Fourth Edition of the International Conference on Research in Applied Mathematics and Computer Science ICRAMCS 2022
 March 24-25-26, 2022
Online and Face-to-Face Conference

ICRAMCS, 4 (2022) | Proceedings ISSN: 2605-7700

Research Communication | Open Access
Volume 2022 | Communication ID 266
Kendall interaction filter for variable interaction screening in high dimensional classification
Youssef Anzarmou, Abdallah Mkhadri, Karim Oualkacha
Academic Editor: Youssef EL FOUTAYENI
Received
Accepted
Published
January 29, 2022
March 03, 2233
April 15, 2233

Abstract: Accounting for important interaction effects can improve the prediction of many statistical learning models. In this work, we develop a new model-free interaction screening method, termed Kendall Interaction Filter (KIF), for the classification in high-dimensional settings. KIF method suggests a weighted-sum measure, which compares the overall to the within-cluster Kendall's tau of pairs of predictors, to select interactive couples of features. The proposed KIF measure captures relevant interactions for the clusters response-variable, handles continuous, categorical or a mixture of ...