CNN Stock Selection Using Momentum, Moving Averages, and Money Flows

Summary

This Chinese strategy discussion combines hand-built stock selection rules with a CNN classifier. It describes converting screening conditions into Boolean features so a model can learn to identify stocks expected to show short-term strength. The feature groups include returns and rankings, capitalization and valuation, turnover, money flows, volatility, technical indicators, and recent limit-up activity. Filters favor positive money flows, bullish moving-average and MACD states, a rising close, and a low that remains above the 20-day average; the discussion also excludes specially treated stocks and applies a large-order inflow screen.

For labeling, the author uses the highest price over the next three days relative to the next day’s open, arguing this captures upside missed by closing-price labels. The document reports a single-factor review in which several money-flow categories appeared useful, but gives no detailed metrics or robust out-of-sample results. It leaves rolling-window settings open to optimization and suggests refreshing features, labels, filters, and training data, so the approach remains a research proposal rather than validated evidence of profitability.

Key ideas

• The strategy encodes traditional screening rules as Boolean model features.
• Its CNN classifier seeks short-term strong stocks using technical, fundamental, and money-flow data.
• Selection filters include bullish moving averages and MACD, positive large-order inflows, and price strength.
• Labels use future highs relative to the following open to represent possible upside.
• The document gives limited factor-test claims but no detailed validation results.

Tags

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