The estimation and policy use of spatially explicit discrete choice models has yet to receive serious attention from practitioners. In this study we aim to analyze how geographical variables influence individuals’ sensitivity to key features of heating systems, namely investment cost and CO₂ emissions. This is of particular policy interest as heating systems are strongly connected to two major current environmental issues: emissions of pollutants and increased use of renewable resources. We estimate a mixed logit model (MXL) to spatially characterize preference heterogeneity in the mountainous North East of Italy. Our results show that geographical variables are significant sources of variation of individual’s sensitivity to the investigated attributes of the system. We generate maps to show how the willingness to pay to avoid CO₂ emissions varies across the region and to validate our estimates ex-post. We discuss why this could be a promising approach to inform applied policy decisions.