Stock Ranking with Market and Trailing Stop Rules

Summary

This brief strategy outline combines a machine-learning stock ranking model with market-level and individual-stock exit rules. It proposes training a StockRanker on price, volume, and valuation factors, then applying three conditions to the CSI 300 index as a broad-market stop: three consecutive down days, a five-day average below the 30-day average, and a decline of 10% from the prior 30-day high. The market stop is triggered only when all three conditions hold together.

At the security level, the outline proposes selling when price falls 10% below its highest level since entry, a trailing stop intended to limit losses or protect gains. The document describes the rules but supplies no code, model specification, factor definitions, backtest, performance evidence, or details on execution and transaction costs. The thresholds are therefore presented as a strategy concept rather than validated settings, and the results would depend on implementation and testing.

Key ideas

• The proposed stock selection method trains a ranking model on price, volume, and valuation factors.
• A broad-market stop requires three simultaneous CSI 300 conditions involving recent returns, moving averages, and drawdown from a recent high.
• Individual holdings use a trailing stop set below the highest price since entry.
• The document gives no backtest, factor definitions, model details, or performance evidence.

Tags

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