Sector categorization using gradient boosted trees trained on fundamental firm data
Document Type
Article
Publication Date
1-1-2020
Abstract
We examine to what extent the GICS sector categorization of equity securities may be systematically reconstructed from historical quarterly firm fundamental data using gradient boosted tree classification. Model complexity and performance tradeoffs are examined and relative feature importance is described. Potential extensions are outlined including ideas to improve feature engineering, validating internal consistency and integrating additional data sources to further improve classification accuracy.
Identifier
85099450981 (Scopus)
Publication Title
Algorithmic Finance
External Full Text Location
https://doi.org/10.3233/AF-200308
e-ISSN
21576203
ISSN
21585571
First Page
91
Last Page
99
Issue
3-4
Volume
8
Recommended Citation
Fang, Ming; Kuo, Lilian; Shih, Frank; and Taylor, Stephen, "Sector categorization using gradient boosted trees trained on fundamental firm data" (2020). Faculty Publications. 5733.
https://digitalcommons.njit.edu/fac_pubs/5733
