CDF: Centroid Decision Forest for High-Dimensional Classification (original) (raw)

Implements the Centroid Decision Forest (CDF) as a single user-facing function CDF(). The method selects discriminative features via a multi-class class separability score (CSS), splits by nearest class centroid, and aggregates tree votes to produce predictions and class probabilities. Returns CSS-based feature importance as well. Amjad Ali, Saeed Aldahmani, Zardad Khan (2025) <doi:10.48550/arXiv.2503.19306>.

Documentation:

Downloads:

Linking:

Please use the canonical formhttps://CRAN.R-project.org/package=CDFto link to this page.