The market for short-term rentals has drawn a lot of academic attention, especially in places like Rome that have a strong cultural history. Analytical techniques that take into consideration geographic context and geographical dependency among observations are necessary to fully understand the spatial drivers of nightly pricing on platforms such as Airbnb. This study uses spatial machine learning techniques to examine how neighborhood features, the density of local amenities, and proximity to historical sites affect Airbnb nightly rates in Rome, Italy.