Product Design Selection With Variability in Preferences for an Implicit Value Function
Many existing selection methods require that the Decision Maker (DM) state his/her preferences precisely. However, the DM may not have enough information about the needs of end users thus causing variability in the preferences. To address this problem, we present a method for selection that accounts for variability in the DM’s preferences. Our method is interactive and iterative and assumes only that the preferences of the DM reflect an implicit value function that is quasi-concave and non-decreasing with respect to attributes. Due to the variability, the DM states his/her preferences with a range for Marginal Rate of Substitution (MRS) between attributes at a series of trial designs. The method uses the range of MRS preferences to eliminate “dominated designs” and find a set of “non-eliminated designs”. We present a heuristic to reduce the set of non-eliminated designs and obtain a set of “potentially optimal designs”. The significance of potentially optimal designs is that only one of these designs will be the most preferred for any subset of the range of MRS preferences. We present a payload design selection example to demonstrate and verify that our method indeed finds the set of potentially optimal designs.