|
Activity Number:
|
56
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Sunday, July 29, 2007 : 4:00 PM to 5:50 PM
|
|
Sponsor:
|
IMS
|
| Abstract - #309278 |
|
Title:
|
Kernel-Induced Classification Tree and Random Forest
|
|
Author(s):
|
Guangzhe Fan*+
|
|
Companies:
|
University of Waterloo
|
|
Address:
|
200 University Ave W, Waterloo, ON, N2L 3G1, Canada
|
|
Keywords:
|
classification ; kernel ; tree ; random forest ; learning
|
|
Abstract:
|
A recursive-partitioning procedure using kernel functions is proposed for classification problems. We call it KICT: kernel-induced classification trees. The resulting model could significantly improve the traditional CART model in many situations. We also introduce KIRF: kernel-induced random forest. KIRF also compares favorably to the traditional random forests in many situations. We use simulated and real world data to illustrate their performances.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2007 program |
