Turning Intraday Signals into Monthly Equity Factors for Index Enhancement

Summary

This report summary presents a framework for converting intraday or other medium-to-high-frequency signals into factors intended to predict returns over a monthly horizon. It separates factor construction into signal generation, aggregation from intraday observations to daily values, and a further transformation from daily values to monthly factors over a chosen rolling window. The method is expressed as a reusable template for producing many price-and-volume factors, rather than as one fixed signal.

The summary reports that ten such factors, after controlling for common price-volume styles, had an average information coefficient of 4.0% and an IC information ratio of 3.16, with reported long-short and long-only returns of 13.6% and 6.8%. Combining the factors with traditional fundamentals in monthly index-enhancement portfolios reportedly improved results for the CSI 500 and CSI 300 over the period beginning in 2011. These are report-reported historical results; the supplied text lacks full methodology, implementation details, and robustness tests, so it is insufficient to assess costs, data bias, or out-of-sample performance.

Key ideas

• Higher-frequency signals may have limited persistence, so aggregation can help align them with longer prediction horizons.
• The proposed factor process has signal generation, daily aggregation, and monthly transformation stages.
• The framework was used to build ten factors with monthly prediction horizons.
• The summary reports historical factor and index-enhancement results, but does not provide enough detail to assess their robustness.

Tags

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