Designing Ranking Systems for Hotels on Travel Search Engines by Mining User-Generated and Crowdsourced Content

User-Generated Content (UGC) on social media platforms is changing the way consumers shop for goods. However, current product search engines fail to effectively leverage information created across diverse social media platforms. Moreover, current ranking algorithms in these product search engines tend to induce consumers to focus on one single product characteristic dimension (e.g., price, star rating, etc). This largely ignores consumers’ multi-dimensional preferences for products. In this paper, we propose to generate a ranking system that recommends products providing the best value for money on an average. The key idea is that products that provide consumers with a higher surplus should be ranked higher on the screen in response to consumer queries. Our study is instantiated on a unique dataset of US hotel reservations over a 3-month period from Travelocity which is supplemented with data from various social media sources using techniques from text mining, image classification, social geo-tagging, human annotations and geo-mapping. We propose a random coefficient hybrid structural model, taking into consideration the two sources of consumer heterogeneity introduced by the different travel occasions and different hotel characteristics. Based on the estimates from the model, we infer the economic impact of various location and service characteristics of hotels. We then propose a new hotel ranking system based on the average utility gain that a consumer gets by staying in a particular hotel. By doing so, we can provide customers with the “best-value" hotels early on, and thereby improve the quality of local searches for such hotels. Our lab experiments in six major cities, using ranking comparisons from several thousand users, validate that our ranking system is superior to existing systems on several travel search engines. On a broader note, the objective of this paper is to illustrate how user-generated content (UGC) on the Internet can be mined and incorporated into a demand estimation model, and how UGC can be leveraged to generate a new ranking system in product search engines to improve the quality of choices available to consumers online. Our inter-disciplinary approach can provide insights for using text mining and image classification techniques in economics and marketing research. 1 We thank Susan Athey, Peter Fader, Brett Gordon, John Hauser, Francois Moreau, Aviv Nevo, Duncan Simester, Minjae Song, Daniel Spulber, Catherine Tucker, and Hal Varian for extremely helpful comments that have significantly improved the paper. We also thank participants at the 2011 Toulouse Conference on the Economics of the Internet and Software, 2010 NBER IT Economics & Productivity Workshop, 2010 Workshop on Digital Business Models, 2010 Marketing Science Conference, 2010 Searle Research Symposium on the Economics and Law of Internet Search at NorthWestern University, Customer Insights Conference at Yale University, 2010 Statistical Challenges in Ecommerce Research (SCECR) conference, 2009 Workshop on Information Technology and Systems (WITS), 2009 Workshop on Economics and Information Systems and seminar participants at Columbia, Harvard, George Mason, Georgia Tech, MIT, University of Maryland at College Park, Seoul National University, Temple University, and University of Minnesota for helpful comments. Anindya Ghose and Panos Ipeirotis acknowledge the financial support from National Science Foundation CAREER Awards IIS-0643847 and IIS-0643846, respectively. Support was also provided through a MSI-Wharton Interactive Media Grant (WIMI) and a Microsoft Virtual Earth Award. The authors thank Travelocity for providing the data and Uthaman Palaniappan for research assistance.