Investigating Some Classification Methods To Evaluate Efficiency Results: A Case Study By Using Conjoint Analysis

Year 2019, Volume: 22 Issue: 3, 687 - 694, 01.09.2019

Ezgi Nazman Hülya Olmuş Semra Erbaş

https://doi.org/10.2339/politeknik.459097

Abstract

 ABSTRACT

A new product development is an
important step of competitive advantage for producers. There are several issues
to be considered during developing a new product from the point of view of both
customers and producers. Costumer preferences require a great deal of
consideration in order to able to address consumer needs in marketing. Conjoint
Analysis (CA) is often preferred to reveal utility of the new product by means
of customer preferences order on a certain type of product or service which is
widely used to reveal how people value different attributes on a new product
concept. On the other hand, Data Envelopment Analysis (DEA) can be used to
determine efficient product concepts considering both utility and development
expenses of the products. In this study, CA was applied with the aim of
determining utilities of new car concepts. Then, DEA was used to reveal
efficient and inefficient car concepts on a real data set. Finally, most
commonly used classification methods Linear Discriminant Analysis (LDA), binary
Logistic Regression (LR) and Artificial Neural Networks (ANN) were compared to
validate the results of DEA in terms of accuracy.  

Keywords

Conjoint analysis, data envelopment analysis, linear discriminant analysis, binary logistic regression, artificial neural networks

Investigating Some Classification Methods To Evaluate Efficiency Results: A Case Study By Using Conjoint Analysis

Abstract

A new product development is an
important step of competitive advantage for producers. There are several issues
to be considered during developing a new product from the point of view of both
customers and producers. Costumer preferences require a great deal of
consideration in order to able to address consumer needs in marketing. Conjoint
Analysis (CA) is often preferred to reveal utility of the new product by means
of customer preferences order on a certain type of product or service which is
widely used to reveal how people value different attributes on a new product
concept. On the other hand, Data Envelopment Analysis (DEA) can be used to
determine efficient product concepts considering both utility and development
expenses of the products. In this study, CA was applied with the aim of
determining utilities of new car concepts. Then, DEA was used to reveal
efficient and inefficient car concepts on a real data set. Finally, most
commonly used classification methods Linear Discriminant Analysis (LDA), binary
Logistic Regression (LR) and Artificial Neural Networks (ANN) were compared to
validate the results of DEA in terms of accuracy.  

Keywords

Conjoint analysis, data envelopment analysis, linear discriminant analysis, binary logistic regression, artificial neural networks

References

• [1] Chaney, P.K. and Devinney, T.M., “New product innovations and stock price performance”, Journal of Business, Finance and Accounting, 19: 677-695, (1992).
• [2] Tone, K., “A slacks-based measure of efficiency in data envelopment analysis”, European Journal of Operational Research, 130: 498-509, (2001).
• [3] Baker, N.R., Green, S.G., and Bean, A.S., “Why R&D projects succed or fail”, Research Management, 6: 29-34, (1986).
• [4] Crawford, C.M., “New product failure rates: a reprise”, Research Management, 30: 20-24, (1987).
• [5] Mishra, S., Kim, D. and Lee, D.H., “Factors affecting new product success: cross country comprisons”. Journal of Product Innovation Management, 13: 530-550, (1996).
• [6] Booz, Allen and Hamilton, “New product management for the 1980s”, New York: Booz Allen Hamilton Inc., Chapter 2, (1982).
• [7] Urban, G.L. and Hauser, J.R., “Design and Marketing of New Products”, 2nd Edition. Upper Saddle River, NJ:Prentice Hall, (1993).
• [8] Salhieh, S. M. and Al-Harris, M.Y. “New product concept selection: an integrated approach using data envelopment analysis (DEA) and conjoint analysis (CA)”, International Journal of Engineering and Technology, 3: 44–55, (2014).
• [9] Rao, V.R., “Applied Conjoint Analysis”, Springer Verlag Berlin Heidelberg, (2014).
• [10] Green, P.E., “On the design of choice experiments involving multifactor alternatives”. Journal of Consumer Research, 1: 61-68, (1974).
• [11] Leber, M., Bastic, M., Mavric, M. and Ivanisevic, A., “Value analysis as an integral part of new product development, Procedia Engineering, 69: 90-98, (2014).
• [12] Pelsmaeker, S.D., Schouteten, J.J., Lagast, S., Dewettinck, K. and Gellynck, X., “Is taste the key driver for consumer preference? A conjoint analysis study”, Food Quality and Preference, 62: 323-331, (2017).
• [13] Wu, W.Y. and Liao, Y.K., “Applying conjoint analysis to evaluate consumer preferences toward subcompact cars”, Expert Systems with Applications, 41: 2782-2792, (2014).
• [14] Niazi, A., Dai, J.S., Balabani, S. and Seneviratne, L., “Product cost estimation:Technique classification and methodology review. Journal of Manufacturing Science and Engineering, 128: 563-575, (2006).
• [15] Charnes, A., Cooper, W. and Rhodes, E., “Measuring the efficiency of decision making units”, European Journal of Operational Research, 2: 429-444, (1978).
• [16] Büschken, J., “How data envelopment analysis reveals brand advertising efficiency”, GFK Marketing Intelligence Review, 1: 36-45, (2009).
• [17] Donthu, N., Hershberger, E. and Osmonbekov, T., “Benchmarking marketing productivity using data envelopment analysis”, Journal of Business Reasearch, 58(11): 1474-1482, (2005).
• [18] Li, W.H., Liang, L. and Cook, W.D., “Measuring efficiency with products, by-products and parent offspring relations: A conditional two-stage DEA model”, Omega, 68: 95-104, (2017).
• [19] Duda, R.O., Hart, P.E. and Stork, D.G., Pattern Classification, Wiley InterScience, (2000).
• [20] McLachlan, G., “Discriminant Analysis and Statistical Pattern Recognition”, Wiley-InterScience, (2004).
• [21] Fisher, R.A., “The use of multiple measurements in taxonomic problems”, Annals of Human Genetics, 7: 179-188, (1936).
• [22] Shyu, J. C. and Liou, H. Y., “The financial distress prediction model under consideration of business cycle and industry factors – the application of logistic regression model and DEA-DA model. Journal of Risk Management, 12: 157-183, (2010).
• [23] Ting, H. M., Lee, T. F., Cho, M. Y., Chao, P. J., Chang, C. M., Chen, L. C. and Fang, F.M., “Comparison of neural network and logistic regression methods to predict xerostomia after radiotherapy”, International Journal of Biomedical and Biological Engineering, 7(7): (2013).
• [24] Sharma, P. and Kaur, M., “Classification in pattern recognition: a review”, International Journal of Advanced Research in Computer Science and Software Engineering, 3(4): (2013).
• [25] Erdoğan, C., “Tüketicinin Otomobil Tercihinin Konjoint analizi ile Belirlenmesi”, Graduate School of Natural and Applied Science, Department of Statistics, Gazi University, (2006).
• [26] Zhu, W., Zeng, N. and Wang, N., “Health Care and Life Sciences”, NESUG, (2010).
• [27] Wong, H. B. and Lim, G. H., “Measures of Diagnostic Accuracy: Sensitivity, Specificity, PPV and NPV”, Proceedings of Singapore Healthcare, 20(4): (2011).