The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON COMPUTERS
Transactions ID Number: 52-239
Full Name: Na Chu
Position: Ph.D. Candidate
Age: ON
Sex: Female
Address: No. 800, Dongchuan Road, Shanghai
Country: CHINA
Tel:
Tel prefix:
Fax:
E-mail address: cina19@163.com
Other E-mails: cina19@sjtu.edu.cn
Title of the Paper: A Comparative Analysis of Methods for Probability Estimation Tree
Authors as they appear in the Paper: Na Chu, Lizhuang Ma, Ping Liu, Yiyang Hu, Min Zhou
Email addresses of all the authors: cina19@163.com,ma-lz@cs.sjtu.edu.cn,liuliver@online.sh.cn,yyhu@citiz.net,zzz208216@hotmail.com
Number of paper pages: 10
Abstract: In this paper, we address the problem of probability estimation of decision trees. This problem has received considerable attention in the areas of machine learning and data mining, and techniques to use tree models as probability estimators have been suggested. We make a comparative study of six well-known class probability estimation methods, measured by classification accuracy, AUC and Conditional Log Likelihood (CLL). Comments on the properties of each method are empirically supported. Our experiments on UCI data sets and our liver disease data sets show that the PETs algorithms outperform traditional decision trees and naïve Bayes significantly in classification accuracy, AUC and CLL respectively. Finally, a unifying pseudocode of algorithm is summarized in this paper.
Keywords: Probability estimation tree, Decision trees, Classification, Joint distribution, AUC, Conditional log likelihood
EXTENSION of the file: .doc
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 58.196.138.20
