Skip to main content
Log in

An additive utility mixed integer programming model for nonlinear discriminant analysis

  • Theoretical Paper
  • Published:
Journal of the Operational Research Society

Abstract

Mathematical programming (MP) discriminant analysis models can be used to develop classification models for assigning observations of unknown class membership to one of a number of specified classes using values of a set of features associated with each observation. Since most MP discriminant analysis models generate linear discriminant functions, these MP models are generally used to develop linear classification models. Nonlinear classifiers may, however, have better classification performance than linear classifiers. In this paper, a mixed integer programming model is developed to generate nonlinear discriminant functions composed of monotone piecewise-linear marginal utility functions for each feature and the cut-off value for class membership. It is also shown that this model can be extended for feature selection. The performance of this new MP model for two-group discriminant analysis is compared with statistical discriminant analysis and other MP discriminant analysis models using a real problem and a number of simulated problem sets.

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

Access this article

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  • Despotis DK and Zopounidis C (1995). Building additive utilities in the presence of non-monotonic preferences. In: Paradalos P.M., Siskos Y. and Zopounidis C. (eds). Advances in Multicriteria Analysis. Kluwer: Dordrecht, The Netherlands, pp. 101–114.

    Chapter  Google Scholar 

  • Doumpos M, Zanakis SH and Zopounidis C (2001). Multicriteria preference disaggregation for classification problems with an application to global investing risk. Decis Sci 32: 333–385.

    Article  Google Scholar 

  • Duarte Silva AP and Stam A (1994). Second order mathematical programming formulations for discriminant analysis. Eur J Opl Res 72: 4–22.

    Article  Google Scholar 

  • Freed N and Glover F (1981). A linear programming approach to the discriminant problem. Decis Sci 12: 68–74.

    Article  Google Scholar 

  • Glen JJ (1999). Integer programming methods for normalisation and variable selection in mathematical programming discriminant analysis models. J Opl Res Soc 50: 1043–1053.

    Article  Google Scholar 

  • Glen JJ (2001). Classification accuracy in discriminant analysis: A mixed integer programming approach. J Opl Res Soc 52: 328–339.

    Article  Google Scholar 

  • Glen JJ (2003). An iterative mixed integer programming method for classification accuracy maximizing discriminant analysis. Comput Opns Res 30: 181–198.

    Article  Google Scholar 

  • Glen JJ (2004). Dichotomous categorical variable formation in mathematical programming discriminant analysis models. Nav Res Logis 51: 575–596.

    Article  Google Scholar 

  • Glen JJ (2005). Mathematical programming models for piecewise-linear discriminant analysis. J Opl Res Soc 56: 331–341.

    Article  Google Scholar 

  • Hand DJ (1997). Construction and Assessment of Classification Rules. Wiley: Chichester, UK.

    Google Scholar 

  • Huberty CJ (1994). Applied Discriminant Analysis. Wiley: New York.

    Google Scholar 

  • Jacquet-Lagrèze E (1995). An application of the UTA discriminant model for the evaluation of R&D Projects. In: Paradalos P.M., Siskos Y. and Zopounidis C. (eds). Advances in Multicriteria Analysis. Kluwer: Dordrecht, The Netherlands, pp. 203–211.

    Chapter  Google Scholar 

  • Jacquet-Lagrèze E and Siskos J (1982). Assessing a set of additive utility functions for multicriteria decision making, the UTA method. Eur J Opns Res 10: 151–164.

    Article  Google Scholar 

  • Keeney RL and Raiffa H (1993). Decisions with Multiple Objectives: Preferences and Value Tradeoffs. Cambridge University Press: Cambridge, UK.

    Book  Google Scholar 

  • Lemeshow S, Teres D, Avrunin JS and Pastides H (1988). Predicting the outcome of intensive care unit patients. J Am Stat Assoc 83: 348–356.

    Article  Google Scholar 

  • Lewis EM (1992). An Introduction to Credit Scoring. Fair Isaac: San Rafael, CA.

    Google Scholar 

  • Markowski EP and Markowski CA (1985). Some difficulties and improvements in applying linear programming formulations to the discriminant problem. Decis Sci 16: 237–247.

    Article  Google Scholar 

  • Pavur R (2002). A comparative study of the effect of the position of outliers on classical and nontraditional approaches to the two-group classification problem. Eur J Opl Res 136: 603–613.

    Article  Google Scholar 

  • Stam A (1997). Nontraditional approaches to statistical classification: Some perspectives on L p-norm methods. Ann Opns Res 74: 1–36.

    Article  Google Scholar 

  • Stam A and Joachimsthaler EA (1990). A comparison of a robust mixed-integer approach to existing methods for establishing classification rules for the discriminant problem. Eur J Opl Res 46: 113–122.

    Article  Google Scholar 

  • Stam A and Ragsdale CT (1992). On the classification gap in mathematical-programming-based approaches to the discriminant problem. Nav Res Logis 39: 545–559.

    Article  Google Scholar 

  • Williams HP (1993). Model Building in Mathematical Programming. Wiley: Chichester, UK.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to J J Glen.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Glen, J. An additive utility mixed integer programming model for nonlinear discriminant analysis. J Oper Res Soc 59, 1492–1505 (2008). https://doi.org/10.1057/palgrave.jors.2602485

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1057/palgrave.jors.2602485

Keywords

Navigation