A Comparison of Two Approaches to Classify with Guaranteed Performance

Authors:
Stijn Vanderlooy;Ida G. Sprinkhuizen-Kuyper
Affiliations:
MICC-IKAT, Universiteit Maastricht, P.O. Box 616, 6200 MD Maastricht, The Netherlands;NICI, Radboud University Nijmegen, P.O. Box 9104, 6500 HE Nijmegen, The Netherlands
Venue:
PKDD 2007 Proceedings of the 11th European conference on Principles and Practice of Knowledge Discovery in Databases
Year:
2007

Citing 3
Cited 0

Robust Classification for Imprecise Environments

Machine Learning
Prediction algorithms and confidence measures based on algorithmic randomness theory

Theoretical Computer Science - Natural computing
Algorithmic Learning in a Random World

Algorithmic Learning in a Random World

Quantified Score

Hi-index	0.00

Visualization

Abstract

The recently introduced transductive confidence machine approach and the ROC isometrics approach provide a framework to extend classifiers such that their performance can be set by the user prior to classification. In this paper we use the k-nearest neighbour classifier in order to provide an extensive empirical evaluation and comparison of the approaches. From our results we may conclude that the approaches are competing and promising generally applicable machine learning tools.