This article develops a method to automatically discover and quantify human-interpretable visual characteristics directly from product image data. The method is generative and can create new visual designs spanning the space of visual characteristics. It builds on disentanglement methods in deep learning using variational autoencoders, which aim to discover underlying statistically independent and interpretable visual characteristics of an object. The impossibility theorem in the deep learning literature indicates that supervision with ground truth characteristics would be required to obtain unique disentangled representations. However, these are typically unknown in real-world applications, and are in fact exactly the characteristics that need to be discovered. Extant machine learning methods are unsuitable since they require ground truth labels for each visual characteristic. In contrast, this method postulates the use of readily available product characteristics (such as brand and price) as proxy supervisory signals to enable disentanglement. This method discovers and quantifies human-interpretable and statistically independent characteristics without any specific domain knowledge on the product category. It is applied to a dataset of watches to automatically discover interpretable visual product characteristics, obtain consumer preferences over visual designs, and generate new ideal point designs targeted to specific consumer segments.
AakerJennifer L. (1997), “Dimensions of Brand Personality,” Journal of Marketing Research, 34 (3), 347–56.
2.
AchilleAlessandroSoattoStefano (2018), “Emergence of Invariance and Disentanglement in Deep Representations,” Journal of Machine Learning Research, 19 (1), 1947–80.
3.
BatraRajeevLehmannDonaldSinghDipinder (1993), “The Brand Personality Component of Brand Goodwill: Some Antecedents and Consequences,” in Brand Equity & Advertising: Advertising’s Role in Building Strong Brands. Psychology Press, 83–96.
4.
BelloniAlexandreFreundRobertSeloveMatthewSimesterDuncan (2008), “Optimizing Product Line Designs: Efficient Methods and Comparisons,” Management Science, 54 (9), 1544–52.
5.
BengioYoshuaCourvilleAaronVincentPascal (2013), “Representation Learning: A Review and New Perspectives,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 35 (8), 1798–828.
6.
BerlyneDaniel E. (1971), Aesthetics and Psychobiology. Appleton-Century-Crofts.
7.
BleiDavid M.KucukelbirAlpMcAuliffeJon D. (2017), “Variational Inference: A Review for Statisticians,” Journal of the American Statistical Association, 112 (518), 859–77.
8.
BlochPeter H. (1995), “Seeking the Ideal Form: Product Design and Consumer Response,” Journal of Marketing, 59 (3), 16–29.
9.
BlochPeter H.BrunelFrederic F.ArnoldTodd J. (2003), “Individual Differences in the Centrality of Visual Product Aesthetics: Concept and Measurement,” Journal of Consumer Research, 29 (4), 551–65.
10.
BurgessChristopherHigginsIrinaPalArkaMattheyLoicWattersNickDesjardinsGuillaumeLerchnerAlexander (2018), “Understanding Disentangling in β-VAE,” arXiv, https://doi.org/10.48550/arXiv.1804.03599.
ChenRicky T.Q.LiXuechenGrosseRoger B.DuvenaudDavid K. (2018), “Isolating Sources of Disentanglement in VAEs,” in Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2615–25.
13.
ChengZhaoqiLeeDokyunTambePrasanna (2022), “InnoVAE: Generative AI for Mapping Patents and Firm Innovation,” SSRN (March 1), https://doi.org/10.2139/ssrn.3868599.
14.
ChoHyun YoungLeeSue HyunSainiRitesh (2022), “What Makes Products Look Premium? The Impact of Product Convenience on Premiumness Perception,” Psychology & Marketing, 39 (5), 875–91.
DahanElySrinivasanV. (2000), “The Predictive Power of Internet-Based Product Concept Testing Using Visual Depiction and Animation,” Journal of Product Innovation Management, 17 (2), 99–109.
17.
DeSarboWayne S.RamaswamyVenkatramCohenSteven H. (1995), “Market Segmentation with Choice-Based Conjoint Analysis,” Marketing Letters, 6, 137–47.
18.
DewRyanAnsariAsimToubiaOlivier (2022), “Letting Logos Speak: Leveraging Multiview Representation Learning for Data-Driven Branding and Logo Design,” Marketing Science, 41 (2), 401–25.
19.
DotsonJeffrey P.McDonnell FeitEleaBeltramoMark A. (2024), “Ratings-Informed Probit for Predicting Substitution,” SSRN (January 19), https://doi.org/10.2139/ssrn.2282570.
20.
