Website Morphing

By John R. Hauser, Glen L. Urban, G. Liberali, Michael Braun. Marketing science (Providence, R.I.), 2009

319 citations recorded by the source corpus.

Virtual advisors often increase sales for those customers who find such online advice to be convenient and helpful. However, other customers take a more active role in their purchase decisions and prefer more detailed data. In general, we expect that websites are more preferred and increase sales if their characteristics (e.g., more detailed data) match customers' cognitive styles (e.g., more analytic). “Morphing” involves automatically matching the basic “look and feel” of a website, not just the content, to cognitive styles. We infer cognitive styles from clickstream data with Bayesian updating. We then balance exploration (learning how morphing affects purchase probabilities) with exploitation (maximizing short-term sales) by solving a dynamic program (partially observable Markov decision process). The solution is made feasible in real time with expected Gittins indices. We apply the Bayesian updating and dynamic programming to an experimental BT Group (formerly British Telecom) website using data from 835 priming respondents. If we had perfect information on cognitive styles, the optimal “morph” assignments would increase purchase intentions by 21%. When cognitive styles are partially observable, dynamic programming does almost as well---purchase intentions can increase by almost 20%. If implemented system-wide, such increases represent approximately $80 million in additional revenue.

Subfields: Artificial Intelligence, Developmental and Educational Psychology

View Paper: https://www.semanticscholar.org/paper/0dab5b4d11620eb410c1e7e3918e3e26d62463ba

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Developmental and Educational Psychology

Citations in the corpus

When Does Retargeting Work? Information Specificity in Online Advertising (2013, background): “Consumer characteristics can be used to identify appropriate segments to customize for, like segmenting on consumers’ cognitive style (Hauser et al., 2009), celebrity aﬃnity (Tucker, 2011), past browsing behavior such as previous ads clicked (Agarwal et al., 2009) or past purchases (Malthouse and…”
Heterogeneity in the Effects of Online Persuasion (2012, background): “Within the marketing research literature, Hauser et al. (2009) developed methods for adapting Web sites to the cognitive style of visitors by measuring and modeling their behavior; they show that this increases the effectiveness of the Web site in persuading visitors to purchase broadband services.”
The potential of generative AI for personalized persuasion at scale (2024, background): “This proportion of significant effects is higher than chance ( t = 8.30, p 0.001).”
Customer Acquisition via Display Advertising Using Multi-Armed Bandit Experiments (2017, methodology): “The Gittins index has been applied recently but sparingly in marketing and management science (Bertsimas and Mersereau 2007; Keller and Oldale 2003; Hauser et al. 2009, 2014; Meyer and Shi 1995; Urban et al. 2014).”
Predictive Analytics in Information Systems Research (2011, unknown): “…the BI question(s) in the original study should be placed last in the questionnaire, to avoid affecting earlier answers (a clickstream-based measure of BI; see Hauser et al. 2009), would be another way of dealing with this issue), and to obtain results that are similar to the prediction context.”
Creating Effective Online Customer Experiences (2018, background): “…elements, star ratings have received most empirical 102 Journal of Marketing 83(2) attention, though studies typically test their effects directly on purchase, without considering underlying mechanisms (Chevalier and Mayzlin 2006; Hauser et al. 2009; Ludwig et al. 2013; Zhu and Zhang 2010).”
Seven cognitive concepts for successful eco-design (2015, background): “…the tools see (Bovea and P!erez-Belis, 2012); for initiatives and efforts taken by different stakeholders to promote sustainable production and consumption see (Barber, 2007); for a special issue on how to achieve eco-design see (Huisingh, 2006; Karlsson and Luttropp, 2006).* Corresponding author.”
Driving Online and Offline Sales: The Cross-Channel Effects of Traditional, Online Display, and Paid Search Advertising (2013, background): “This represents another reason to control for endogeneity, as this model does: the online environment also enables customization of advertisements based on web content (Hauser et al. 2009), whereas traditional advertising such as newspapers and radio cannot be customized.”
Digital Nudging (2016, unknown): “12 For example, Bayesian updating can be used to infer cognitive styles from readily available clickstream data and automatically match customers’ cognitive styles to the characteristics of the website (such as through “mor-phing” 11 ).”
Our Twitter Profiles, Our Selves: Predicting Personality with Twitter (2011, background): “The second insight is that user personality can be easily and effectively predicted from public data, and that suggests future directions in a variety of areas, including : 1) Marketing: Since there is a relationship between marketing strategies and consumer personality [28], [41], one could select ”
Online Trust: State of the Art, New Frontiers, and Research Potential (2009, result): “An example of this cross-disciplinary approach is current research work by the authors of this paper and our MITcolleagues on morphing sites to match cognitive and cultural style (Hauser et al. 2009).”
Artificial Intelligence and Marketing: Pitfalls and Opportunities (2020, unknown): “Academic literature already contains numerous examples of real-time optimization of website designs (Hauser, Liberali, & Urban, 2014; Hauser, Urban, Guy, & Braun, 2009; Urban, Liberali, MacDonald, Bordley, & Hauser, 2014), online advertising (Baardman, Fata, Pani, & Perakis, 2019; Schwartz,…”
Marketing Analytics for Data-Rich Environments (2016, unknown): “Hauser et al. (2009) develop a system for adaptive personalization of website design.”
Explore/Exploit Schemes for Web Content Optimization (2009, background): “By now, multi-armed bandit schemes have found wide applicability in diverse areas like clinical trials [4], marketing [5], management [6], web search [7] and online advertising [8].”