Radha would like to thank Ajeshkumar Vijaydas for contributing this column.


In last month’s column, I examined the process of developing scoring models for multistage cross selling in the insurance industry. This month we will develop choice models for arriving at suitable product combinations to help cross-sell.




Conjoint analysis is used to study consumers’ product preferences and simulate consumer choice. Conjoint analysis is also used to study the factors that influence consumers’ purchasing decisions. Products possess attributes such as price, color, ingredients, guarantee, environmental impact and predicted reliability. Consumers typically do not have the option of buying the product that is best in every attribute, particularly when one of those attributes is price. As a result, consumers are forced to make trade-offs as they decide which products to purchase.


Conjoint analysis is based on a main-effects analysis-of-variance model. Subjects provide data about their preferences for hypothetical products defined by attribute combinations. Conjoint analysis decomposes the judgment data into components, based on qualitative attributes of the products. A numerical part-worth utility value is computed for each level of each attribute. Large part-worth utilities are assigned to the most preferred levels, and small part-worth utilities are assigned to the least preferred levels. The attributes with the largest part-worth utility range are considered the most important in predicting preference. Conjoint analysis is a statistical model with an error term and a loss function.


Here, the nonmetric conjoint analysis is used for solving the problems; a monotone transformation of rating variable is requested instead of an identity transformation. An example of the formulated attributes (only four products identified as profitable) and levels is given in Figure 1.



In the next part of this example, PROC TRANSREG is used to perform a non-metric conjoint analysis of the problem. Initially, the fractional-factorial design is generated using the auto call macro %mktruns (4 4 4 2). Part of SAS code for the process is given in Figure 2 with part-worth utilities in Figure 3.




Figure 3, it can be seen that product is the important attribute with 64.5 percent and product 3 is most preferred over product 1, product 2 and product 4. Plan is the next preferred attribute with 35 percent. Similarly in the plan category, PPO-HS-H is most preferred plan. Price attributes have no impact. Finally, co-payment is the least-preferred attribute with 0.50 percent. Among this, co-payment “N/A” is preferred over the “yes” category. Part of the predicted utilities for each combination and the rank of each combination are given in Figure 4.



Predicted utilities shows the utility of each combination of levels. This describes the customer’s best choice with rank and utilities.


Metric and nonmetric conjoint analyses are widely applicable in customer-response modeling as well as customer-buying behavioral analysis. This helps the marketing teams to identify customer’s best choice in buying patterns. It also helps ease marketing efforts for new product launches by companies.

Register or login for access to this item and much more

All Information Management content is archived after seven days.

Community members receive:
  • All recent and archived articles
  • Conference offers and updates
  • A full menu of enewsletter options
  • Web seminars, white papers, ebooks

Don't have an account? Register for Free Unlimited Access