Marketing managers are often tasked with assessing the future profitability, sales and market share of new products and modifications to existing products.  One of the best assessment methods is a marketing research technique called conjoint analysis.  Conjoint analysis works by simulating real purchase decisions that customers make. In a typical study, respondents are given a simple exercise that asks them to select or rank their most preferred choice from a selection of alternatives. Using hierarchical Bayesian mathematics, the results are analyzed and a predictive model is developed.   Once the model is developed, a number of what-if scenarios can be run to determine the optimal set of features, the best pricing strategy and the estimated market share that your new product will achieve.  In addition, the model can also predict how your competitors may react and influence your market position.

There are a variety of conjoint analysis techniques including MaxDiff, Choice Based Conjoint (CBC) and Adaptive Conjoint Analysis (ACA).  Each type of conjoint analysis offers its own unique advantage. When the right method is used, conjoint analysis is an extremely effective marketing research technique for new product development.   Leading Marketing Research firms like THE MARKETING ANALYSTS offer a broad range of conjoint analysis techniques to meet your unique needs.  However, conjoint analysis should only be used when the following assumptions are met:
1. A product (good or service) must be able to be described or represented by a set of attributes that are mutually exclusive.
2. Consumers view the product as a combination of attributes that can be exchanged for others. An example is the inclusion of an additional product feature in exchange for a higher price.
3. The total utility (value) of the product being analyzed is equivalent to the sum of the individual utilities of each attribute. It is important to realize that several common forms of “conjoint analysis” do not consider nonlinear relationships, particularly interactions among attributes. Ignoring interaction will lead to bad research results.
4. Products with a greater overall utility are more attractive than products with lower total utility scores.
When these assumptions are met, conjoint analysis provides quantifiable and actionable data that include:
• Relative importance for each product attribute
• Most desirable level of each product attribute
• Potential market share for the product
• Market segmentation information