Abstract
The paper is motivated by a ranking problem arising e.g. in financial institutions. This ranking problem is reduced to a system of inequalities that may be solved by applying the perceptron learning theorem. Under certain additional assumptions the associated probabilities are derived by exploiting Bayes’ Theorem. It is shown that from these a posteriori probabilities the original classifier may be recovered. On the other hand, assuming that perfect classification is possible, a maximum likelihood solution is derived from the classifier. Some experimental results are given.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Banking Committee on Banking Supervision: International Convergence of Capital Measurements and Capital Standards, A Revised Framework, Bank for International Settlements (June 2004), http://www.bis.org/publ/bcbsca.htm
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1998)
Cover, T.M.: Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition. IEEE Trans. on Electronic Computers 14 (1965)
Devroye, L., Györfi, L., Lugosi, G.: A Probabilistic Theory of Pattern Recognition. Springer, Heidelberg (1996)
Episcopos, A., Pericli, A., Hu, J.: Commercial Mortgage Default: A Comparison of the Logistic Model with Artificial Neural Networks. In: Proceedings of the Third International Conference on Neural Networks in the Capital Markets, London, England (1995)
Falkowski, B.-J.: Lernender Klassifikator, Offenlegungsschrift DE 101 14874 A1, Deutsches Patent- und Markenamt, München (Learning Classifier, Patent Number DE 101 14874 A1, German Patent Office, Munich) (2002)
Falkowski, B.-J.: Assessing Credit Risk Using a Cost Function. In: Proceedings of the Intl. Conference on Fuzzy Information Processing, vol. II, Tsinghua University Press, Springer (2003)
Falkowski, B.-J.: Scoring Systems, Classifiers, Default Probabilities, and Kernel Methods. In: Kantardzic, M., Nasraoui, O., Milanova, M. (eds.) Proceedings of the 2004 Intl. Conference on Machine Learning and Applications (ICMLA 2004), IEEE Catalog Number: 04EX970 (2004)
Gallant, S.I.: Perceptron-based Learning Algorithms. IEEE Transactions on Neural Networks I(2) (1990)
Hand, D.J., Henley, W.E.: Statistical Classification Methods in Consumer Credit Scoring: a Review. J.R. Statist. Soc. A 160(Part 3) (1997)
Haykin, S.: Neural Networks, 2nd edn. Prentice-Hall, Englewood Cliffs (1999)
Knuth, D.E.: The Art of Computer Programming, 2nd edn. Fundamental Algorithms, vol. 1 (1973)
Müller, M., Härdle, W.: Exploring Credit Data. In: Bol, G., Nakhneizadeh, G., Racher, S.T., Ridder, T., Vollmer, K.-H. (eds.) Credit Risk-Measurement, Evaluation, and Management, Physica-Verlag (2003)
Ripley, B.D.: Pattern Recognition and Neural Networks. Oxford University Press, Oxford (1998)
Shadbolt, J., Taylor, J.G. (eds.): Neural Networks and the Financial Markets. Springer, Heidelberg (2002)
Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press, Cambridge (2004)
Vapnik, V.N.: Statistical Learning Theory. John Wiley & Sons, Chichester (1998)
Wong, S.K.M., Ziarko, W., Wong, P.C.N.: Generalized Vector Space Model in Information Retrieval. In: Proceedings of the 8th ACM SIGIR Conference on Research and Development in Information Retrieval, USA, (1985)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Falkowski, BJ. (2005). Ranking Functions, Perceptrons, and Associated Probabilities. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2005. Lecture Notes in Computer Science(), vol 3683. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11553939_159
Download citation
DOI: https://doi.org/10.1007/11553939_159
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28896-1
Online ISBN: 978-3-540-31990-0
eBook Packages: Computer ScienceComputer Science (R0)