Stars vs lemons. Survival analysis of peer-to peer marketplaces: the case of Airbnb

Abstract

[eng] This paper analyses the determinants of listings' survival on peer-to-peer marketplaces. Working on a dataset of Airbnb listings in Ibiza, we implement survival analysis to estimate the relationship between listings' key attributes and the probability to leave the platform. In addition, we highlight the importance of user-generated content to reduce the asymmetry of information and prevent adverse selection. Results confirm that listings' characteristics, location, degree of local competition and hosts' managerial skills, significantly affect the survival chance. Moreover, we found that low quality listings (proxied by the customer rating) are intended to disappear: the reviewing system successfully signals the quality on this market and drive the market selection process.