Airbnb has grown in popularity since its conception in 2008 as an alternative to traditional hotels, offering travellers broader options for accommodations, location, and amenities. Airbnb listings are managed by individual hosts who often own the property, setting their own prices and rules. Because of this, properties vary significantly in size and price, even within the same city. We will explore what characteristics are associated with the variance in nightly rental price for Airbnb properties within Austin, Texas. Machine learning provides us with computational algorithms that will let us determine the correlated characteristics and discover if we may be able to accurately predict rental prices given these variables.
The goal of our project is to investigate how accurately machine learning can predict the nightly price of an Airbnb listing based on its characteristics. A 2017 study published in the International Journal of Hospitality Management (Wang & Nicolau) explores a similar question using least squares regression on price with predictors property characteristics, host attributes, amenities, rules, and ratings in 33 cities throughout the world. This has applications in the broader economy to determine how such a wide variety of properties may be fairly and standardly priced. In 2021, a study in the Journal of Theoretical and Applied Electronic Commerce Research (Chang & Li) expanded on this study, utilizing machine learning algorithms like random forest and support vector regression to show that the marketing of a listing (pictures, titles, descriptions, proximity to tourist attractions) are all significant factors in pricing. They found that tree based models outperformed regression based models, which is very useful information for this study.
We will be using publicly available Airbnb data from Inside Airbnb, a community of researchers, journalists, and activists who seek to explore the impact of private rental homes on the housing market, communities, and economy. The website is updated quarterly with the listings scraped directly from the app by city. We will be using the most recent data from Austin Texas, collected during the third fiscal quarter of 2026 and published on September 17.
Chang, C., & Li, S. (2021). Study of price determinants of sharing economy-based accommodation services: Evidence from Airbnb.com. Journal of Theoretical and Applied Electronic Commerce Research, 16(4), 584–601. https://doi.org/10.3390/jtaer16040035
Wang, D., & Nicolau, J. L. (2017). Price determinants of sharing economy based accommodation rental: A study of listings from 33 cities on Airbnb.com. International Journal of Hospitality Management, 62, 120–131. https://doi.org/10.1016/j.ijhm.2016.12.007