Building Custom Factors from Financial Statement Data

Summary

This brief BigQuant forum exchange addresses how to construct a custom factor when it is not available as a precomputed field. The question proposes an expression combining single-quarter revenue less single-quarter cost, divided by average total assets over four quarters, and then divided by price-to-book ratio. The reply points users toward the platform’s populated financial statement data as the source for the required inputs.

The response recommends consulting a platform notebook for details on extracting those data, but the notebook itself is not included here. It does not explain the calculation steps, accounting alignment, treatment of missing values, or how to validate the resulting factor. No empirical results or investment interpretation are provided, so the exchange mainly illustrates that custom factors can be assembled from underlying reported financial data rather than retrieved as a ready-made metric.

Key ideas

• A custom factor can be formed by combining components from financial statements and valuation data.\nThe example uses quarterly revenue and costs, a four-quarter average asset measure, and price-to-book.\nThe platform’s populated financial statement tables are suggested as the source for factor inputs.\nThe exchange gives no guidance on data alignment, missing values, validation, or predictive performance.

Tags

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