Designing Optimal Products: Algorithms and Systems
The high cost of a product failure makes it imperative for a company to assess the market penetration of a new product at its early design. In this context, the Optimal Product Line Design problem was formulated thirty five years ago, and remains a significant research topic in the area of quantitative marketing until today. In this chapter we provide a brief description of the problem, which belongs to the class of NP-hard problems, and review the optimization algorithms that have been applied to it. The performance of the algorithms is evaluated, and the best two approaches are applied to simulated data, as well as a real world scenario. Emphasis is placed on Genetic Algorithms, since the results of the study indicate them as the approach that better fits to the specific marketing problem. Finally, the relevant marketing systems that deal with the problem are presented, and their pros and cons are discussed.
KeywordsGenetic Algorithm Product Line Market Share Optimal Product Attribute Level
Unable to display preview. Download preview PDF.
- Belloni, A., Freund, R., Selove, M., Simester, D.: Optimizing Product Line Designs: Efficient Methods and Comparisons. Working Paper, MIT Sloan School of Management (2005)Google Scholar
- Holland, J.H.: Adaptation in Natural and Artificial systems. The University of Michigan Press, Ann Arbor (1975)Google Scholar
- Kotler, P., Armstrong, G.: Principles of Marketing, 12th edn. Prentice Hall, New Jersey (2008)Google Scholar
- McFadden, D.: Conditional Logit Analysis of Qualitative Choice Behaviour. In: Zaremka, P. (ed.) Frontiers in Econometrics, Academic Press, N.Y. (1973)Google Scholar
- Radcliffe, N.J.: Forma analysis and random respectful recombination. In: Proceedings of the 4th International Conference on Genetic Algorithms (1991)Google Scholar
- Sawtooth Software, Advanced Simulation Module (ASM) for product optimization. Sawtooth Software technical paper series (2003)Google Scholar
- Steiner, W., Hruschka, H.: A probabilistic one-step approach to the optimal product line design problem using conjoint and cost data. Review of Marketing Science working papers 1(4), 1–36 (2002)Google Scholar
- Steiner, W., Hruschka, H.: Generic Algorithms for product design: how well do they really work? International Journal of Market Research 45(2), 229–240 (2003)Google Scholar
- Zufryden, F.: A conjoint measurement-based approach for optimal new product design and market segmentation. In: Shocker, A.D. (ed.) Analytical approaches to product and marketing planning, Marketing Science Institute, Cambridge (1977)Google Scholar