Troubleshooting Missing Stocks in BigQuant Feature Extraction

Summary

This BigQuant support note explains why some stocks may disappear during a feature-extraction workflow. It gives two configuration suggestions: leave the feature module’s start and end dates blank when those dates should be inherited from the upstream code-list module, and use the missing-value removal option carefully. The example issue involved a stock being removed because its extracted data contained missing values.

The note points readers to an example implementation, but it does not describe a trading strategy, data-quality validation procedure, or broader handling rules for missing observations. Removing incomplete rows can change the securities included in an analysis, while retaining them may require deliberate treatment downstream. The guidance is specific to the described BigQuant workflow and should be checked against the platform’s current module behavior. It provides a concise diagnosis rather than evidence from a systematic comparison of configuration choices.

Key ideas

• The feature-extraction module can inherit its date range from an upstream code-list module.
• Leaving its start and end dates blank is recommended when relying on that inheritance.
• Enabling missing-value removal may exclude securities whose extracted features contain gaps.
• The example attributes one stock’s omission to missing data being removed.
• The advice is platform-specific and does not provide a general missing-data methodology.

Tags

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