Accessibility by Public Transport Predicts Residential Real Estate Prices: A Case Study in Helsinki Region

Indre Zliobaite, Michael Mathioudakis, Tuukka Lehtiniemi, Pekka Parviainen, Tomi Janhunen

Abstract: This pilot study investigates how considering accessibility could help to model prices of residential real estate more accurately. We introduce two novelties from the price modeling point of view (1) defining accessibility as travel time by public transport, in addition to geographic distance, and (2) considering dynamic points of interest from check-ins into social networks, in addition to fixed location community centers. Our case study focuses on the Helsinki region. We model price per square meter as a linear function of apartment characteristics, and characteristics of the neighborhood, including accessibility by public transport and social activities. The resulting models show good predictive performance, as compared to baselines not taking accessibility into account. We discover that apartment price relates to the geographical distance from the city center, but accessibility by public transport to local centers of interest is more informative than just the geographical distance to those centers.