AI-Ranked China Securities 150 Stocks with MACD and Trend Filters

Summary

This strategy combines machine-learning stock ranking with trend-based entry filters for a manually selected pool of China Securities 150 constituents. The pool emphasizes larger, liquid companies, often described as core or sector leaders. A model scores and ranks candidates for the potential of a strong move over the next five trading days, while simple timing rules seek to confirm momentum: MACD measures favor positive momentum, price must remain above its 25-day average, and the MACD signal measure must exceed a threshold. The described features include turnover, large-order net money flow, and a price-volume measure.

The author presents the approach as a blend of longer-term stock selection and shorter-term signal timing, arguing that restricting the universe can reduce noise. The article reports no backtest results, validation design, or realized returns. It gives little detail about model training, feature construction, portfolio weights, trading costs, or risk controls, and notes that signal strategies can lose gains when market style shifts. Its claims about factor quality are not substantiated with evidence in the text.

Key ideas

• The strategy ranks a restricted universe of China Securities 150 stocks with an AI model.
• MACD conditions and a close above the 25-day average act as entry filters.
• Turnover, large-order money flow, and price-volume data are described as model features.
• The article does not provide backtest results or sufficient model and portfolio details to evaluate performance.

Tags

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