Prediction of Sequential Values for Debt Recovery

  • Tomasz Kajdanowicz
  • Przemysław Kazienko
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5856)

Abstract

The concept of new approach for debt portfolio pattern recognition is presented in the paper. Aggregated prediction of sequential repayment values over time for a set of claims is performed by means of hybrid combination of various machine learning techniques, including clustering of references, model selection and enrichment of input variables with prediction outputs from preceding periods. Experimental studies on real data revealed usefulness of the proposed approach for claim appraisals. The average accuracy was over 93%, much higher than for simplifier methods.

Keywords

financial pattern recognition prediction repayment prediction claim appraisal competence regions modeling 

References

  1. 1.
    Aburto, L., Weber, R.: A Sequential Hybrid Forecasting System for Demand Prediction. In: Perner, P. (ed.) MLDM 2007. LNCS (LNAI), vol. 4571, pp. 518–532. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  2. 2.
    Ali, S., Smith, K.: On learning algorithm selection for classification. Applied Soft Computing 6(2), 119–138 (2006)CrossRefGoogle Scholar
  3. 3.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, Heidelberg (2006)MATHCrossRefGoogle Scholar
  4. 4.
    Chou, C.-H., Lin, C.-C., Liu, Y.-H., Chang, F.: A prototype classification method and its use in a hybrid solution for multiclass pattern recognition. Pattern Recognition 39(4), 624–634 (2006)MATHCrossRefGoogle Scholar
  5. 5.
    Dietterich, T.G.: Approximate statistical tests for comparing supervised classification learning algorithms. Neural Computation 10(7), 1895–1923 (1998)CrossRefGoogle Scholar
  6. 6.
    Eastwood, M., Gabrys, B.: Building Combined Classifiers, A chapter in Knowledge Processing and Reasoning for Information Society. In: Nguyen, N.T., Kolaczek, G., Gabrys, B. (eds.), pp. 139–163. EXIT Publishing House, Warsaw (2008)Google Scholar
  7. 7.
    Gabrys, B., Ruta, D.: Genetic algorithms in classifier fusion. Applied Soft Computing 6(4), 337–347 (2006)CrossRefGoogle Scholar
  8. 8.
    Garcia-Pedrajas, N., Ortiz-Boyer, D.: Boosting k-nearest neighbor classifier by means of input space projection. Expert Systems with Applications 36, 10570–10582 (2009)CrossRefGoogle Scholar
  9. 9.
    Kajdanowicz, T., Kazienko, P.: Hybrid Repayment Prediction for Debt Portfolio. In: ICCCI 2009. LNCS (LNAI), vol. 5796, pp. 850–857. Springer, Heidelberg (2009)Google Scholar
  10. 10.
    Kazienko, P., Musiał, K., Kajdanowicz, T.: Multidimensional Social Network and Its Application to the Social Recommender System. IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans (in press, 2009)Google Scholar
  11. 11.
    Keles, A., Kolcak, M., Keles, A.: The adaptive neuro-fuzzy model for forecasting the domestic debt. Knowledge-Based Systems 21(8), 951–957 (2008)CrossRefGoogle Scholar
  12. 12.
    Kuncheva, L.: Combining Pattern Classifiers. Methods and Algorithms. John Wiley & Sons, Inc., Chichester (2004)MATHCrossRefGoogle Scholar
  13. 13.
    Lin, P.-C., Chen, J.-S.: A genetic-based hybrid approach to corporate failure prediction. International Journal of Electronic Finance 2(2), 241–255 (2008)CrossRefGoogle Scholar
  14. 14.
    Pelleg, D., Moore, A.W.: X-means: Extending K-means with Efficient Estimation of the Number of Clusters. In: International Conference on Machine Learning, pp. 727–734. Morgan Kaufmann Publishers Inc., San Francisco (2000)Google Scholar
  15. 15.
    Ravi, V., Kurniawan, H., Nwee, P., Kumar, R.: Soft computing system for bank performance prediction. Applied Soft Computing 8(1), 305–315 (2008)CrossRefGoogle Scholar
  16. 16.
    Rud, O.: Data Mining Cookbook. Modeling Data for Marketing, Risk, and Customer Relationship Management. John Wiley & Sons, Inc., Chichester (2001)Google Scholar
  17. 17.
    Swanson, N.R., White, H.: A model selection approach to assessing the information in the term structure using linear model and the artificial neural network. Journal of Business and Economics Statistics 13, 265–275 (1995)CrossRefGoogle Scholar
  18. 18.
    Zurada, J., Lonial, S.: Comparison of The Performance of Several Data Mining Methods For Bad Debt Recovery In The Healthcare Industry. The Journal of Applied Business Research 21(2), 37–53 (2005)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Tomasz Kajdanowicz
    • 1
  • Przemysław Kazienko
    • 1
  1. 1.Wrocław University of TechnologyWrocławPoland

Personalised recommendations