Segmentation of Spatially Dependent Geographical Regions: Model and Application

Spatially Contiguous segments are managerially more attractive in terms of logistical and administrative efficiencies. The research develops and tests a methodology that assigns geographical units into segments by simultaneously considering customer attitudes and the geographical contiguity of regions within the resulting segments. This approach uses regional consumer data to capture spatial dependence flexibly while allowing us to identify managerially actionable segments that effectively balance homogeneity and spatial contiguity. A Monte Carlo simulation and an illustrative empirical application demonstrate the performance of the proposed method. In particular, the simulation and empirical application illustrate the tradeoffs between the different approaches.