Analyzing the most determinant factors of Airbnb unit prices in Indonesia and Singapore
Keywords:Tourism, Airbnb, Pricing Strategy, Marketing, Linear Regression
In the tourism business, a place to stay is an integral part that cannot be ignored. Airbnb, as one of the newest platforms in Indonesia and Singapore let people rent or share their unit (house, villa, or apartment) for travelers. However, there is no standardized rule in determining a unitâ€™s price-per-night. This study brings the novelty method in determining a unitâ€™s price based on seven facility parameters (such as number of guests, air conditioning, Wi-fi, kitchen, pool, rating, and number of reviews) and contributes to tourism and business studies by illustrating how big data can be used and visually interpreted. This study selected Yogyakarta and Singapore as the observed of the study because of their similarities in term of their huge number of visitors in a relatively small area. To get insight of the most influential factors of determining Airbnb unit prices, this study used content scrapping methods to gathers and prepare dataset and linear regression for data analysis. Number of guests, rating, and number of reviews are classified as numeric variables whereas Wi-fi, air conditioning, kitchen and pool are classified as Boolean. The results show that the linear regression fit the data quite properly for the determinant of unit prices behavior. However, Singapore has more price variance than that of Yogyakarta. Furthermore, while air condition and Wi-fi considered as significant unit prices determinant in Yogyakarta and Singapore partially, the number of guest, rating, and pool becoming the most unit prices determinant factors for both Yogyakarta and Singapore. Surprisingly, the availability of kitchen does not have any impact in determining the unitâ€™s price.