Blackboard | 中文版 | Mail | OA

Seminars & Announcements Present Location:HomeSeminars & Announcements

Marketing Department's Lecture


Speaker:李虹爽(Fisher College of Business, The Ohio State University)

Time:14:00 Nov.13 2017

Place:Room706,Mingde Bussiness Building


In gathering information for an intended purchase decision, consumers submit search phrases to online search engines. These search phrases directly express the consumers’ need in their own language and thus provide valuable information to marketing managers. Interpreting consumers’ search phrases renders a better understanding of consumers’ intention, which is critical for marketing success. In this paper, we develop a model to connect the latent topics embedded in consumers’ search phrases to their website visits and purchase decisions. Our model captures the dynamics and heterogeneity in the latent topics searched by consumers along their path to purchase. Additionally, we apply topic models, which have been traditionally used to analyze long text documents, to typically short search phrases. Using a unique dataset with more than 8,000 individual consumers’ search phrases on various search engines that led to a hospitality firm's website visits, our model identifies four latent topics: “loyalty”, “luxury”, “convenience”, and “location”. Compared to a model with existing semantic heuristics or a model without any usage of the textual information in consumers’ search phrases, our model provides better evaluation of consumers’ current stages on their path to purchase and achieves much better predictive accuracy. Our method can be used by marketing managers to extract structured information out of consumers’ search phrases and better design their offerings and promotions to target the right consumers.


Alice Li received her Ph.D. in Marketing from the University of Maryland – College Park in 2014.
Her primary research areas are marketing measurement, attribution models, multichannel marketing, and search engine marketing. The quantitative methods she uses include Bayesian statistics, econometrics, machine learning, and field experiments.
She has worked with Marriott International, Adobe Systems, and Efficient Frontier to develop statistical models in the context of attribution models, multichannel marketing and search engine marketing. Her work has been recognized with Adobe Research Award, Marketing Science Institute Research Grant, the MSI Alden G. Clayton Dissertation Proposal Competition Winner, and University of Maryland Distinguished Dissertation Award. Her research has been published in journals including the Journal of Marketing Research, Marketing Science, International Journal of Research in Marketing, and Journal of Behavioral Decision Making.