Reproduce “Deep Learning Enhanced Multi-Day Turnover Quantitative Trading Algorithm for Chinese A-Share Market” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Yimin Du
An innovative quantitative trading algorithm tailored for the Chinese A-share market combines deep learning techniques with established quantitative methodologies to achieve multi-day turnover. It demonstrates a 15.2% annualized return and a Sharpe Ratio of 1.87 with a 4.8% maximum drawdown over a four-year out-of-sample period, maintaining positive returns even in high volatility markets.
Key insights
- Synergistic integration of deep learning for prediction, opening signal analysis for entry timing, and adaptive risk management creates a robust trading system that effectively navigates emerging market complexities.
- Exploiting specific microstructure inefficiencies, such as Chinese A-share market's opening auction dynamics, provides a distinct alpha edge.
- Dynamic, regime-adaptive risk controls embedded across multiple modules are critical for maintaining superior performance and controlling drawdowns in highly volatile market conditions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.