Sensory informed design: An effective clustering of incomplete block consumer data

Sara King/ August 11, 2013/ Oral Presentation/ 0 comments

Consumer research has advanced its business relevance through segmenting consumer populations into clusters based upon liking. Products designed to meet the expectations and desires of specific niche markets have demonstrated commercial success. The studies that are typically designed to reveal liking segments require a relatively large number of products and a large sample of consumers in a complete block design.

A study of 12 Cabernet Sauvignon wines was conducted using over 600 consumers recruited and tested

for liking  of 3 of the 12 wines in a BIB design. The data were subsequently analyzed for liking clusters with missing data replaced with the consumer’s individual mean. Four liking clusters successfully demonstrated different sensory liking profiles. The method was not robust. Consequently, a research program was initiated to develop a systematic approach to building designs using sensory information to ensure contrast.

The Sensory Informed Design (SID) approach was applied to a 12-present-6 study of white breads. All breads were profiled using calibrated descriptive analysis. The results of the DA were used to construct a balanced experimental design (12:6) that included two smaller-sized SIDs (12:3 and 12:4) nested within the experiment to evaluate the efficiency and stability. Consumer data (n=400) were collected and missing data were imputed as part of a novel EM approach for mixture model-based clustering; the one latent factor model gave a six-cluster solution.

In 2012, a study of whole grain breads was conducted with 570 consumers using an improved SID of 16:6, with nested designs of 16:3 and 16:4. The nested designs demonstrated stable clusters, provided internal validation and supported the results of previous work. The application of SID, EM imputation and model-based cluster analysis can dramatically reduce the resources required to conduct large category appraisals and deliver effective consumer clusters.

Findlay, C.J., Browne, R.P., McNicholas, P.D., & Castura, J. C. (2013). Sensory informed design: An effective clustering of incomplete block consumer data. In: 10th Pangborn Sensory Science Symposium. 11-15 August. Rio de Janeiro, Brazil.


Share this Post

Leave a Comment

Your email address will not be published. Required fields are marked *