Abstract
Given an input \(x_i\) and an arbitrary output \(c_j,\) a classification algorithm usually works by estimating the probability of \(x_i\) being related to \(c_j\) (i.e., class membership probability). Well calibrated classification algorithms are those able to produce functions that provide accurate estimates of class membership probabilities, that is, the estimated probability \(\hat{p}(c_j|x_i)\) is close to \(p(c_j|\hat{p}(c_j|x_i)),\) which is the true, (unknown) empirical probability of \(x_i\) being related to output \(c_j\) given that the probability estimated by the classification algorithm is \(\hat{p}(c_j|x_i).\) Calibration is not a necessary property for producing an accurate approximation of the target function, and, thus, most of the research has focused on direct accuracy maximization strategies rather than on calibration. However, non-calibrated functions are problematic in applications where the reliability associated with a prediction must be taken into account (i.e., cost-sensitive classification , cautious classifications etc.). In these applications, a sensible use of the classification algorithm must be based on the reliability of its predictions (Veloso et al. Calibrated lazy associative classification, Inform Sci, 2009), and thus, the algorithm must produce well calibrated functions. In this chapter we introduce calibrated associative classification algorithms .
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
\(v\) can take the values 0 (the prediction is wrong) or 1 (otherwise), as shown in step 6 of Algorithm 14.
- 2.
For each experiment, predictions were sorted from the most reliable to the least reliable.
- 3.
The basic idea is to solicit a person \(x_i\) for whom the expected return \(\hat{p}(\hbox{donate}|x_i)y(x_i)\) is greater than the cost of mailing the solicitation.
References
Boser, B., Guyon, I., Vapnik, V.: A training algorithm for optimal margin classifiers. In: Proceedings of the Annual Conference on Computational Learning Theory (COLT), pp. 144–152. Springer (1992)
Cestnik, B.: Estimating probabilities: a crucial task in machine learning. In: Proceedings of the European Conference on Artificial Intelligence (ECAI), pp. 147–149 (1990)
Chang, C.-C., Lin, C.-J.: LIBSVM: a library for support vector machines. Available at http://www.csie.ntu.edu.tw/∼cjlin/papers/libsvm.pdf (2001)
Cohen, I., Goldszmidt, M.: Properties and benefits of calibrated classifiers. In: Proceedings of the European Conference on Principles of Data Mining and Knowledge Discovery (PKDD), pp. 125–136. Springer (2004)
Cussens, J.: Bayes and pseudo-bayes estimates of conditional probabilities and their reliability. In: Proceedings of the European Conference on Machine Learning (ECML), pp. 136–152. Springer (1993)
DeGroot, M., Fienberg, S.: The comparison and evalution of forecasters. Statistician 32, 12–22 (1982)
Fayyad, U., Irani, K.: Multi interval discretization of continuous-valued attributes for classification learning. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pp. 1022–1027 (1993)
Platt, J.: Probabilistic outputs for support vector machines and comparison to regularized likelihood methods. Adv. Large Margin Classif. 61–74 (1999)
Quinlan, J.: C4.5: Programs for Machine Learning. Morgan Kaufmann, San Francisco (1993)
Rissanen, J.: Modeling by shortest data description. Automatica 14, 465–471 (1978)
Zadrozny, B., Elkan, C.: Obtaining calibrated probability estimates from decision trees and naive bayesian classifiers. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 609–616. IEEE Computer Society (2001)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2011 Adriano Veloso
About this chapter
Cite this chapter
Veloso, A., Meira, W. (2011). Calibrated Associative Classification. In: Demand-Driven Associative Classification. SpringerBriefs in Computer Science. Springer, London. https://doi.org/10.1007/978-0-85729-525-5_7
Download citation
DOI: https://doi.org/10.1007/978-0-85729-525-5_7
Published:
Publisher Name: Springer, London
Print ISBN: 978-0-85729-524-8
Online ISBN: 978-0-85729-525-5
eBook Packages: Computer ScienceComputer Science (R0)