Improving ROE Stock Selection with Earnings Time-Series Features

Summary

This report summary describes a method for improving return on equity as a stock-selection factor. Starting from quarterly ROE, it derives four features from its time series: year-over-year earnings comparison, stability, persistence, and growth. The features are combined in stages to build a stronger profitability signal, with the broader method presented as applicable to other financial statement factors.

The summary reports a mean information coefficient of 5.12%, annualized ICIR of 2.97, and positive monthly IC results in 78.68% of months. In decile long-short tests, it reports annualized hedged returns and information ratios for the broad market, CSI 300, and CSI 500 universes. It says the unmodified ROE factor did not show significant excess-return ability. The evidence is historical backtesting only; the source warns that future performance may differ or the model may cease to work. Detailed construction and test design are referenced but not included in the supplied text.

Key ideas

• Quarterly ROE can be decomposed into year-over-year, stability, persistence, and growth features.
• Combining complementary time-series features is proposed as a way to strengthen profitability-based stock selection.
• The supplied summary reports positive factor and long-short backtest results across several Chinese equity universes.
• The reported evidence is historical and does not establish that the factor will work in future markets.

Tags

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