Skip to main content
SpringerLink
Log in

Commercial Mortgage Default: A Comparison of Logit with Radial Basis Function Networks

  • Published:
The Journal of Real Estate Finance and Economics Aims and scope Submit manuscript

Abstract

This article explores the use of artificial neural networks in the modeling of foreclosure of commercial mortgages. The study employs a large set of individual loan histories previously used in the literature of proportional hazard models on loan default. Radial basis function networks are trained (estimated) using the same input variables as those used in the logistic. The objective is to demonstrate the use of networks in forecasting mortgage default and to compare their performance with that of the logistic benchmark in terms of prediction accuracy. Neural networks are shown to be superior to the logistic in terms of discriminating between “good” and “bad” loans. The study performs sensitivity analysis on the average loan and offers suggestions on further improving prediction of defaulting loans.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  • American Council of Life Insurance. (1995). “Quarterly Survey of Mortgage Loan Delinquencies and Foreclosures,” Investment Bulletin, 1289 (March 31).

  • Berndt, E. K., B. H. Hall, R. E. Hall, and J. A. Hausman. (1974). “Estimation and Inference in Nonlinear Structural Models,” Annals of Economic and Social Measurement 3/4, 653-665.

    Google Scholar 

  • Collins, E., S. Ghosh, and C. Scofield. (1988). “An Application of Multiple Neural Network Learning System to Emulation of Mortgage Underwriting Judgements,” Proceedings of the IEEE International Conference on Neural Networks 2, 495-566.

    Google Scholar 

  • Dutta, S., and S. Shekhar. (1988). “Bond Rating: A Non-Conservative Application of Neural Networks,” Proceedings of the IEEE International Conference on Neural Networks 2, 443-450.

    Google Scholar 

  • Foster, C., and R. Van Order. (1984). “An Option-Based Model of Mortgage Default,” Housing Finance Review 13, 351-372.

    Google Scholar 

  • Foster, C., and R. Van Order. (1985). “FHA Terminations: A Prelude to Mortgage Pricing,” Journal of the American Real Estate and Urban Economics Association 13(3), 292-316.

    Google Scholar 

  • Hutchinson, J., A. Lo, and T. Poggio. (1994). “A Nonparametric Approach to Pricing and Hedging Derivative Securities Via Learning Networks,” Journal of Finance 49, 851-889.

    Google Scholar 

  • Kau, J. B., D. C. Keenan, W. J. Muller III, and J. T. Epperson. (1990). “Pricing Commercial Mortgages and Their Mortgage-Backed Securities,” Journal of Real Estate Finance and Economics 2, 333-356.

    Google Scholar 

  • Leonard, J. A., and M. A. Kramer. (1991). “Radial Basis Functions for Classifying Process Faults,” IEEE Control Systems (April).

  • Moody, J., and C. J. Darken. (1989). “Fast Learning of Locally Tuned Processing Units,” Neural Computation 1, 281-294.

    Google Scholar 

  • Quigley, J., and R. Van Order. (1994). “Explicit Tests of Contingent Claims Models of Mortgage Default,” Working paper, University of California, Berkeley.

    Google Scholar 

  • Refenes, A. (ed.). (1995). Neural Networks in the Capital Markets. New York: Wiley.

    Google Scholar 

  • Reilly, D. L., E. Collins, C. Scofield, and S. Ghosh. (1991). “Risk Assessment of Mortgage Applications with a Neural Network System: An Update as the Test Portfolio Ages,” Proceedings of the IEEE International Conference of Neural Networks 2, 479-482.

    Google Scholar 

  • Tam, K. Y., and Y. M. Kiang. (1992). “Managerial Applications of Neural Networks: The Case of Bank Failures,” Institute of Management Sciences 38(7), 926-947.

    Google Scholar 

  • Titman, S., and W. Torrus. (1989). “Valuing Commercial Mortgages: An Empirical Investigation of the Contingent-Claims Approach to Pricing Risky Debt,” Journal of Finance 44(2), 345-373.

    Google Scholar 

  • Vandell, Kerry D. (1992). “Predicting Commercial Mortgage Foreclosure Experience,” Journal of the American Real Estate and Urban Economics Association 20(1), 345-373.

    Google Scholar 

  • Vandell, K. D., W. Barnes, D. Hartzell, D. Kraft, and W. Wendt. (1993). “Commercial Mortgage Defaults: Proportional Hazard Estimation Using Individual Loan Histories,” Journal of the American Real Estate and Urban Economics Association 21(4), 451-480.

    Google Scholar 

  • White, H., A. Gallant, K. Hornik, M. Stinchcombe, and J. Wooldridge. (1992). Artificial Neural Networks: Approximation and Learning Theory. Oxford: Blackwell.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. National Bank of Greece, Eolou 86, Athens, Greece, 102-32

    Athanasios Episcopos

  2. Asset/Liability Management, Federal Home Loan Mortgage Corporation, 8200 Jones Branch Drive, McLean, VA, 22102

    Andreas Pericli

  3. Advanta Mortgage Corporation, 850 Ridgeview Dr., Horsham, PA, 19044

    Jianxun Hu

Authors
  1. Athanasios Episcopos
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Andreas Pericli
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jianxun Hu
    View author publications

    You can also search for this author in PubMed Google Scholar

Rights and permissions

Reprints and permissions

About this article

Cite this article

Episcopos, A., Pericli, A. & Hu, J. Commercial Mortgage Default: A Comparison of Logit with Radial Basis Function Networks. The Journal of Real Estate Finance and Economics 17, 163–178 (1998). https://doi.org/10.1023/A:1007701420328

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1007701420328

Search

Navigation