[ SolEuNet | Library | Education ]
Model Selection for Dynamic Processes
and Peter Flach.
In Marko Bohanec,
and Nada Lavrac, editors, ECML/PKDD'02
workshop on Integrating Aspects of Data Mining, Decision Support and
Meta-Learning, August 2002.
In machine learning, ROC (Receiver Operating Characteristic) analysis is widely
used in model selection when we consider both class distribution and cost of
misclassification that must be given at test time. In this paper we consider
the case of a dynamic process, such that the class distributions are
different in different time periods or states. The main problem is then to
decide when to change models according to the different states of the
generating process. In this paper we use a control chart to choose models for
the process when misclassification costs are considered. Four strategies are
given and model selection approaches are discussed.
Peter.Flach@bristol.ac.uk. Last modified on Wednesday 9 April 2003 at 18:18. © 2003 SolEuNet