview of the Bootstrapping module.
  • Figure 3: (Left) Cumulative excess return comparison in the CSI300 market. (Middle) Cumulative excess return comparison in the CSI500 market. (Right) Visualization of factor correlation structure of three agent-based methods based on MDS.
  • Figure 4: Yearly IC and Rank IC comparisons in the CSI300 (Left) and CSI500 markets (Middle). Mean IC and Rank IC between the top 10% factors and future returns at T+N on the CSI300 market across three experimental settings (Right).
  • Figure 5: Left:Effect of Bayesian micro-search. Bayesian parameter search (bay_avg) yields higher final performance and a faster improvement trajectory than that without Bayesian tuning (no_bay_avg). Right: Comparison of three methods evolved using the GPT-4o and Gemini-2.5-flash-lite models as backbone agents.