| There are few decisions more critical to firm success than the development of its product or service offerings. Here, the relative cost impact of potential offerings must be considered, as well as the desires of key customer constituents. This research applies a novel heuristic technique called ant colony optimization (ACO) toward the product design (PD) problem. Here, algorithms based on the behavior of social insects are applied to a consumer decision model.; Prior research has considered optimal product planning using consumer preference data from a single point in time. Consumer preferences are affected by prior experience and choices. Consequently, for this application, consumer preferences are modeled as evolving over time.; ACO heuristic methods are efficient at searching through a vast decision space. When compared to complete enumeration of all possible solutions, ACO is found to generate near-optimal results to the problem. By using these methods, consumer preference data can be used as a critical input for a decision support system (DSS) designed to facilitate the development of product offerings that have the best potential of satisfying the most customers.; This dissertation finds that ACO algorithms are very robust when dealing with uncertain market conditions, such as the uncertainty of consumer preference shifts over a product's life cycle. Additionally, this dissertation finds that ACO algorithms are successful when dealing with problems of increasing complexity. Uncertainty and complexity are of considerable import to PD problem modelers as future consumer desires for product characteristics cannot be definitively judged, and as product designing becomes increasingly more complex.; Contrary to wide acceptance, where local-probability updates, or pheromone evaporation, lead to high quality ant-generated decisions, this dissertation could find no statistically significant support for this assertion. On the other hand, global-probability updates, or pheromone deposit, were found to have a statistically significant impact on ACO performance. This finding is in concert with the extant literature that states that the positive reinforcement-quality of ants leads to superior decision making. |
