An Enhanced Projection Pursuit Tree Classifier with Visual Methods for Assessing Algorithmic Improvements

ArXi:2602.21130v2 Announce Type: replace-cross This paper presents enhancements to the projection pursuit tree classifier and visual diagnostic methods for assessing their impact in high dimensions. The original algorithm uses linear combinations of variables in a tree structure where depth is constrained to be less than the number of classes -- a limitation that proves too rigid for complex classification problems.