Preference Elicitation and Modeling

Keywords: active learning, adaptive choice-based-conjoint, crux and sentinel attributes, deep learning, efficient global optimization, elicitation query, feature learning, group generalized biary search, interactive GAs, multidisciplinary, preference construction, preference inconsistency, privacy safeguards, shape preference, support vector machine, visual aesthetics, visual attraction

There is much hype around the term “big data.” There are many opportunities for inferring data-driven design decisions via large data sets and algorithms able to handle these data through recent advances in parallel CPU and GPU-processing architectures. We used databases made up of variables representing millions of previous customers and the products they actually purchased, and creating preference prediction models that can be tested using held-out portions of the database.

Our models are focused on “content-based” preference prediction rather than “collaborative filtering.” In other words, we look at variables describing you as a person and the product as an identity that interacts with you meaningfully (e.g., with your personal values), and then try to predict future product purchases. Contrast this with the case of upvotes and downvotes from your favorite online music provider, in which just your upvote pattern history is enough to infer your preferences apart from the underlying variable correlations that are unknown.

The family of models we employ are referred to as "feature learning," and have shown impressive results by breaking records in the image and speech recognition fields (e.g., Siri voice recognition). These advances have been enabled by learning correlations amongst large swaths of raw data to build higher-level data that better capture the underlying phenomena. At the same time, the amount of market data generated relating customers and their purchases is growing exponentially. Can we learn more discriminative features amongst this market data so we can better predict which customer will prefer which design concept?

For more information contact: Alex Burnap, Yanxin Pan

Kelly, J., Wakefield, G. H., and Papalambros, P. Y., "The Development of a Tool for the Preference Assessment of the Visual Aesthetics of an Object Using Interactive Genetic Algorithms", Generative Art Conference, Milan, Italy, December 13-15, 2006.

Kelly, J. and Papalambros, P. Y., "Use of Visual Aesthetic Preference Information in Product Design", International Conference on Engineering Design, Paris, France, August 28-31, 2007.

MacDonald, E., Gonzalez, R., and Papalambros, P., "Preference Inconsistency in Multidisciplinary Design Decision Making", ASME 2007 International Design Engineering Technical Conferences Computers and Information in Engineering Conference, Las Vegas, Nevada, September 4-7, 2007, doi: 10.1115/DETC2007-35580.

MacDonald, E., Gonzalez, R., and Papalambros, P. Y., "The Construction of Preferences for Crux and Sentinel Product Attributes", International Conference on Engineering Design, Paris, France, August 28-31, 2007.

MacDonald, E., Gonzalez, R., and Papalambros, P., "Preference Inconsistency in Multidisciplinary Design Decision Making", Journal of Mechanical Design, Vol. 131, No. 3, 2009. doi: 10.1115/DETC2007-35580.

Ren, Y. and Papalambros, P. Y., "Design Preference Elicitation, Derivative-Free Optimization and Support Vector Machine Search", 2010 ASME International Design Engineering Technical Conferences, Montreal, Canada, August 15-18, 2010, doi: 10.1115/DETC2010-28475.

MacDonald, E. F., Gonzalez, R., and Papalambros, P. Y., "The Construction of Preferences for Crux and Sentinel Product Attributes", Journal of Engineering Design, Vol. 2, No. 6, 2010, 609-626. doi: 10.1080/09544820802132428. See also the 2007 conference version.

Kelly, J. C., Wakefield, G. H., and Papalambros, P. Y., "Evidence for Using Interactive Genetic Algorithms in Shape Preference Assessment",International Journal of Product Development, Vol. 13, No. 2, 2010, 168-184. doi: 10.1504/IJPD.2011.038870.

Ren, Y. and Papalambros, P. Y., "Design Preference Elicitation: Exploration and Learning", Proceedings of the International Conference on Engineering Design, Copenhagen, Denmark, 2011.

Ren, Y. and Papalambros, P. Y., "A Design Preference Elicitation Query as an Optimization Process", Journal of Mechanical Design, Vol. 133, No. 11, 2011. doi: 10.1115/1.4005104.

Ren, Y. and Papalambros, P. Y., "Design Preference Elicitation Using Efficient Global Optimization", Proceedings of the ASME 2011 International Design Engineering Technical Conferences & Computers and Information in Engineering Conference, Washington D.C., 2011. doi: 10.1115/DETC2011-48316.

Kelly, J. C., Maheut, P., Petiot, J. F., and Papalambros, P. Y., "Incorporating User Shape Preference in Engineering Design Optimization", Journal of Engineering Design,2011. doi: 10.1080/09544821003662601.

Ren, Y. and Papalambros, P. Y., "On Design Preference Elicitation with Crowd Implicit Feedback", Proceedings of the ASME 2012 International Design Engineering Technical Conferences, Chicago, IL, Aug 12-Aug 15, 2012, doi: 10.1115/DETC2012-70605.

Ren, Y. and Papalambros, P. Y., "On the Use of Active Learning in Engineering Design", Proceedings of the ASME 2012 International Design Engineering Technical Conferences, Chicago, IL, Aug 12-Aug 15, 2012, doi: 10.1115/DETC2012-70624.

Ren, Y., Scott, C., and Papalambros, P. Y., "A Scalable Preference Elicitation Algorithm Using Group Generalized Binary Search", Proceedings of the ASME 2013 International Design Engineering Technical Conferences, Portland, Aug 4-Aug 7, 2013. doi: 10.1115/DETC2013-13059.

Ren, Y. and Papalambros, P. Y., "Enhanced Adaptive Choice-Based Conjoint Analysis Incorporating Engineering Knowledge", Proceedings of the ASME 2014 International Design Engineering Technical Conferences, Buffalo, Aug 17-Aug 20, 2014. doi: 10.1115/DETC2014-34790.

Burnap, A., Ren, Y., Lee, H., Gonzalez, R., and Papalambros, P. Y., "Improving Preference Prediction Accuracy with Feature Learning",Proceedings of the ASME 2014 International Design Engineering Technical Conferences, Buffalo, Aug 17-Aug 20, 2014.

Burnap, A., Pan, Y., Liu, Y., Ren, Y., Lee, H., Gonzalez, R., and Papalambros, P. Y., "Improving Design Preference Prediction Accuracy using Feature Learning", Journal of Mechanical Design, Vol. 138, No. 7, 2016, 071404. doi: 10.1115/1.4033427.

Pan, Y., Burnap, A., Liu, Y., Lee, H., Gonzalez, R., and Papalambros, P. Y., "A Quantitative Model For Identifying Regions Of Design Visual Attraction And Application To Automobile Styling", Proceedings of the DESIGN 2016 14th International Design Conference, Dubrovnik, Croatia, May 16-May 19, 2016.

Burnap, A. and Papalambros, P. Y., "Design Preference Prediction with Data Privacy Safeguards: A Preliminary Study", Proceedings of the ASME 2017 International Design Engineering Technical Conferences, Cleveland, OH, Aug 6-Aug 9, 2017. doi: 10.1115/DETC2017-68366