S. Kramer, G. Widmer, B. Pfahringer, and M. DeGroeve. Prediction of ordinal classes using regression trees. Fundamenta Informaticae, 47:1--13, 2001.  Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Modelling Large Datasets Using Algebraic Datatypes: A Case Study.. - Mottl (2002) (Correct)
....accuracy. Predicting unsuccessful is surely worse than predicting partial agreement if indeed a full settlement was achievable. This problem should not be confused with cost sensitive learning as described in e.g. Dom99] or similar techniques that take a detour over regression as in e.g. [KWPD01] to predict ordinal classes. We will show that ordered structures can be represented naturally without the help of numerical values of any kind. 2.1.2 Solution: expressing order with algebraic datatypes To remedy this shortcoming, we now explain the way in which ordered structures can be ....
Stefan Kramer, Gerhard Widmer, Bernhard Pfahringer, and Michael DeGroeve. Prediction of ordinal classes using regression trees. Fundamenta Informaticae, XXI:1001-1013, 2001.
A Simple Approach to Ordinal Classification - Frank, Hall (2001) (2 citations) (Correct)
....is very strong evidence that the ordinal classi cation method improves on the standard one per class encoding. 4 Related Work The ordinal classi cation method discussed in this paper is applicable in conjunction with any base learner that can output class probability estimates. Kramer et al. [5] investigate the use of a learning algorithm for regression tasks more Table 4. Experimental results for target value discretized into three bins: percentage of correct classi cations, and standard deviation Dataset C4.5 ORD C4.5 C4.5 1PC Abalone 66.04 0.29 63.90 0.24 65.91 0.34 Ailerons ....
....(signi cantly) outperforms method in row C4.5 ORD C4.5 C4.5 1PC C4.5 ORD 6 (2) 3 (2) C4.5 23 (22) 6 (3) C4.5 1PC 26 (25) 23 (17) speci cally, a regression tree learner to solve ordinal classi cation problems. In this case each class needs to be mapped to a numeric value. Kramer et al. [5] compare several di erent methods for doing this. However, if the class attribute represents a truly ordinal quantity which, by de nition, cannot be represented as a number in a meaningful way there is no principled way of devising an appropriate mapping and this procedure is necessarily ad hoc. ....
S. Kramer, G. Widmer, B. Pfahringer, and M. DeGroeve. Prediction of ordinal classes using regression trees. Fundamenta Informaticae, 2001.
Gaussian Processes for Ordinal Regression - Chu, Ghahramani (2005) (1 citation) (Correct)
No context found.
S. Kramer, G. Widmer, B. Pfahringer, and M. DeGroeve. Prediction of ordinal classes using regression trees. Fundamenta Informaticae, 47:1--13, 2001.
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