This study aims to establishing a predictive model that would aid sirbnb hosts in adopting a market calibrated price to enhance their listing’s revenue performance.
With the rise of the peer to peer (P2P) sharing economy, Airbnb has emerged as a major rival to traditional business in the consumer lodging industry. This study aims to address a significant problem faced by Airbnb host with regards to revenue loss due to inadequate pricing strategy. Though several studies have been conducted, there is still a gap in existing literature with regards to factors influencing Airbnb prices in Singapore.
This study used data of Airbnb listings in Singapore from September 2021 to address this by building a fair pricing model for Airbnb in Singapore. Simple linear regression, stepwise forward regression, stepwise backward regression, and K-Nearest Neighbour (KNN) models were built and evaluated. The stepwise forward regression yielded the optimum predictive model with an adjusted R-square of 0.60. Number of bedrooms, room type, location and the presence of a pool were found to be the major factors influencing price. Update of the model with post pandemic data, inclusion of other fixed costs such a cleaning and miscellaneous fees and inclusion of host attributes and customer ratings were identified as areas of future work.