Model selection for dynamic processes

S Wu, PA Flach

Research output: Chapter in Book/Report/Conference proceedingConference Contribution (Conference Proceeding)

Abstract

In machine learning, ROC (Receiver Operating Characteristic) analysis is widely used in model selection when we consider both class distribution and misclassification costs 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 considered and model selection approaches are discussed.
Original languageEnglish
Title of host publicationUnknown
EditorsM. Bohanec, B. Kasek, N. Lavrac, D. Mladenic
PublisherUniversity of Helsinki
Pages168 - 173
Number of pages5
Publication statusPublished - Aug 2002

Bibliographical note

Conference Proceedings/Title of Journal: ECML/PKDD'02 workshop on Integration and Collaboration Aspects of Data Mining, Decision Support and Meta-Learning

Fingerprint Dive into the research topics of 'Model selection for dynamic processes'. Together they form a unique fingerprint.

  • Cite this

    Wu, S., & Flach, PA. (2002). Model selection for dynamic processes. In M. Bohanec, B. Kasek, N. Lavrac, & D. Mladenic (Eds.), Unknown (pp. 168 - 173). University of Helsinki. http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=1000660