news | 02.08.2019 |

Visualising substitutability in the Glasgow Housing Market

UBDC has investigated a range of issues around diverse populations within cities, and what their neighbourhoods and movements mean for urban life and urban economies.

As part of this research, Nema Dean (School of Mathematics and Statistics, University of Glasgow), Gwilym Pryce and Dan Olner (both from Sheffield Methods Institute, University of Sheffield) wanted to show how data can be used to help understand different neighbourhoods in a single city. Specifically, they wanted to see how data can help people work out which neighbourhood might suit them best. Their work used Glasgow Solicitors’ Property Centre (GSPC) data and Scottish Index of Multiple Deprivation (SIMD) data.

What is substitutability in the housing market?

If two neighbourhoods are perceived to be close substitutes, then house prices in those areas will tend to move in tandem.

With a dataset of a hundred million possible substitutability connections between postcodes in Glasgow, a “substitutability map” was plotted by the researchers. This map displays which neighbourhoods are considered close substitutes for the postcode in question. The substitutability map for your postcode, for example, would reveal which parts of the city are considered by the housing market to be close substitutes to your own.

You can find out more about this work in Gwilym and Nema’s blog post on 'Invisible Fissures in the Glasgow Housing Market: Finding a neighbourhood that feels like home'. There is also a related academic paper using the same data: 'Is the housing market blind to religion? A perceived substitutability approach to homophily and social integration', which was published in Urban Studies.

Visualising substitutability

As part of the research outlined above, Dan Olner created a visualisation (shown in the video above) that illustrates how house price substitutability changes between Glasgow postcodes.

Dan explains:

“It starts with a map of Glasgow – when you hover the cursor over a postcode, it shows CPEP values for all other postcodes: large red dots indicate postcodes where prices moved in tandem with the one being hovered over. Dots become smaller and fade to a transparent green as price movements match less. The video above shows a small sample of doing this, for a single line of postcodes in the centre, just below the river (the moving blue dot).

“And what do we see? To my eyes, there are two fascinating things going on. First – there are substitutability waves across space. This is stronger in some places than others – but when present, it’s striking. As the cursor is moved across postcodes, substitutability patterns flow smoothly. This doesn’t just happen in one location – several will be linked, showing the same wave-like pattern.”

Find out more about the visualisation - and Dan’s interpretation of the patterns it shows - on his website.