An Online Ensemble of Classifiers

S. B. Kotsiantis, P. E. Pintelas


Along with the explosive increase of data and information, incremental learning ability has become more and more important for machine learning approaches. The online algorithms try to forget irrelevant information instead of synthesizing all available information (as opposed to classic batch learning algorithms). Nowadays, combining classifiers is proposed as a new direction for the improvement of the classification accuracy. However, most ensemble algorithms operate in batch mode. For this reason, we propose an online ensemble of classifiers that combines an incremental version of Naive Bayes, the Voted Perceptron and the Win-now algorithms using the voting methodology. We performed a large-scale comparison of the proposed ensemble with other state-of-the-art algorithms on several datasets and we took better accuracy in most cases.


  1. Aha, D., Lazy Learning. Dordrecht: Kluwer Academic Publishers (1997).
  2. Auer P. & Warmuth M., Tracking the Best Disjunction, Machine Learning 32 (1998) 127- 150, Kluwer Academic Publishers.
  3. Bauer, E. & Kohavi, R., An empirical comparison of voting classification algorithms: Bagging, boosting, and variants. Machine Learning 36 (1999) 105-139.
  4. Blake, C.L. & Merz, C.J, UCI Repository of machine learning databases. Irvine, CA: University of California, Department of Information and Computer Science (1998): []
  5. Cohen W., Fast Effective Rule Induction. In Proc. of Int Conf. of ML-95 (1995). 115-123.
  6. Domingos P. & Pazzani M., On the optimality of the simple Bayesian classifier under zero-one loss. Machine Learning, 29 (1997) 103-130.
  7. Fan W., Stolfo S., and Zhang J., The application of AdaBoost for distributed, scalable and on-line learning, in Proceedings of the Fifth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY: ACM Press, 1999, pp. 362-366.
  8. Fayyad U., and Irani K., Multi-interval discretization of continuous-valued attributes for classification learning. In Proc. of the 13th Int. Joint Conference on AI (1993) 1022-1027.
  9. Fern, A., & Givan, R., Online ensemble learning: An empirical study. In Proceedings of the Seventeenth International Conference on ML (2000) 279-286. Morgan Kaufmann.
  10. Freund Y., Schapire R., Large Margin Classification Using the Perceptron Algorithm, Machine Learning 37 (1999) 277-296, Kluwer Academic Publishers.
  11. Littlestone N. & Warmuth M., The weighted majority algorithm. Information and Computation 108 (1994) 212-261.
  12. Mitchell, T., Machine Learning. McGraw Hill (1997).
  13. Oza, N. C. and Russell, S., Online Bagging and Boosting." In Artificial Intelligence and Statistics 2001, eds. T. Richardson and T. Jaakkola, 105-112.
  14. Quinlan J.R., C4.5: Programs for machine learning. Morgan Kaufmann, San Francisco (1993).
  15. Saad, D., Online learning in neural networks, London, Cambridge University Press (1998).
  16. Salzberg, S., On Comparing Classifiers: Pitfalls to Avoid and a Recommended Approach, Data Mining and Knowledge Discovery 1 (1997) 317-328.
  17. Schaffer, C., Selecting a classification method by cross-validation. Machine Learning 13 (1993) 135-143.
  18. Utgoff, P., Berkman, N., & Clouse, J., Decision tree induction based on efficient tree restructuring. Machine Learning, 29 (1997) 5-44.
  19. Widmer G. and Kubat M., Learning in the presence of concept drift and hidden contexts. Machine Learning 23 (1996) 69-101.
  20. Witten I. & Frank E., Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations, Morgan Kaufmann, San Mateo (2000).

Paper Citation

in Harvard Style

B. Kotsiantis S. and E. Pintelas P. (2004). An Online Ensemble of Classifiers . In Proceedings of the 4th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2004) ISBN 972-8865-01-5, pages 59-68. DOI: 10.5220/0002672400590068

in Bibtex Style

author={S. B. Kotsiantis and P. E. Pintelas},
title={An Online Ensemble of Classifiers},
booktitle={Proceedings of the 4th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2004)},

in EndNote Style

JO - Proceedings of the 4th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2004)
TI - An Online Ensemble of Classifiers
SN - 972-8865-01-5
AU - B. Kotsiantis S.
AU - E. Pintelas P.
PY - 2004
SP - 59
EP - 68
DO - 10.5220/0002672400590068