Sector Categorization Using Gradient Boosted Trees Trained on Fundamental Firm Data
6 Pages Posted: 20 Jun 2019
Date Written: June 13, 2019
We demonstrate that the GICS sector and industry group categorizations can be systematically reconstructed from quarterly firm fundamental data using gradient boosted tree classification with high accuracy. Model complexity and performance tradeoffs are examined and relative feature importance is described. Potential extensions are outlined including validating internal consistency of existing classification methods and reducing model complexity.
Keywords: GICS Sector, Gradient Boosted Trees, Fundamental Data, Financial Ratios
JEL Classification: D40, C80
Suggested Citation: Suggested Citation