Abstract
Most of supervised learning algorithms assume the stability of the target concept over time. Nevertheless in many real-user modeling systems, where the data is collected over an extended period of time, the learning task can be complicated by changes in the distribution underlying the data. This problem is known in machine learning as concept drift. The main idea behind Statistical Quality Control is to monitor the stability of one or more quality characteristics in a production process which generally shows some variation over time. In this paper we present a method for handling concept drift based on Shewhart P-Charts in an on-line framework for supervised learning. We explore the use of two alternatives P-charts, which differ only by the way they estimate the target value to set the center line. Experiments with simulated concept drift scenarios in the context of a user modeling prediction task compare the proposed method with other adaptive approaches. The results show that, both P-Charts consistently recognize concept changes, and that the learner can adapt quickly to these changes to maintain its performance level.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Castillo, G., Gama, J., Breda, A.M.: Adaptive Bayes for a User Modeling Prediction Task based on Learning Styles. In: Brusilovsky, P., Corbett, A.T., de Rosis, F. (eds.) UM 2003. LNCS, vol. 2702, pp. 328–332. Springer, Heidelberg (2003)
del Castillo, E.: Statistical Process Adjustment for Quality Control. John Willey and Sons, Inc., New York (2002)
Felder, R.M., Soloman, B.A.: Index of Learning Style Questionnaire, available online at http://www2.ncsu.edu/unity/lockers/users/f/felder/public/ILSdir/ilsweb.html
M.R.: Matters of Style. ASEE Prism 6(4), 18–23 (1996)
Gama, J., Castillo, G.: Adaptive Bayes. In: Garijo, F.J., Riquelme, J.-C., Toro, M. (eds.) IBERAMIA 2002. LNCS (LNAI), vol. 2527, pp. 765–774. Springer, Heidelberg (2002)
Klinkenberg, R., Renz, I.: Adaptive Information Filtering: Learning in the Presence of Concept Drifts, Learning for Text Categorization, pp. 33–40. AAAI Press, Menlo Park (1998)
Klinkenberg, R., Joachims, T.: Detecting Concept Drift with Support Vector Machines. In: Proceedings of the Seventeenth International Conference on Machine Learning (ICML), Morgan Kaufmann, San Francisco (2000)
Lanquillon, C.: Enhancing Test Classification to Improve Information Filtering, PhD. Dissertation, University of Madgdeburg, Germany (2001), available on-line at http://diglib.uni-magdeburg.de/Dissertationen/2001/carlanquillon.pdf
Maloof, M., Michalski, R.: Selecting Examples for Partial Memory Learning. Machine Learning 41, 27–52 (2000)
Medas, P., Gama, J.: Aprendizagem com Detecção de Mudança de Conceito. Actas das X Jornadas de Classificação e Análise de Dados, Aveiro, 27–31 (2003)
Mitchell, T.: Machine Learning. McGraw Hill, New York (1997)
Montgomery, D.C.: Introduction to Statistical Quality Control, 3rd edn. John Willey & Sons, Inc., New York (1997)
Webb, G., Pazzani, M., Billsus, D.: Machine Learning for User Modeling. User Modeling and User-Adapted Interaction 11, 19–29 (2001)
Widmer, G., Kubat, M.: Learning in the Presence of Concept Drift and Hidden Context. Machine Learning 23, 69–101 (1996)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Castillo, G., Gama, J., Medas, P. (2003). Adaptation to Drifting Concepts. In: Pires, F.M., Abreu, S. (eds) Progress in Artificial Intelligence. EPIA 2003. Lecture Notes in Computer Science(), vol 2902. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24580-3_34
Download citation
DOI: https://doi.org/10.1007/978-3-540-24580-3_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-20589-0
Online ISBN: 978-3-540-24580-3
eBook Packages: Springer Book Archive