DuanSunnyMattheyLoicSaraivaAndreWattersNickBurgessChrisLerchnerAlexanderHigginsIrina (2020), “Unsupervised Model Selection for Variational Disentangled Representation Learning,” in International Conference on Learning Representations, https://openreview.net/pdf?id=SyxL2TNtvr.
21.
EastwoodCianWilliamsChristopher K.I. (2018), “A Framework for the Quantitative Evaluation of Disentangled Representations,” in International Conference on Learning Representations, https://openreview.net/forum?id=By-7dz-AZ.
22.
FlemingRoland W. (2014), “Visual Perception of Materials and Their Properties,” Vision Research, 94, 62–75.
23.
FürnkranzJohannesHüllermeierEyke (2010), “Preference Learning and Ranking by Pairwise Comparison,” in Preference Learning. Springer, 65–82.
24.
GoodfellowIanPouget-AbadieJeanMirzaMehdiXuBingWarde-FarleyDavidOzairSherjilCourvilleAaronBengioYoshua (2020), “Generative Adversarial Networks,” Communications of the ACM, 63 (11), 139–44.
25.
GustafssonAndersHerrmannAndreasHuberFrank (2013), Conjoint Measurement: Methods and Applications.Springer Science & Business Media.
26.
HauserJohn R.EggersFelixSeloveMatthew (2019), “The Strategic Implications of Scale in Choice-Based Conjoint Analysis,” Marketing Science, 38 (6), 1059–81.
27.
HauserJohn R.SimmiePatricia (1981), “Profit Maximizing Perceptual Positions: An Integrated Theory for the Selection of Product Features and Price,” Management Science, 27 (1), 33–56.
28.
HauserJohn R.UrbanGlen L. (1977), “A Normative Methodology for Modeling Consumer Response to Innovation,” Operations Research, 25 (4), 579–619.
29.
HeKaimingZhangXiangyuRenShaoqingSunJian (2016), “Deep Residual Learning for Image Recognition,” in Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 770–78.
30.
HeitmannMarkLandwehrJan R.SchreinerThomas F.van HeerdeHarald J. (2020), “Leveraging Brand Equity for Effective Visual Product Design,” Journal of Marketing Research, 57 (2), 257–77.
31.
HigginsIrinaChangLeLangstonVictoriaHassabisDemisSummerfieldChristopherTsaoDorisBotvinickMatthew (2021), “Unsupervised Deep Learning Identifies Semantic Disentanglement in Single Inferotemporal Face Patch Neurons,” Nature Communications, 12 (1), 1–14.
32.
HigginsIrinaMattheyLoicPalArkaBurgessChristopherGlorotXavierBotvinickMatthewMohamedShakirLerchnerAlexander (2017), “β-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework,” in International Conference on Learning Representations, https://openreview.net/forum?id=Sy2fzU9gl.
HoffmanMatthew D.JohnsonMatthew J. (2016), “Elbo Surgery: Yet Another Way to Carve Up the Variational Evidence Lower Bound,” in Workshop in Advances in Approximate Bayesian Inference, https://approximateinference.org/2016/accepted/HoffmanJohnson2016.pdf.
35.
JohnsonRichard M. (1971), “Market Segmentation: A Strategic Management Tool,” Journal of Marketing Research, 8 (1), 13–18.
KarushWilliam (1939), “Minima of Functions of Several Variables with Inequalities as Side Constraints,” MSc dissertation, Department of Mathematics, University of Chicago.
38.
KaulAnilRaoVithala R. (1995), “Research for Product Positioning and Design Decisions: An Integrative Review,” International Journal of Research in Marketing, 12 (4), 293–320.
39.
KhemakhemIlyesKingmaDiederikMontiRicardoHyvarinenAapo (2020), “Variational Autoencoders and Nonlinear ICA: A Unifying Framework,” in Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research, 108, 2207–17.
40.
KimHyunjikMnihAndriy (2018), “Disentangling by Factorising,” Proceedings of the 35th International Conference on Machine Learning, in Proceedings of Machine Learning Research, 80, 2649–58.
LeeJung EunHurSongyeeWatkinsBrandi (2018), “Visual Communication of Luxury Fashion Brands on Social Media: Effects of Visual Complexity and Brand Familiarity,” Journal of Brand Management, 25, 449–62.
47.
LeeJack K.H.SudhirKarunakaranSteckelJoel H. (2002), “A Multiple Ideal Point Model: Capturing Multiple Preference Effects from Within an Ideal Point Framework,” Journal of Marketing Research, 39 (1), 73–86.
