Foster Provost, Pedro Domingos  Home/Search
Context Related
| nyu.edu/~fprovost/Papers/petwp.ps Cached: PS.gz PS PDF This document uses CoBlitz to cache paper downloads. If your firewall is blocking outgoing connections to port 3125, you can use these links to download local copies.
Image Update HelpPS.gz PS PDF From: nyu.edu/~fprovost (more) (Enter author homepages) |
Rate this article:      (best)Comment on this article |
Abstract: Decision trees are one of the most effective and widely used classification methods. However, many applications require class probability estimates, and probability estimation trees (PETs) have the same attractive features as classification trees (e.g., comprehensibility, accuracy and efficiency in high dimensions and on large data sets). Unfortunately, decision trees have been found to provide poor probability estimates. Several techniques have been proposed to build more accurate PETs, but,... (Update)
Context of citations to this paper: More
.... The Laplace correction has been shown to improve the CPEs produced by PETs [Bauer and Kohavi, 1998; Provost et al. 1998; Provost Domingos, 2000]. When evaluating CPE accuracy, if the true underlying class probability distribution were known, an evaluation of an...
.... classification has been investigated with other model classes such as neural networks [14] and ensembles of decision trees [8, 21]. These models tend to be much more complex than rule sets and may not have rules appealing properties of modularity and intelligibility....
Cited by: More
Sensitivity Analysis of the Result in Binary Decision Trees - Alvarez (2004) (Correct)
The Effect Of Small Disjuncts And - Class Distribution On (Correct)
Improved Class Probability estimates from Decision Tree Models - Margineantu, Dietterich (2002) (Correct)
Similar documents (at the sentence level):
26.1%: Tree Induction for Probability-based Ranking - Provost, Domingos (Correct)
Active bibliography (related documents): More All
0.6: Learning and Making Decisions When Costs and Probabilities.. - Zadrozny, Elkan (2001) (Correct)
0.6: An Evolutionary Algorithm for Cost-Sensitive - Decision Rule Learning (2001) (Correct)
0.5: Extracting context-sensitive models in Inductive Logic Programming - Srinivasan (2001) (Correct)
Similar documents based on text: More All
0.6: Improved Class Probability Estimates from Decision Tree Models - Margineantu, Dietterich (2001) (Correct)
0.5: Active Sampling for Class Probability Estimation and Ranking - Saar-Tsechansky, Provost (Correct)
0.3: Pointwise ROC Confidence Bounds: An Empirical Evaluation - Sofus Macskassy Smacskas (2005) (Correct)
Related documents from co-citation: More All
7: Programs for machine learning (context) - Quinlan - 1993
5: Learning and making decisions when costs and probabilities are both unknown - Zadrozny, Elkan - 2001
4: Pruning decision trees with misclassification costs - Bradford, Kunz et al. - 1998
BibTeX entry: (Update)
P. Domingos and F. Provost. Well-trained PETs: Improving probability estimation trees. CDER Working Paper #00-04-IS, Stern School of Business, New York University, NY, NY 10012, 2000. http://citeseer.ist.psu.edu/provost00welltrained.html More
@misc{ domingos00welltrained,
author = "P. Domingos and F. Provost",
title = "Well-trained {PETs}: Improving probability estimation trees",
note = "CDER Working Paper #00-04-IS, Stern School of Business, New York
University, NY, NY 10012.",
year = "2000",
url = "citeseer.ist.psu.edu/provost00welltrained.html" }
Citations (may not include all citations):2177 Programs for Machine Learning (context) - Quinlan - 1993
1359 Induction of decision trees (context) - Quinlan - 1986
696 UCI repository of machine learning databases (context) - Blake, Merz - 2000
657 Bagging predictors - Breiman - 1996
202 Statistical Methods for Speech Recognition (context) - Jelinek - 1997
121 Classication and Regression Trees (context) - Breiman, Friedman et al. - 1984
99 Concept learning and the problem of small disjuncts (context) - Holte, Acker et al. - 1989
77 Learning Bayesian networks with local structure - Friedman, Goldszmidt - 1996
75 The meaning and use of the area under a receiver operating c.. (context) - Hanley, McNeil - 1982
70 The case against accuracy estimation for comparing induction.. - Provost, Fawcett et al. - 1998
68 Rule induction with CN2: Some recent improvements (context) - Clark, Boswell - 1991
55 Measuring the accuracy of diagnostic systems (context) - Swets - 1988
53 The use of the area under the ROC curve in the evaluation of.. (context) - Bradley - 1997
40 An empirical comparison of voting classication algorithms: B.. (context) - Bauer, Kohavi - 1999
40 Extracting Comprehensible Models from Trained Neural Network.. (context) - Craven - 1996
36 Constructing decision trees in noisy domains (context) - Niblett - 1987
35 A survey of methods for scaling up inductive algorithms - Provost, Kolluri - 1999
30 Knowledge acquisition from examples via multiple models - Domingos - 1997
24 An exploratory technique for investigating large quantities .. (context) - Kass - 1980
22 Large data sets lead to overly complex models: an explanatio.. - Oates, Jensen - 1998
18 Improving simple Bayes - Kohavi, Becker et al. - 1997
17 MetaCost: a general method for making classiers cost-sensiti.. (context) - Domingos - 1999
15 Out-of-bag estimation - Breiman - 1998
13 Robust classication for imprecise environments - Provost, Fawcett - 2000
11 Construction and Assessment of Classication Rules (context) - Hand - 1997
10 Dependency networks for density estimation (context) - Heckerman, Chickering et al. - 2000
9 A theory of learning classication rules (context) - Buntine - 1991
7 Probabilistic estimation-based data mining for discovering i.. (context) - Apte, Grossman et al. - 1999
6 Analysis and visualization of classier performance: Comparis.. (context) - Provost, Fawcett - 1997
6 Robust classication systems for imprecise environments (context) - Provost, Fawcett - 1998
5 Exploiting the cost (context) - Drummond, Holte - 2000
5 Separate-and-conquer rule learning (context) - urnkranz - 1999
5 Pruning decision trees with misclassication costs (context) - Bradford, Kunz et al. - 1998
3 A comparison of prediction accuracy (context) - Lim, Loh et al. - 2000
3 Reducing misclassication costs (context) - Pazzani, Merz et al. - 1994
3 Retrotting decision tree classiers using kernel density esti.. (context) - Smyth, Gray et al. - 1995
1 Private communication (context) - Breiman - 2000
1 Moody's public rm risk model: A hybrid approach to modeling .. (context) - Sobehart, Stein et al. - 2000
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://www.stern.nyu.edu/~fprovost): More
On Applied Research in Machine Learning - Provost (1998) (Correct)
Machine Learning from Imbalanced Data Sets 101 (Extended Abstract) - Provost (Correct)
Scaling Up Inductive Algorithms: An Overview - Provost, Kolluri (1997) (Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC