Improving Multi-Factor Equity Universes with Tradability and Quality Filters

Summary

The report summary presents a two-layer framework for improving the stock universe used in multi-factor strategies. Rigid filters aim to ensure that securities are tradable, while flexible filters seek to improve universe quality. The flexible layer addresses both factor-related risks and event-related risks, treating universe construction as a distinct part of strategy design rather than a simple list of eligible stocks.

For event risks, the framework separates predictable from unpredictable events. It applies ongoing exclusion to unpredictable events and uses a financial-quality scoring model, adapted from risk-control binning methods, to identify questionable financial reports tied to predictable negative events. For factor risks, it examines factor combination, exclusion scope, and sensitivity, reporting that removing stocks based on combined negative factors improved strategy performance. These findings are summarized without detailed data, sample definitions, or performance figures. The report explicitly cautions that its backtest results rely on historical data and may not recur, so the stated improvements are not guarantees of future results.

Key ideas

• The framework separates tradability filters from filters intended to improve stock-universe quality.
• Flexible universe optimization considers both factor risks and event risks.
• Unpredictable events are handled through ongoing tracking and exclusion.
• A financial-quality score is used to screen reports associated with predictable negative events.
• The summary reports improved strategy performance from excluding stocks using combined negative factors, while warning that historical results may not repeat.

Tags

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