Leveraging Black-box Models to Assess Feature Importance in Unconditional Distribution

Tools

Zhou, Jing ORCID: https://orcid.org/0000-0002-8894-9100 and Li, Chunlin (2024) Leveraging Black-box Models to Assess Feature Importance in Unconditional Distribution.

Full text not available from this repository. (Request a copy)

Abstract

Understanding how changes in explanatory features affect the unconditional distribution of the outcome is important in many applications. However, existing black-box predictive models are not readily suited for analyzing such questions. In this work, we develop an approximation method to compute the feature importance curves relevant to the unconditional distribution of outcomes, while leveraging the power of pre-trained black-box predictive models. The feature importance curves measure the changes across quantiles of outcome distribution given an external impact of change in the explanatory features. Through extensive numerical experiments and real data examples, we demonstrate that our approximation method produces sparse and faithful results, and is computationally efficient.

Item Type:	Article
Uncontrolled Keywords:	stat.ml,cs.lg,stat.co,stat.me
Faculty \ School:	Faculty of Science > School of Engineering, Mathematics and Physics
Related URLs:	http://arxiv.org/pdf/2412.05759v1
Depositing User:	LivePure Connector
Date Deposited:	07 Jan 2025 01:55
Last Modified:	07 Jan 2025 01:55
URI:	https://ueaeprints.uea.ac.uk/id/eprint/98099
DOI:

Actions (login required)

View Item