Abstract
This paper introduces a novel method for obtaining increased predictive performance from transparent models in situations where production input vectors are available when building the model. First, labeled training data is used to build a powerful opaque model, called an oracle. Second, the oracle is applied to production instances, generating predicted target values, which are used as labels. Finally, these newly labeled instances are utilized, in different combinations with normal training data, when inducing a transparent model. Experimental results, on 26 UCI data sets, show that the use of oracle coaches significantly improves predictive performance, compared to standard model induction. Most importantly, both accuracy and AUC results are robust over all combinations of opaque and transparent models evaluated. This study thus implies that the straightforward procedure of using a coaching oracle, which can be used with arbitrary classifiers, yields significantly better predictive performance at a low computational cost.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Quinlan, J.R.: C4.5: programs for machine learning. Morgan Kaufmann Publishers Inc., San Francisco (1993)
Breiman, L., Friedman, J., Stone, C.J., Olshen, R.A.: Classification and Regression Trees. Chapman & Hall/CRC (1984)
Cohen, W.W.: Fast effective rule induction. In: Proceedings of the 12th International Conference on Machine Learning, pp. 115–123. Morgan Kaufmann, San Francisco (1995)
Zhu, X.: Semi-supervised learning literature survey. Technical Report 1530, Computer Sciences, University of Wisconsin-Madison (2005)
Joachims, T.: Transductive inference for text classification using support vector machines, pp. 200–209. Morgan Kaufmann, San Francisco (1999)
Andrews, R., Diederich, J., Tickle, A.B.: Survey and critique of techniques for extracting rules from trained artificial neural networks. Knowl.-Based Syst. 8(6), 373–389 (1995)
Craven, M.W., Shavlik, J.W.: Extracting tree-structured representations of trained networks. In: Advances in Neural Information Processing Systems, pp. 24–30. MIT Press, Cambridge (1996)
Thrun, S., Tesauro, G., Touretzky, D., Leen, T.: Extracting rules from artificial neural networks with distributed representations. In: Advances in Neural Information Processing Systems, vol. 7, pp. 505–512. MIT Press, Cambridge (1995)
Zhou, Z.H.: Rule extraction: using neural networks or for neural networks? J. Comput. Sci. Technol. 19(2), 249–253 (2004)
Johansson, U., Niklasson, L.: Evolving decision trees using oracle guides. In: CIDM, pp. 238–244. IEEE, Los Alamitos (2009)
Johansson, U., König, R., Niklasson, L.: Rule extraction from trained neural networks using genetic programming. In: ICANN, supplementary proceedings, pp. 13–16 (2003)
Witten, I.H., Frank, E.: Data Mining: Practical Machine Learning Tools and Techniques, 2nd edn. Morgan Kaufmann, San Francisco (2005)
Breiman, L.: Random forests. Machine Learning 45(1), 5–32 (2001)
Breiman, L.: Bagging predictors. Machine Learning 24(2), 123–140 (1996)
Fawcett, T.: Using rule sets to maximize roc performance. In: IEEE International Conference on Data Mining, ICDM 2001, pp. 131–138. IEEE Computer Society, Los Alamitos (2001)
Asuncion, A., Newman, D.J.: UCI machine learning repository (2007)
Demšar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1–30 (2006)
Friedman, M.: The use of ranks to avoid the assumption of normality implicit in the analysis of variance. Journal of American Statistical Association 32, 675–701 (1937)
Nemenyi, P.B.: Distribution-free multiple comparisons. PhD-thesis. Princeton University (1963)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Johansson, U., Sönströd, C., Löfström, T. (2010). Oracle Coached Decision Trees and Lists. In: Cohen, P.R., Adams, N.M., Berthold, M.R. (eds) Advances in Intelligent Data Analysis IX. IDA 2010. Lecture Notes in Computer Science, vol 6065. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-13062-5_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-13062-5_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-13061-8
Online ISBN: 978-3-642-13062-5
eBook Packages: Computer ScienceComputer Science (R0)