Comparing Traditional and AI Small-Cap Equity Strategies

Summary

The article compares two Chinese equity approaches built around market capitalization. The traditional strategy selects the smallest-cap stocks for a portfolio. The AI version uses a StockRanker ranking model with market capitalization as its sole feature. Both approaches are described as backtested over the same historical period, allowing the author to compare returns, drawdowns, volatility, and Sharpe ratio.

The article reports that the AI approach had higher cumulative returns and a higher Sharpe ratio in that sample, while also experiencing a somewhat larger maximum drawdown; return volatility was described as similar. The traditional approach also produced a positive result over the period. These figures are historical backtest claims, not evidence of future performance. The comparison is limited by its short sample, single factor, and lack of detail here on trading costs, portfolio construction, or validation outside the test period. The author notes that crowded exposure to small-cap stocks may create strategy similarity, and suggests that AI workflows can incorporate additional domain-informed features. The article also states that its implementation is outdated for the current platform.

Key ideas

• The traditional strategy forms a portfolio from the smallest-cap stocks.
• The AI strategy uses a ranking model with market capitalization as its only feature.
• In the reported backtest, the AI approach had higher return and Sharpe ratio but a slightly larger maximum drawdown.
• The comparison covers a limited historical sample and does not establish future performance.
• The article flags crowding in small-cap exposure and says its platform implementation is outdated.

Tags

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