Airbnb listings’ performance: determinants and predictive models

The present study analyzes Airbnb listings’ performance in terms of occupancy rate, number bookings and revenue, by employing data mining methodologies. research objective is twofold, to highlight the strongest determinants that influence customer’s purchase intentions propose reliable models capable predicting performance. set refers market Thessaloniki, Greece contains explanatory variables about hosts, lodgings, rules quests’ ratings. Elaborated inducers derived from Artificial Intelligence are used as analytical tools. interpretable models, sensitivity analysis a proposed complex wrapper estimator provide evidence significance specific central role host. Random Forest outperforms its competitors suitable classifier for domain. results conclusions can be useful individual professional managers, well legislative taxation authorities.