Selecting Appropriate Variables for DEA Using Genetic Algorithm (GA) Search Procedure

R. Madhanagopal^1, and R. Chandrasekaran¹

¹Department of Statistics, Madras Christian College, Chennai, Tamil Nadu, India

Cite this paper:
R. Madhanagopal and R. Chandrasekaran. Selecting Appropriate Variables for DEA Using Genetic Algorithm (GA) Search Procedure. International Journal of Data Envelopment Analysis and *Operations Research*. 2014; 1(2):28-33. doi: 10.12691/ijdeaor-1-2-3

Abstract

Data envelopment analysis (DEA) is one of the most powerful non-parametric methods to assess the relative efficiency of each Decision making units (DMU’s). Its simplicity in computation and mathematical programming technique attracted many researchers and at the same time DEA is more sensitive to variables considered. It uses multiple inputs and outputs for efficiency analysis but does not provide any guidelines in choosing variables and hence researchers selected their own number of input and output variables using several methods. Usage of all the variables in DEA is not sensible, since irrelevant variables will reduce the efficiency power. Therefore, selection of appropriate or best set of variables for input and output is needed but it’s one of the crucial tasks in DEA. In the present paper, a new approach of selecting appropriate set of variables using genetic algorithm are discussed and applied to Indian banking sector.

Keywords:
data envelopment analysis variable selection genetic algorithm Indian banking sector efficiency analysis

This work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

References:

[1]	Dyson, R. G., Allen, R., Camanho, A. S., Podinovski, V. V., Sarrico, C. S and Shale, E.A., Pitfalls and protocols in DEA, European Journal of Operational Research, 132(2), 245-259, 2001.
[2]	Galagedera, D.U. A and Silvapulle, P., Experimental Evidence on Robustness of Data Envelopment Analysis, Journal of the Operational Research Society, 54, 654-660, 2003.
[3]	Sexton, T. R., Silkman, R. H and Hogan A. J., Data Envelopment Analysis: Critique and Extensions, New Directions for Program Evaluation, 32, 73-105, 1986.
[4]	Smith, P., Model Misspecification in Data Envelopment Analysis, Annals of Operations Research, 73, 233-252, 1997.
[5]	Natarja, N. R and Johnson, A. J., Guidelines for Using Variable Selection Technique in Data Envelopment Analysis, European Journal of Operation Research, 215, 662-669, 2011.
[6]	Ruiz J.L.; Pastor, J.; Sirvent, I., A statistical test for radial DEA models, Operations Research, 50(4), 728-735, 2002.
[7]	Jenkins, L and Anderson, M., A Multivariate Statistical Approach to Reducing the Number of Variables in Data Envelopment Analysis, European Journal of Operational Research, 147(1), 51-61, 2003.
[8]	Ruggiero, J., Impact Assessment of Input Omission on DEA, International Journal of Information Technology and Decision Making, 4(3), 359-368, 2005.
[9]	Morita, H and Haba,Y., Variable Selection in Data Envelopment Analysis Based on External Information, Proceedings of the Eighth Czech-Japan Seminar on Data Analysis and Decision Making Under Uncertainty, 181-187, 2005.
[10]	Edirisinghe, N. C. P and Zhang, X., Generalized DEA Model of Fundamental Analysis and Its Application to Portfolio Optimization, Journal of Banking and Finance, 31, 311-335, 2007.
[11]	Morita. H and Avkiran. N. K., Selecting Inputs and Outputs in Data Envelopment Analysis by Designing Statistical Experiments, Journal of Operation Research Society of Japan, 52 (2), 163-173, 2009.
[12]	Coley, A. D., An Introduction to Genetic Algorithm for scientists and Engineers, World Scientific, Singapore, 1999,188.
[13]	Pham, D.T and Karaboga, D., Intelligent Optimization Techniques, Springer, London, Great Britain, 261, 2000.
[14]	Holger F., Feature Selection for Support Vector Machines by Means of Genetic Algorithm, Diploma Thesis in Computer Science, Philipps Univesity, Marburg, 2002.
[15]	Tang, K.S., Man, K.F., Kwong, S and HE, Q., Genetic Algorithm and Its Applications, IEEE Signal Processing Magazine, 22-37, 1996.
[16]	Kim, H. S and Cho, S. B., An Efficient Genetic Algorithm with Less Fitness Evolution by Clustering, Proceedings of the IEEE Congress on Evolutionary Computation Seoul, Korea, May, 27-30, 887-894, 2001.
[17]	Melanie M., An Introduction to Genetic Algorithms, A Bradford Book, The MIT Press, London, 1998.
[18]	Trevino, V and Falciani, F., GALGO: an R Package for Multivariate Variable Selection Using Genetic Algorithms, Bioinformatics, 22(9), 1154-1156, 2006.
[19]	Cadima, J., Cerderira, J,O., Silva, P.D and Minhoto, M., The subselect R package, (2012). Available at: http://cran.r-project.org/web/packages/subselect/subselect.pdf.
[20]	Cadima, J., Cerdeira J.O and Minhoto, M., Computational aspects of algorithms for variable selection in the context of principal components, Computational statistics and Data Analysis, 47, 225-236, 2004.
[21]	McCabe, G. P., Principal variables, Technometrics, vol.26 (2), pp.137-144, 1984.
[22]	McCabe, G. P., Prediction of Principal Components by Variables Subsets, Technical Report 86-19, Department of Statistics, Purdue University, 1986.
[23]	Cadima, J and Jolliffe, I. T., Variable Selection and the Interpretation of Principal Subspaces, Journal of Agricultural, Biological, Environment Statistics, 6(1), 62-79, 2001.
[24]	Sealey, C and Lindley J. T., Inputs, outputs and a theory of production and cost at depository financial institution, Journal of Finance, 32, 1251-1266, 1977.
[25]	Berger, A. N and Humphrey, D. B., Efficiency of Financial Institutions: International Survey and Directions for Future Research, European Journal of Operational Research, 98, 175-212, 1997.
[26]	Colwell and Davis., Output and Productivity in Banking, Scandinavian Journal of Economics, 94 (Supplement), 111-129, 1992.
[27]	Favero, C.A. and Papi, L., Technical efficiency and scale efficiency in the Italian banking sector, Applied Economics, 27(4): 385-395, 1995.
[28]	Cooper, W. W., Seiford, L. M and Tone, K., Data Envelopment Analysis, A Comprehensive Text with Models, Applications, References and DEA-Solver Software, Second Edition. USA: Springer, 2007.