Issue No.09 - September (2008 vol.20)
Francisco J. Ruiz , UPC - ESAII, Vilanova i la Geltrú
Cecilio Angulo , UPC - ESAII, Vilanova i la Geltrú
Núria Agell , ESADE, Barcelona
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TKDE.2008.66
This article introduces a new method for supervised discretization based on interval distances by using a novel concept of neighbourhood in the target's space. The method proposed takes into consideration the order of the class attribute, when this exists, so that it can be used with ordinal discrete classes as well as continuous classes, in the case of regression problems. The method has proved to be very efficient in terms of accuracy and faster than the most commonly supervised discretization methods used in the literature. It is illustrated through several examples and a comparison with other standard discretization methods is performed for three public data sets by using two different learning tasks: a decision tree algorithm and SVM for regression.
Interval arithmetic, Clustering, classification, and association rules, Mining methods and algorithms
Francisco J. Ruiz, Cecilio Angulo, Núria Agell, "IDD: A Supervised Interval Distance-Based Method for Discretization", IEEE Transactions on Knowledge & Data Engineering, vol.20, no. 9, pp. 1230-1238, September 2008, doi:10.1109/TKDE.2008.66