Exploiting Socio-Economic Models for Lodging Recommendation in the Sharing Economy

Recent years have witnessed the emergence of sharing economy marketplaces, which enable users to share goods and services in a peer-to-peer fashion. A prominent example in the travel industry is Airbnb, which connects guests with hosts, allowing both to exchange cultural experiences in addition to the economic transaction. Nonetheless, Airbnb guest profiles are typically sparse, which limits the applicability of traditional lodging recommendation approaches. Inspired by recent socio-economic analyses of repurchase intent behavior on Airbnb, we propose a context-aware learning-to-rank approach for lodging recommendation, aimed to infer the user's perception of several dimensions involved in choosing which lodging to book. In particular, we devise features aimed to capture the user's price sensitivity as well as their perceived value of a particular lodging, the risk involved in choosing it rather than other available options, the authenticity of the cultural experience it could provide, and its overall perception by other users through word of mouth. Through a comprehensive evaluation using publicly available Airbnb data, we demonstrate the effectiveness of our proposed approach compared to a number of alternative recommendation baselines, including a simulation of Airbnb's own recommender.