(Enter summary)
Abstract: Although the majority of conceptlearning
systems previously designed usually assume
that their training sets are well-balanced, this
assumption is not necessarily correct. Indeed, there
exist many domains for which one class is represented
by a large number of examples while the
other is represented by only a few. The purpose of
this paper is 1) to demonstrate experimentally that,
at least in the case of connectionist systems, class
imbalances hinder the performance of standard classifiers
and... (Update)
Context of citations to this paper: More
...words is far greater than that of IC words. To deal with this imbalanced dataset, we have tried both down sampling [12] and over sampling [9], and found that down sampling produced more accurate classifiers than oversampling. e.g. it produced about 20 higher recall of IC...
Cited by: More
Mixture of Expert Agents for Handling Imbalanced Data Sets - Kotsiantis, Pintelas (2003)
(Correct)
Learning Browsing Behavior Model for Web Recommendation - Zhu (2003)
(Correct)
Predicting Web Information Content - Tingshao Zhu Russ
(Correct)
Similar documents (at the sentence level):
64.5%: Learning from Imbalanced Data Sets: A Comparison of Various.. - Japkowicz (2000)
(Correct)
Active bibliography (related documents): More All
0.1: A Comparative Study On Hybrid Acoustic Phonetic.. - Bengio, De Mori.. (1991)
(Correct)
0.1: The Applicability of Neural Nets for Decision Support - Aarts, Wessels, Zwietering (1993)
(Correct)
0.1: -104 A Procedure For On Line Learning And Improvemnet Of.. - Safavi Gunes Kharazmi (2000)
(Correct)
Similar documents based on text: More All
0.2: A Case-Based Reasoning System Involving A Quantized.. - Kuchar, Lazukova..
(Correct)
0.1: Supervised versus Unsupervised Binary-Learning by Feedforward.. - Japkowicz
(Correct)
0.1: Class Imbalances versus Class Overlapping: An Analysis of .. - Prati, Batista, Monard (2004)
(Correct)
Related documents from co-citation: More All
6: Data mining for direct marketing: Problems and solutions
- Ling, Li - 1998
5: Pattern classification and scene analysis (context) - Duda, Hart - 1973
4: Fast Algorithms for Mining Association Rules
- Agrawal, Srikant - 1994
BibTeX entry: (Update)
Japkowicz, N. 2000. The class imbalance problem: Significance and strategies. In Proceedings of the 2000 International Conference on Artificial Intelligence (ICAI '2000). http://citeseer.ist.psu.edu/japkowicz00class.html More
@inproceedings{ japkowicz00class,
author = "Nathalie Japkowicz",
title = "The Class Imbalance Problem: Significance and Strategies",
booktitle = "Proceedings of the 2000 International Conference on Artificial Intelligence ({IC}-{AI}'2000)",
volume = "1",
pages = "111--117",
year = "2000",
url = "citeseer.ist.psu.edu/japkowicz00class.html" }
Citations (may not include all citations):
8
Williams Learning Internal Representations by Error Propagat.. (context) - Rumelhart, Hinton - 1986
1
Fawcett and Foster Provost Adaptive Fraud Detection Data Min.. (context) - Tom - 1997
1
Catherine Myers and Mark Gluck A Novelty Detection Approach .. (context) - Japkowicz - 1995
1
Robert Holte and Stan Matwin Machine Learning for the Detect.. (context) - Kubat - 1998
1
Reducing Misclassification Costs Proceedings of the Eleventh.. (context) - Pazzani, Merz et al. - 1994
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://borg.cs.dal.ca/~nat/Papers/papers.html): More
Are we better off without Counter-Examples? - Japkowicz (1999)
(Correct)
Bootstrapping Training-Data Representations for Inductive.. - Hirsh, Japkowicz (1994)
(Correct)
Adaptability of the Backpropagation Procedure - Nathalie Japkowicz (1999)
(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