Journal
PRODUCTION AND OPERATIONS MANAGEMENT
Volume 31, Issue 1, Pages 194-217Publisher
WILEY
DOI: 10.1111/poms.13495
Keywords
robust optimization; min-max relative regret; product line design; conjoint analysis; risk management
Ask authors/readers for more resources
The study explores robustness approaches to decision making in the face of uncertainties, focusing on protecting against downside risk and maximizing potential opportunities. It examines the trade-offs between minimizing ex post regrets and minimizing downside risks, proposing a method that combines both approaches for better decision-making in product line design. The research shows that no single robustness approach dominates the other, emphasizing the importance of balancing upside regret and downside risk.
Many decisions must be made before relevant uncertainties are revealed; hence robustness approaches to decision making are often considered. There are two major approaches to robustness in the literature: (i) maximizing the value of the worst outcome and (ii) minimizing the maximum ex post regret of the decision. While the first approach seeks the best worst-case outcome, it may result in substantial opportunity losses relative to the ex post optimal decision; this is particularly critical in new product design decisions as it leaves the leading firm exposed to a late entrant who designs its products after uncertainties are resolved. The second approach seeks to minimize these ex post opportunity losses, but it may expose the decision maker to greater downside risk, that is, lower outcome in the worst case. Most studies have examined one of these approaches in isolation; in contrast, in this study, we explore the trade-offs between protecting upside regret and downside risk with a focus on a product line design (PLD) problem, which relies greatly on conjoint analysis data. The PLD problem may suffer from significant uncertainty in the partworth utilities which define the attribute-level consumer preferences on a product for different population segments. Our numerical experiments, based on a real conjoint data set, show that neither robustness approaches dominates the other and hence our proposed approach uses both. We construct a Min-Value vs. Max-Relative-Regret efficient frontier to narrow down the PLD choice and propose a metric to quantify the trade-offs and finalize the selection.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available