AI-Ranked CSI 150 Stock Selection with Trend Timing and Risk Controls

Summary

This strategy combines model-based stock ranking with technical timing. It starts from a manually defined CSI 150-related universe, then ranks candidates using an AI prediction score and volume, turnover, and large-order money-flow factors. Timing filters include MACD conditions, price holding above a 25-day average, and positive recent relative performance versus a benchmark. The strategy seeks stocks with stronger short- and medium-term relative trends, then holds a concentrated portfolio with a fixed rotation schedule and per-stock exposure cap.

Risk controls include a CSI 300 MACD trigger and stated take-profit and stop-loss thresholds. The author contrasts this hybrid of stock selection and signal timing with value-only and signal-only approaches, and explains the intended role of each filter. Although a backtest section is named, no results or statistics are supplied in the text. The model's predictions, factor behavior, universe construction, costs, and historical robustness therefore remain unverified; the described rules are not evidence of future returns.

Key ideas

• The strategy ranks stocks within a CSI 150-related universe using an AI prediction score and market factors.
• MACD, a 25-day moving average, and relative returns provide timing and trend filters.
• A benchmark MACD condition and stock-level profit and loss thresholds define risk controls.
• The portfolio is concentrated, with a fixed rotation schedule and a cap on individual positions.
• The supplied text does not report backtest results or establish the strategy's robustness.

Tags

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