Title :
YaDT: yet another decision tree builder
Author :
Ruggieri, Salvatore
Author_Institution :
Dipt. di Inf., Pisa Univ., Italy
Abstract :
YaDT is a from-scratch main-memory implementation of the C4.5-like decision tree algorithm. Our presentation would be focused on the design principles that allowed for obtaining an extremely efficient system. Experimental results are reported comparing YaDT with Weka, dti, Xelopes and (E)C4.5.
Keywords :
C++ language; Java; abstract data types; computational complexity; decision trees; divide and conquer methods; entropy; learning (artificial intelligence); meta data; object-oriented programming; optimisation; storage management; C++ language; C4.5 decision tree algorithm; Java; Weka; Xelopes; YaDT; abstract data types; decision trees; divide and conquer methods; main-memory implementation; meta data; optimisation; training set; Algorithm design and analysis; Classification algorithms; Classification tree analysis; Databases; Decision trees; Java; Object oriented modeling; Proposals; Software libraries; Terminology;
Conference_Titel :
Tools with Artificial Intelligence, 2004. ICTAI 2004. 16th IEEE International Conference on
Print_ISBN :
0-7695-2236-X
DOI :
10.1109/ICTAI.2004.123
