Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

Assessing the Degree of Feature Interactions that Determine a Model Prediction

Published

Author(s)

Krishna Khadka, Sunny Shree, Yu Lei, Raghu Kacker, David Kuhn

Abstract

Machine Learning (ML) models rely on capturing important feature interactions to generate predictions. This study is focused on validating the hypothesis that model predictions often depend on interactions involving only a few features. This hypothesis is inspired by t-way combinatorial testing for software systems. In our study, we utilize the notion of Shapley Additive Explanations (SHAP) values to quantify each feature's contribution to model prediction. We then use a greedy approach to identify a minimal subset of features (t) required to determine a model prediction. Our empirical evaluation is performed on three datasets: Adult Income, Mushroom, and Breast Cancer, and three classification models: Logistic Regression, XGBoost, and SVM. Through our experiments, we find that the majority of predictions are determined by interactions involving only a subset of features.
Proceedings Title
2024 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW)
Conference Dates
May 31, 2024
Conference Location
Toronto, CA
Conference Title
IEEE International Workshop on Combinatorial Testing

Keywords

Feature Interaction, Model Prediction, Combi- natorial Testing

Citation

Khadka, K. , Shree, S. , Lei, Y. , Kacker, R. and Kuhn, D. (2024), Assessing the Degree of Feature Interactions that Determine a Model Prediction, 2024 IEEE International Conference on Software Testing, Verification and Validation Workshops (ICSTW), Toronto, CA, [online], https://doi.org/10.1109/ICSTW60967.2024.00043, https://tsapps.nist.gov/publication/get_pdf.cfm?pub_id=957716 (Accessed April 3, 2025)

Issues

If you have any questions about this publication or are having problems accessing it, please contact reflib@nist.gov.

Created September 17, 2024, Updated April 1, 2025