F. Provost and T. Fawcett. Anaylysis and visualization of classifier performance: Comparison under imprecise class and cost distributions. In Proc. Third Intl. Conf. Knowledge Discovery and Data Mining, pages 43--48, 1997. Home/Search Document Not in Database Summary Related Articles Check |
This paper is cited in the following contexts:
Pruning Meta-Classifiers in a Distributed Data Mining System - Prodromidis, Stolfo (1998) (7 citations) (Correct)
....3 and it is expensive and impractical when dealing with numerous of classifiers and large data sets. On the other hand, the pruning methods presented in this paper precede the meta learning phase and, as such, can be used in conjunction with SCANN or any other algorithm. Provost and Fawcett [26] introduced the ROC convex hull method for its intuitiveness and flexibility. The method evaluates models for binary classification problems, by mapping them onto a True Positive False Negative plane and 1 As opposed to post training pruning [25] which denotes the evaluation and revision pruning ....
....TP FP spread is an ad hoc, yet informative and simple metric characterizing the performance of the classifiers. In comparing the classifiers, one can replace the TP FP spread, which defines a certain family of curves in the ROC plot, with a different metric or even with a complete analysis [26] in the ROC space. 0.83 0.84 0.85 0.86 0.87 0.88 0.89 0.9 5 10 15 20 25 30 35 40 45 50 number of base classifiers in a meta classifier Total Accuracy of Ripper Chase meta classifiers with Chase base classifiers Accuracy Coverage PCS Coverage Arbitrary Accuracy Diversity Accuracy Coverage ....
F. Provost and T. Fawcett. Anaylysis and visualization of classifier performance: Comparison under imprecise class and cost distributions. In Proc. Third Intl. Conf. Knowledge Discovery and Data Mining, pages 43--48, 1997.
On the Management of Distributed Learning Agents - Prodromidis (1997) (Correct)
....obtained by training (possibly) different learning algorithms over (possibly) distinct databases. Furthermore, instead of voting over the predictions of classifiers for the final classification, we adopt meta learning to discover the importance of the individual classifiers. Provost and Fawcett in [34] introduce the ROC convex hull method as a means to manage, analyze and compare classifiers. The ROC convex hull method is intuitive in that it provides clear visual comparisons and flexible in the sense that it allows classifier comparison under different metrics (e.g. accuracy, true ....
F. Provost and T. Fawcett. Anaylysis and visualization of classifier performance: Comparison under imprecise class and cost distributions. In Proc. Third Intl. Conf. Knowledge Discovery and Data Mining, pages 43--48, 1997.
Pruning Classifiers in a Distributed Meta-Learning System - Prodromidis, Stolfo, Chan (1998) (3 citations) (Correct)
....Classifiers To analyze, compare and manage ensembles of classifiers, one can employ several different measures and methods. Before we present the metrics employed in this study, we summarize the previous and current research within the Machine Learning and KDD communities. Provost and Fawcett [18] introduced the ROC convex hull method for its intuitiveness and flexibility. The method evaluates models for binary classification problems, by mapping them onto a True Positive False Negative plane and by allowing comparisons under different metrics (true positive false negative rates, ....
F. Provost and T. Fawcett. Anaylysis and visualization of classifier performance: Comparison under imprecise class and cost distributions. In Proc. Third Intl. Conf. Knowledge Discovery and Data Mining, pages 43--48, 1997.
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