Estimating the Gains from New Rail Transit Investment: A Machine Learning Tree Approach

Abstract

Urban rail transit investments are expensive and irreversible. Since people differ with respect to their demand for trips, their value of time, and the types of real estate they live in, such projects are likely to offer heterogeneous benefits to residents of a city. Using the opening of a major new subway in Seoul, we contrast hedonic estimates based on multivariate hedonic methods with a machine learning approach that allows us to estimate these heterogeneous effects. While a majority of the "treated" apartment types appreciate in value, other types decline in value. We explore potential mechanisms. We also cross-validate our estimates by studying what types of new housing units developers build in the treated areas close to the new train lines.