Motivated by continued interest within the design community to model design preferences, this paper investigates the question of predicting preferences with particular application to consumer purchase behavior: How can we obtain high prediction accuracy in a consumer preference model using market purchase data? To this end, we employ sparse coding and sparse restricted Boltzmann machines, recent methods from machine learning, to transform the original market data into a sparse and high-dimensional representation. We show that these ‘feature learning’ techniques, which are independent from the preference model itself (e.g., logit model), can complement existing efforts towards high-accuracy preference prediction. Using actual passenger car market data, we achieve significant improvement in prediction accuracy on a binary preference task by properly transforming the original consumer variables and passenger car variables to a sparse and high-dimensional representation.
Skip Nav Destination
ASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference
August 17–20, 2014
Buffalo, New York, USA
Conference Sponsors:
- Design Engineering Division
- Computers and Information in Engineering Division
ISBN:
978-0-7918-4631-5
PROCEEDINGS PAPER
Improving Preference Prediction Accuracy With Feature Learning
Alex Burnap,
Alex Burnap
University of Michigan, Ann Arbor, MI
Search for other works by this author on:
Honglak Lee,
Honglak Lee
University of Michigan, Ann Arbor, MI
Search for other works by this author on:
Richard Gonzalez,
Richard Gonzalez
University of Michigan, Ann Arbor, MI
Search for other works by this author on:
Panos Y. Papalambros
Panos Y. Papalambros
University of Michigan, Ann Arbor, MI
Search for other works by this author on:
Alex Burnap
University of Michigan, Ann Arbor, MI
Yi Ren
University of Michigan, Ann Arbor, MI
Honglak Lee
University of Michigan, Ann Arbor, MI
Richard Gonzalez
University of Michigan, Ann Arbor, MI
Panos Y. Papalambros
University of Michigan, Ann Arbor, MI
Paper No:
DETC2014-35440, V02AT03A012; 9 pages
Published Online:
January 13, 2015
Citation
Burnap, A, Ren, Y, Lee, H, Gonzalez, R, & Papalambros, PY. "Improving Preference Prediction Accuracy With Feature Learning." Proceedings of the ASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. Volume 2A: 40th Design Automation Conference. Buffalo, New York, USA. August 17–20, 2014. V02AT03A012. ASME. https://doi.org/10.1115/DETC2014-35440
Download citation file:
16
Views
Related Proceedings Papers
Related Articles
A Machine Learning Approach to Customer Needs Analysis for Product Ecosystems
J. Mech. Des (January,2020)
Talk to me
Mechanical Engineering (November,2016)
Product Competition Prediction in Engineering Design Using Graph Neural Networks
ASME Open J. Engineering (January,2022)
Related Chapters
Interactive Virtual Prototyping for Improving the Design of Consumer Products
Advances in Computers and Information in Engineering Research, Volume 1
Cyber-Physical Systems, Blended Tool Environments, and Playful Creativity
Advances in Computers and Information in Engineering Research, Volume 2
A New Model for Rockburst Prediction Based on Gaussian Process
Geological Engineering: Proceedings of the 1 st International Conference (ICGE 2007)