Welcome to the web version of the dissertation I completed as part of the Geographic Data Science MSc I completed at the University of Liverpool. To view the PDF version, click here (or click the cover image). The PDF and website should be identical in all but presentation, so choose whichever is most convenient for you. In both, chapter, section, table, and figure references should be hyperlinked.

Download PDF


Whenever geographic data are aggregated spatially, a decision must be made about the spatial unit into which individual data points are grouped. In analyses of the real estate market, properties are grouped in this way into housing submarkets: sections of the real estate market which share similar characteristics. Typically, existing spatial units (such as administrative neighbourhoods or districts) are used to represent these submarkets, however there is no guarantee that such units align with the housing market dynamics they seek to delineate. This dissertation presents a method to segment an urban area into different spatial units based on its built form – its urban morphology. The spatial segmentations produced are then assessed to determine whether they can be used to represent housing submarkets. Besides the novel segmentations themselves, the dissertation presents several methodological findings. Contextual characters and the transposition of cluster labels onto simpler geometries are shown to be key methods for ensuring spatially coherent segmentations. Segmentations are shown to significantly vary depending on the spatial units clustered to generate the segmentations (with regular grids performing significantly worse than units based on buildings), and on the clustering algorithm employed.


This dissertation could not have been written without the help of many people, a few of whom are acknowledged below.

Throughout the project, my supervisor Dani Arribas-Bel has offered expert advice and guidance; throughout the year he has worked to ensure the quality of my remote experience at Liverpool. I am particularly grateful to Martin Fleischmann, not only for his development of momepy, an invaluable tool in measuring the morphometric characters of urban spaces, but also for the help he provided with several of the thornier technical issues I encountered while completing this dissertation.

This project was organised through the Consumer Data Research Centre’s Master’s Dissertation Scheme, and so I thank those involved in the Scheme for facilitating the collaboration with idealista. At idealista, Juan Ramón Selva-Royo was vital in helping determine the direction of the dissertation, and provided me with both necessary data and helpful feedback.

I am forever grateful to my parents and grandparents, who provided me with countless forms of support, not least a pleasant working environment throughout the time I spent on the dissertation. I’m also thankful to all the friends who have in some way helped over the course of this dissertation – particular thanks are due to Ben, who tried his best to stop me leaving all the writing until the last minute; and to Marie-Laure, for foolishly agreeing to proofread.