48.
LenkPeter J.DeSarboWayne S.GreenPaul E.YoungMartin R. (1996), “Hierarchical Bayes Conjoint Analysis: Recovery of Partworth Heterogeneity from Reduced Experimental Designs,” Marketing Science, 15 (2), 173–91.
49.
LewandowskiDanielKurowickaDorotaJoeHarry (2009), “Generating Random Correlation Matrices Based on Vines and Extended Onion Method,” Journal of Multivariate Analysis, 100 (9), 1989–2001.
50.
LiuLiuDzyaburaDariaMizikNatalie (2020), “Visual Listening In: Extracting Brand Image Portrayed on Social Media,” Marketing Science, 39 (4), 669–86.
51.
LiuYanLiKrista J.ChenHaipengBalachanderSubramanian (2017), “The Effects of Products’ Aesthetic Design on Demand and Marketing-Mix Effectiveness: The Role of Segment Prototypicality and Brand Consistency,” Journal of Marketing, 81 (1), 83–102.
52.
LiuZhiyuanLinYankaiSunMaosong (2020), Representation Learning for Natural Language Processing. Springer Nature.
53.
LiuZiweiLuoPingWangXiaogangTangXiaoou (2015), “Deep Learning Face Attributes in the Wild,” Proceedings of International Conference on Computer Vision.
54.
LocatelloFrancescoBauerStefanLučićMarioRätschGunnarGellySylvainSchölkopfBernhardBachemOlivier (2019), “Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations,” Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research, 97, 4114–24.
55.
LocatelloFrancescoTschannenMichaelBauerStefanRätschGunnarSchölkopfBernhardBachemOlivier (2020), “Disentangling Factors of Variations Using Few Labels,” in International Conference on Learning Representations, https://openreview.net/forum?id=SygagpEKwB.
56.
LundbergScott M.LeeSu-In (2017), “A Unified Approach to Interpreting Model Predictions,” Advances in Neural Information Processing Systems, 30.
MichalekJeremy J.FeinbergFred M.PapalambrosPanos Y. (2005), “Linking Marketing and Engineering Product Design Decisions via Analytical Target Cascading,” Journal of Product Innovation Management, 22 (1), 42–62.
59.
NormanDonald A. (2004), Emotional Design: Why We Love (or Hate) Everyday Things. Civitas Books.
60.
OppenheimerDaniel M.MeyvisTomDavidenkoNicolas (2009), “Instructional Manipulation Checks: Detecting Satisficing to Increase Statistical Power,” Journal of Experimental Social Psychology, 45 (4), 867–72.
61.
OrsbornSethCaganJonathanBoatwrightPeter (2009), “Quantifying Aesthetic Form Preference in a Utility Function,” Journal of Mechanical Design, 131 (6), 061001.
62.
RaoVithala R. (2014), Applied Conjoint Analysis. Springer.
63.
RolinekMichalZietlowDominikMartiusGeorg (2019), “Variational Autoencoders Pursue PCA Directions (by Accident),” in 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 12398–407.
64.
SchölkopfBernhardLocatelloFrancescoBauerStefanKeNan RosemaryKalchbrennerNalGoyalAnirudhBengioYoshua (2021), “Toward Causal Representation Learning,” Proceedings of the IEEE, 109 (5), 612–34.
65.
SimonsonAlexSchmittBernd H. (1997), Marketing Aesthetics: The Strategic Management of Brands, Identity, and Image.Simon and Schuster.
SylcottBrianOrsbornSethCaganJonathan (2016), “The Effect of Product Representation in Visual Conjoint Analysis,” Journal of Mechanical Design, 138 (10), 101104.
68.
TractinskyNoamKatzAdi S.IkarDror (2000), “What Is Beautiful Is Usable,” Interacting with Computers, 13 (2), 127–45.
69.
WardEllaYangSongRomaniukJenniBealVirginia (2020), “Building a Unique Brand Identity: Measuring the Relative Ownership Potential of Brand Identity Element Types,” Journal of Brand Management, 27, 393–407.
70.
WatanabeSatosi (1960), “Information Theoretical Analysis of Multivariate Correlation,” IBM Journal of Research and Development, 4 (1), 66–82.
71.
WedelMichelKamakuraWagner A. (2000), Market Segmentation: Conceptual and Methodological Foundations.Springer Science & Business Media.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
