Improving Design Preference Prediction Accuracy Using Feature Learning

Quantitative preference models are used to predict customer choices among design alternatives by collecting prior purchase data or survey answers. This paper examines how to improve the prediction accuracy of such models without collecting more data or changing the model. We propose to use features as an intermediary between the original customer-linked design variables and the preference model, transforming the original variables into a feature representation that captures the underlying design preference task more effectively. We apply this idea to automobile purchase decisions using three feature learning methods (principal component analysis (PCA), low rank and sparse matrix decomposition (LSD), and exponential sparse restricted Boltzmann machine (RBM)) and show that the use of features offers improvement in prediction accuracy using over 1 million real passenger vehicle purchase data. We then show that the interpretation and visualization of these feature representations may be used to help augment data-driven design decisions. [DOI: 10.1115/1.4033427]

[1]  Alex Burnap,et al.  Quantification of perceptual design attributes using a crowd , 2013 .

[2]  Masashi Sugiyama,et al.  A Fast Augmented Lagrangian Algorithm for Learning Low-Rank Matrices , 2010, ICML.

[3]  D. McFadden,et al.  MIXED MNL MODELS FOR DISCRETE RESPONSE , 2000 .

[4]  Wei Chen,et al.  INCORPORATING CUSTOMER PREFERENCES AND MARKET TRENDS IN VEHICLE PACKAGE DESIGN , 2007, DAC 2007.

[5]  Wei Chen,et al.  Incorporating Social Impact on New Product Adoption in Choice Modeling: A Case Study in Green Vehicles , 2012, DAC 2012.

[6]  Wei Chen,et al.  Enhancing Discrete Choice Demand Modeling for Decision-Based Design , 2003 .

[7]  Daniel D. Frey,et al.  Engineering design thinking, teaching, and learning , 2006 .

[8]  Richard Gonzalez,et al.  On the Shape of the Probability Weighting Function , 1999, Cognitive Psychology.

[9]  Geoffrey E. Hinton.  Training Products of Experts by Minimizing Contrastive Divergence , 2002, Neural Computation.

[10]  Christopher Hoyle,et al.  Decision-Based Design: An Approach for Enterprise-Driven Engineering Design , 2013 .

[11]  Paul Smolensky,et al.  Information processing in dynamical systems: foundations of harmony theory , 1986 .

[12]  John R. Hauser,et al.  Fast Polyhedral Adaptive Conjoint Estimation , 2002 .

[13]  Jonathan Cagan,et al.  Quantifying Aesthetic Form Preference in a Utility Function , 2008 .

[14]  Yun Fu,et al.  Low-Rank and Sparse Modeling for Visual Analysis , 2014, Springer International Publishing.

[15]  Donald Geman,et al.  Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Giorgos Zacharia,et al.  Generalized robust conjoint estimation , 2005 .

[17]  Wei Chen,et al.  An Approach to Decision-Based Design With Discrete Choice Analysis for Demand Modeling , 2003 .

[18]  Stephen P. Boyd,et al.  Proximal Algorithms , 2013, Found. Trends Optim..

[19]  Conrad S. Tucker,et al.  Automated Discovery of Lead Users and Latent Product Features by Mining Large Scale Social Media Networks , 2015 .

[20]  Shuicheng Yan,et al.  Scalable Low-Rank Representation , 2014, Low-Rank and Sparse Modeling for Visual Analysis.

[21]  Olivier Toubia,et al.  Eliciting Consumer Preferences Using Robust Adaptive Choice Questionnaires , 2008, IEEE Transactions on Knowledge and Data Engineering.

[22]  Allan D. Shocker,et al.  Consideration set influences on consumer decision-making and choice: Issues, models, and suggestions , 1991 .

[23]  Mark Fuge,et al.  A Scalpel Not a Sword: On the Role of Statistical Tests in Design Cognition , 2015 .

[24]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[25]  Wei Chen,et al.  Decision-Based Design: Integrating Consumer Preferences into Engineering Design , 2012 .

[26]  Eric T. Bradlow,et al.  Beyond conjoint analysis: Advances in preference measurement , 2008 .

[27]  Geoffrey E. Hinton,et al.  Restricted Boltzmann machines for collaborative filtering , 2007, ICML '07.

[28]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[29]  Tara N. Sainath,et al.  FUNDAMENTAL TECHNOLOGIES IN MODERN SPEECH RECOGNITION Digital Object Identifier 10.1109/MSP.2012.2205597 , 2012 .

[30]  D. Norman.  Emotional design : why we love (or hate) everyday things , 2004 .

[31]  Zaïd Harchaoui,et al.  A Machine Learning Approach to Conjoint Analysis , 2004, NIPS.

[32]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[33]  John R. Hauser,et al.  Conjoint Analysis, Related Modeling, and Applications , 2004 .

[34]  Amy L. Parsons,et al.  Emotional Design: Why We Love (or Hate) Everyday Things , 2006 .

[35]  M. Pontil,et al.  A Convex Optimization Approach to Modeling Consumer Heterogeneity in Conjoint Estimation , 2007 .

[36]  Erin F. MacDonald,et al.  Market-System Design Optimization With Consider-Then-Choose Models , 2014 .

[37]  Honglak Lee,et al.  Unsupervised learning of hierarchical representations with convolutional deep belief networks , 2011, Commun. ACM.

[38]  Wei Chen,et al.  A Data-Driven Network Analysis Approach to Predicting Customer Choice Sets for Choice Modeling in Engineering Design , 2015 .

[39]  Jeremy J. Michalek,et al.  Towards Understanding the Role of Interaction Effects in Visual Conjoint Analysis , 2013, DAC 2013.

[40]  Jeremy J. Michalek,et al.  Linking Marketing and Engineering Product Design Decisions via Analytical Target Cascading , 2005 .

[41]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[42]  Kemper Lewis,et al.  The use of analytics in the design of sociotechnical products , 2014, Artificial Intelligence for Engineering Design, Analysis and Manufacturing.

[43]  Yanxin Pan,et al.  Balancing design freedom and brand recognition in the evolution of automotive brand styling , 2016 .

[44]  Kurt Becker,et al.  Engineering Design Thinking. , 2013 .

[45]  P. Lenk,et al.  Hierarchical Bayes Conjoint Analysis: Recovery of Partworth Heterogeneity from Reduced Experimental Designs , 1996 .

[46]  Léon Bottou,et al.  Large-Scale Machine Learning with Stochastic Gradient Descent , 2010, COMPSTAT.

[47]  Honglak Lee,et al.  Sparse deep belief net model for visual area V2 , 2007, NIPS.

[48]  Panos Y. Papalambros,et al.  Perceptual Attributes in Product Design: Fuel Economy and Silhouette-Based Perceived Environmental Friendliness Tradeoffs in Automotive Vehicle Design , 2012 .

[49]  Yi Ren,et al.  When Crowdsourcing Fails: A Study of Expertise on Crowdsourced Design Evaluation , 2015 .

[50]  Wei Chen,et al.  Decision Making in Engineering Design , 2006 .

[51]  Claudia Baier,et al.  Principles Of Optimal Design Modeling And Computation , 2016 .

[52]  John Rust,et al.  A nested logit model of automobile holdings for one vehicle households , 1985 .

[53]  Jitesh H. Panchal.  USING CROWDS IN ENGINEERING DESIGN – TOWARDS A HOLISTIC FRAMEWORK , 2015 .