Paper: arXiv 2507.07107

Authors: Yimin Du

Abstract

This paper presents a comprehensive machine learning framework for quantitative trading that achieves superior risk-adjusted returns through systematic factor engineering, real-time computation optimization, and cross-sectional portfolio construction. Our approach integrates multi-factor alpha discovery with bias correction techniques, leveraging PyTorch-accelerated factor computation and advanced portfolio optimization. The system processes 500-1000 factors derived from open-source alpha101 extensions and proprietary market microstructure signals. Key innovations include tensor-based factor computation acceleration, geometric Brownian motion data augmentation, and cross-sectional neutralization strategies. Empirical validation on Chinese A-share markets (2010-2024) demonstrates annualized returns of $20%$ with Sharpe ratios exceeding 2.0, significantly outperforming traditional approaches. Our analysis reveals the critical importance of bias correction in factor construction and the substantial impact of cross-sectional portfolio optimization on strategy performance. Code and experimental implementations are available at: https://github.com/initial-d/ml-quant-trading

Complexity vs Empirical Score

  • Math Complexity: 8.0/10
  • Empirical Rigor: 9.0/10
  • Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper presents advanced mathematical frameworks including tensor operations, geometric Brownian motion augmentation, and complex portfolio optimization formulations, while demonstrating high empirical rigor with detailed performance metrics, backtest data over a 14-year period, and publicly available code implementations.

Research Flowchart

  flowchart TD
  A["Research Goal: ML-Enhanced Quant Trading with<br>Factor Optimization & Bias Correction"] --> B["Data & Inputs<br>1000+ Factors: Alpha101 + Microstructure<br>Chinese A-Shares (2010-2024)"]
  B --> C["Methodology: Tensor-Accelerated<br>Factor Computation via PyTorch"]
  C --> D["Processing: Cross-Sectional<br>Portfolio Optimization & Neutralization"]
  D --> E["Innovation: Bias Correction<br>+ Geometric Brownian Motion Augmentation"]
  E --> F["Outcomes: 20% Annualized Return<br>Sharpe Ratio > 2.0"]
  F --> G["Key Finding: Bias Correction &<br>Portfolio Optimization Critical to Performance"]

Cited References (76)

  1. Empirical asset pricing via machine learning (2020)
  2. Deep learning in asset pricing (2024)
  3. Dissecting characteristics nonparametrically (2020)
  4. Capital asset prices: A theory of market equilibrium (1964)
  5. The valuation of risk assets (1965)
  6. The arbitrage theory of capital asset pricing (1976)
  7. Common risk factors in the returns on stocks and bonds (1993)
  8. A five-factor asset pricing model (2015)
and 68 more
  1. On persistence in mutual fund performance (1997)
  2. Returns to buying winners and selling losers (1993)
  3. … and the cross-section of expected returns (2016)
  4. The characteristics that provide independent information about average US monthly stock returns (2017)
  5. 101 formulaic alphas (2016)
  6. Characteristics are covariances: A unified model of risk and return (2019)
  7. Taming the factor zoo: A test of new factors (2020)
  8. Does academic research destroy stock return predictability? (2016)
  9. Bond risk premiums with machine learning (2021)
  10. Does it pay to follow anomalies research? Machine learning approach with international evidence (2021)
  11. Machine learning in the Chinese stock market (2022)
  12. Deep learning for predicting asset returns (2023)
  13. Factor investing in Chinese A-share markets (2024)
  14. XGBoost : A scalable tree boosting system (2016)
  15. LightGBM : A highly efficient gradient boosting decision tree (2017)
  16. CatBoost : Unbiased boosting with categorical features (2018)
  17. Long short-term memory (1997)
  18. Deep learning with long short-term memory networks for financial market predictions (2018)
  19. Attention is all you need (2017)
  20. Hierarchical multi-scale Gaussian transformer for stock movement prediction (2020)
  21. Enhancing the locality and breaking the memory bottleneck of transformer on time series forecasting (2019)
  22. Stock movement prediction from tweets and historical prices (2021)
  23. Stock selection via spatiotemporal hypergraph attention network (2021)
  24. Factorvae: A probabilistic dynamic factor model based on variational autoencoder for predicting cross-sectional stock returns (2022)
  25. Qlib: An AI-oriented quantitative investment platform (2020) — link
  26. Open source cross-sectional asset pricing (2022)
  27. Advances in Financial Machine Learning (2018)
  28. The deflated S harpe ratio (2014)
  29. Reports of value’s death may be greatly exaggerated (2019)
  30. Survivorship bias and mutual fund performance (1996)
  31. The delisting bias in CRSP data (1997)
  32. A reality check for data snooping (2000)
  33. Stepwise multiple testing as formalized data snooping (2005)
  34. Price limit performance: Evidence from the Tokyo stock exchange (2013)
  35. Price limits and stock market volatility in China (2018)
  36. Price limit changes and market quality in the Chinese stock market (2005)
  37. Portfolio selection (1952)
  38. Active Portfolio Management (2000)
  39. Asset Management: A Systematic Approach to Factor Investing (2014)
  40. A well-conditioned estimator for large-dimensional covariance matrices (2004)
  41. Nonlinear shrinkage of the covariance matrix for portfolio selection (2017)
  42. Analytical nonlinear shrinkage of large-dimensional covariance matrices (2020)
  43. High dimensional covariance matrix estimation using a factor model (2008)
  44. Optimal versus naive diversification: How inefficient is the 1/N portfolio strategy? (2009)
  45. Machine learning and portfolio optimization (2018)
  46. Deep learning for portfolio optimization (2020)
  47. AlphaPortfolio: Direct construction through deep reinforcement learning and interpretable AI (2021)
  48. Deep portfolio optimization via distributional prediction of residual factors (2021)
  49. The pricing of options and corporate liabilities (1973)
  50. The jackknife and the bootstrap for general stationary observations (1989)
  51. The stationary bootstrap (1994)
  52. Resampling Methods for Dependent Data (2003)
  53. Modeling financial time-series with generative adversarial networks (2019)
  54. Quant GAN s: Deep generation of financial time series (2020)
  55. Time series simulation by conditional generative adversarial net (2019) — link
  56. Data augmentation approaches in natural language processing (2022)
  57. On the constrained time-series generation problem (2024)
  58. CVXPY : A P ython-embedded modeling language for convex optimization (2016)
  59. Conic optimization via operator splitting and homogeneous self-dual embedding (2016)
  60. Scikit-learn: Machine learning in P ython (2011)
  61. Adam: A method for stochastic optimization (2015)
  62. MOSEK Optimization Toolbox (2023) — link
  63. Types and Programming Languages (2002)
  64. Monads for functional programming (1995)
  65. A B ayesian approach to real estate assessment (1975)
  66. Stock price prediction via discovering multi-frequency trading patterns (2017)
  67. 60 years of portfolio optimization: Practical challenges and current trends (2014)
  68. Temporal relational ranking for stock prediction (2019)

0 of 76 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2518 linked papers.