AI-Ranked China A-Share Momentum Strategy with MACD Timing and Risk Controls
Summary
The strategy combines model-based stock ranking with trend and timing filters for a selected universe of China A-shares. The author describes ranking stocks by predicted prospects, then screening for recent relative strength, liquidity, large-order money flow, and price behavior around a 25-day moving average. MACD conditions provide additional entry timing, while a broad-market MACD signal is used as a risk trigger. The intended style blends fundamental-oriented candidate selection with shorter-term trend following.
The portfolio description specifies five holdings, a five-day rotation period, and a per-stock capital cap, along with fixed profit-taking and loss-cutting thresholds. The write-up explains the logic and cites historical strategy results only as a section heading; it does not include the actual performance figures or enough backtest detail to assess robustness. It also does not fully specify model training, validation, transaction costs, or how factors are constructed. The approach is therefore a strategy sketch rather than evidence that the model or rules will generalize beyond the described research setting.
Key ideas
- The strategy ranks a restricted China A-share universe with an AI model and applies technical timing filters.
- Relative performance over short and longer windows is used to identify stronger stocks.
- Liquidity and large-order money-flow factors are included in stock selection.
- MACD conditions guide entries and provide a broad-market risk signal.
- The described portfolio uses five holdings, rotates on a five-day schedule, and limits exposure per stock.
- The document omits detailed backtest results and key model-validation information.
Tags
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.