Learning through changes

An empirical study of dynamic behaviors of probability estimation trees

Kun Zhang, Zujia Xu, Jing Peng, Bill Buckles

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

4 Citations (Scopus)

Abstract

In practice, learning from data is often hampered by the limited training examples. In this paper, as the size of training data varies, we empirically investigate several probability estimation tree algorithms over eighteen binary classification problems. Nine metrics are used to evaluate their performances. Our aggregated results show that ensemble trees consistently outperform single trees. Confusion factor trees(CFT) register poor calibration even as training size increases, which shows that CFTs are potentially biased if data sets have small noise. We also provide analysis on the observed performance of the tree algorithms.

Original languageEnglish
Title of host publicationProceedings - Fifth IEEE International Conference on Data Mining, ICDM 2005
Pages817-820
Number of pages4
DOIs
StatePublished - 1 Dec 2005
Event5th IEEE International Conference on Data Mining, ICDM 2005 - Houston, TX, United States
Duration: 27 Nov 200530 Nov 2005

Other

Other5th IEEE International Conference on Data Mining, ICDM 2005
CountryUnited States
CityHouston, TX
Period27/11/0530/11/05

Fingerprint

Trees (mathematics)
Calibration

Cite this

Zhang, K., Xu, Z., Peng, J., & Buckles, B. (2005). Learning through changes: An empirical study of dynamic behaviors of probability estimation trees. In Proceedings - Fifth IEEE International Conference on Data Mining, ICDM 2005 (pp. 817-820). [1565790] https://doi.org/10.1109/ICDM.2005.88
Zhang, Kun ; Xu, Zujia ; Peng, Jing ; Buckles, Bill. / Learning through changes : An empirical study of dynamic behaviors of probability estimation trees. Proceedings - Fifth IEEE International Conference on Data Mining, ICDM 2005. 2005. pp. 817-820
@inproceedings{1c82e0dd49ef4eaa8aa14e21d98fa634,
title = "Learning through changes: An empirical study of dynamic behaviors of probability estimation trees",
abstract = "In practice, learning from data is often hampered by the limited training examples. In this paper, as the size of training data varies, we empirically investigate several probability estimation tree algorithms over eighteen binary classification problems. Nine metrics are used to evaluate their performances. Our aggregated results show that ensemble trees consistently outperform single trees. Confusion factor trees(CFT) register poor calibration even as training size increases, which shows that CFTs are potentially biased if data sets have small noise. We also provide analysis on the observed performance of the tree algorithms.",
author = "Kun Zhang and Zujia Xu and Jing Peng and Bill Buckles",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/ICDM.2005.88",
language = "English",
isbn = "0769522785",
pages = "817--820",
booktitle = "Proceedings - Fifth IEEE International Conference on Data Mining, ICDM 2005",

}

Zhang, K, Xu, Z, Peng, J & Buckles, B 2005, Learning through changes: An empirical study of dynamic behaviors of probability estimation trees. in Proceedings - Fifth IEEE International Conference on Data Mining, ICDM 2005., 1565790, pp. 817-820, 5th IEEE International Conference on Data Mining, ICDM 2005, Houston, TX, United States, 27/11/05. https://doi.org/10.1109/ICDM.2005.88

Learning through changes : An empirical study of dynamic behaviors of probability estimation trees. / Zhang, Kun; Xu, Zujia; Peng, Jing; Buckles, Bill.

Proceedings - Fifth IEEE International Conference on Data Mining, ICDM 2005. 2005. p. 817-820 1565790.

Research output: Chapter in Book/Report/Conference proceedingConference contributionResearchpeer-review

TY - GEN

T1 - Learning through changes

T2 - An empirical study of dynamic behaviors of probability estimation trees

AU - Zhang, Kun

AU - Xu, Zujia

AU - Peng, Jing

AU - Buckles, Bill

PY - 2005/12/1

Y1 - 2005/12/1

N2 - In practice, learning from data is often hampered by the limited training examples. In this paper, as the size of training data varies, we empirically investigate several probability estimation tree algorithms over eighteen binary classification problems. Nine metrics are used to evaluate their performances. Our aggregated results show that ensemble trees consistently outperform single trees. Confusion factor trees(CFT) register poor calibration even as training size increases, which shows that CFTs are potentially biased if data sets have small noise. We also provide analysis on the observed performance of the tree algorithms.

AB - In practice, learning from data is often hampered by the limited training examples. In this paper, as the size of training data varies, we empirically investigate several probability estimation tree algorithms over eighteen binary classification problems. Nine metrics are used to evaluate their performances. Our aggregated results show that ensemble trees consistently outperform single trees. Confusion factor trees(CFT) register poor calibration even as training size increases, which shows that CFTs are potentially biased if data sets have small noise. We also provide analysis on the observed performance of the tree algorithms.

UR - http://www.scopus.com/inward/record.url?scp=33749570764&partnerID=8YFLogxK

U2 - 10.1109/ICDM.2005.88

DO - 10.1109/ICDM.2005.88

M3 - Conference contribution

SN - 0769522785

SN - 9780769522784

SP - 817

EP - 820

BT - Proceedings - Fifth IEEE International Conference on Data Mining, ICDM 2005

ER -

Zhang K, Xu Z, Peng J, Buckles B. Learning through changes: An empirical study of dynamic behaviors of probability estimation trees. In Proceedings - Fifth IEEE International Conference on Data Mining, ICDM 2005. 2005. p. 817-820. 1565790 https://doi.org/10.1109/ICDM.2005.88