Work

Feature Interactions in XGBoost

Year: 2020

Type: preprint

Abstract: In this paper, we investigate how feature interactions can be identified to be used as constraints in the gradient boosting tree models using XGBoost's implementation. Our results show that accurate identification of these constraints can help improve the performance of baseline XGBoost model significantly. Further, the improvement in the model structure can also lead to better interpretability.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2007.05758

Authors: Goyal, Kshitij, Dumancic, Sebastijan, Blockeel, Hendrik

Language: English

Topic: Data Mining Algorithms and Applications

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W3041173218

Cites: 10

Cited by: 8

Related to: 10