AI-Ranked China A-Shares with MACD Timing and Risk Controls

Summary

This strategy combines model-based stock ranking with trend filters for a selected universe of China A-shares drawn from the CSI 150 and related large-cap core-asset stocks. It aims to rank candidates for potential five-day strength, then apply timing conditions based on MACD and price relative to a 25-day average. Inputs include turnover, large-order net money flow, and a price-volume feature; an additional filter selects stocks with positive recent relative returns and a high 30-day relative-return rank.

For market-level risk control, the method monitors a MACD crossover on the CSI 300. It describes taking profits at a 60% gain and cutting losses at a 5% decline, while holding five stocks with a five-day rotation and a 10% maximum allocation per name. These are reported design choices, not demonstrated results: the document supplies no performance series, benchmark comparison, or validation details. It also does not explain model construction or address survivorship, transaction costs, and other implementation risks.

Key ideas

• The approach combines AI-based ranking with signal-based timing to select stocks from a restricted China A-share universe.
• Its timing rules use MACD conditions and require price to remain above a 25-day moving average.
• Turnover, large-order money flow, and relative returns contribute to screening and ranking.
• A CSI 300 MACD condition serves as the stated market-level risk trigger.
• The portfolio design specifies five holdings, five-day rotation, and a 10% per-stock allocation cap.
• The article describes the strategy but provides no backtest or validation evidence.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.