Using Financial and Macro Data as Model Features in BigQuant

Summary

The document explains how to bring financial statement and macroeconomic data into a quantitative model as features. It distinguishes macro data, which is readable from the platform but must first be aligned and merged with the sample data, from financial statement data, which can be read in a stock-oriented, forward-filled form.

The practical method is to attach each date’s macro observations to the relevant stock records so the resulting data has the structure expected for model inputs. For financial data, the note points to reading an existing forward-filled statement dataset by security. It offers no modeling example, feature definitions, or evidence that particular variables improve predictions. Researchers still need to handle timing and availability carefully to avoid using information before it was public.

Key ideas

• Macro data must be merged with stock samples before it can serve as a model feature.
• The merge should match each stock observation with the corresponding macro data for that date.
• The platform provides a forward-filled financial statement dataset that can be read for an individual security.
• The document gives data access guidance but does not evaluate feature performance.

Tags

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