|
Published Articles >> Table of Contents >> Abstract
Fifth IEEE International Conference on Data Mining (ICDM'05)
pp. 3-9
Handling Generalized Cost Functions in the Partitioning Optimization Problem through Sequential Binary Programming
Alan S. Abrahams, University of Pennsylvania
Adrian Becker, University of Pennsylvania
Daniel Fleder, University of Pennsylvania
Ian C. MacMillan, University of Pennsylvania
Full Article Text:
 
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICDM.2005.74
Send link to a friend
| Abstract |
|
This paper proposes a framework for cost-sensitive
classification under a generalized cost function. By
combining decision trees with sequential binary
programming, we can handle unequal misclassification
costs, constrained classification, and complex objective
functions that other methods cannot. Our approach has
two main contributions. First, it provides a new method
for cost-sensitive classification that outperforms a
traditional, accuracy-based method and some current
cost-sensitive approaches. Second, and more important,
our approach can handle a generalized cost function,
instead of the simpler misclassification cost matrix to
which other approaches are limited.
|
 Additional Information
|
Citation:
Alan S. Abrahams, Adrian Becker, Daniel Fleder, Ian C. MacMillan,
"Handling Generalized Cost Functions in the Partitioning Optimization Problem through Sequential Binary Programming,"
icdm,
pp. 3-9,
Fifth IEEE International Conference on Data Mining (ICDM'05),
2005
|
|
