Abstract
In this paper, we discuss how a proper definition of a ranking can be introduced in the framework of supervised learning. We elaborate on its practical representation, and show how we can deal in a sound way with reversed preferences by transforming them into uncertainties within the representation.
Keywords
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
A. Ben-David, Automatic generation of symbolic multiattribute ordinal knowledgebased DSSs: methodology and applications. Decision Sciences 23 (1992), 1357–1372.
G. Gediga and I. Düntsch, Approximation quality for sorting rules, submitted.
S. Greco, B. Mattarazo and S. Słlowiński, Rough set theory for multicriteria decision analysis. European J. Oper. Res. 129 (2000), 1–47.
K. Makino, T. Suda, H. Ono, T. Ibaraki, Data analysis by positive decision trees. IEICE Trans. Inf. and Syst. E82-D (1999), 76–88.
R. Potharst, J. C. Bioch, Decision trees for ordinal classification. Intelligent Data Analysis 4 (2000), 97–112.
B. Roy, Multicriteria Methodology for Decision Aiding. Kluwer Academic Publishers, Dordrecht, 1996.
Ph. Vincke, Basic concepts of preference modelling. In: Readings in Multiple Criteria Decision Aid (C. Bana e Costa, ed.), Springer Verlag, Berlin-Heidelberg, 1990, pp. 101–118.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Cao-Van, K., De Baets, B. (2002). On the Definition and Representation of a Ranking. In: de Swart, H.C.M. (eds) Relational Methods in Computer Science. RelMiCS 2001. Lecture Notes in Computer Science, vol 2561. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36280-0_20
Download citation
DOI: https://doi.org/10.1007/3-540-36280-0_20
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00315-1
Online ISBN: 978-3-540-36280-7
eBook Packages: Springer Book Archive