Predictive Geodemographics

Lead Research Organisation: University of Leeds
Department Name: Sch of Geography

Abstract

One of the many criticisms of geodemographics is that they are static - typically build using census data, they are out of date as soon as they are released, a snap shot of what the population was like 3 years previously (this is, on average, the time taken for census agencies to release census data). The next step is to make geodemographics dynamic - what do people truly look like now, and what changes in their characteristics or circumstances will move them into another segment? This is important for timely communication, in for example, marketing activities. However if long-term customer value is considered, it is what the consumer will look like three or five years hence that becomes important. The ability to identify the association of individuals with a defined social trajectory, a socio-economic path through life, is a powerful concept. Using new forms of data, is it possible to build a geodemographic system for the UK, that provides a predictive path through a CAMEO-like hierarchy, to enable our customers to evaluate consumers' lifetime value, and also serve up the right mix of timely information for consumers to make better decisions?

Publications

10 25 50

Studentship Projects

Project Reference Relationship Related To Start End Student Name
ES/P000401/1 01/10/2017 30/09/2024
1944002 Studentship ES/P000401/1 01/10/2017 31/03/2022 Jennie Gray
 
Description This research has developed a new method for identifying dynamic neighbourhood changes over a ten year period via neighbourhood processes, namely through the lens of gentrification. The method is able to capture cycles of gentrification, identifying the year in which the changes started, the year associated with the greatest amount of change (the peak), and the year in which these changes ended. This research has analysed how these cycles manifest throughout space, and has implemented predictive models to predict the spatial and temporal extent of gentrification for England. This approach can be used for other investigating other neighbourhood processes, like urban decline, and suburbanisation.
Exploitation Route The data primitive approach can be explored in greater depth, particularly with change vector analysis. They have great potential for uncovering the intricate relationships between neighbourhood processes, alongside the complex periodicities of specific neighbourhood processes. This will help to uncover insights into the neighbourhood processes under investigation, how they operate through space and time, which in turn could be greatly beneficial for public policy and planners.
Sectors Communities and Social Services/Policy

 
Description AGILE 2019 Grant
Amount £560 (GBP)
Organisation Environmental Systems Research Institute 
Sector Private
Country United States
Start 04/2019 
End 06/2019
 
Description GSIRUK 2019 Early Career Scholarship
Amount £150 (GBP)
Organisation GISRUK 
Sector Charity/Non Profit
Start 03/2019 
End 04/2019
 
Description Data Supplier 
Organisation EDGE Analytics Limited
Country United Kingdom 
Sector Private 
PI Contribution Acknowledgement of Edge Analytics (EA) and their data in any of my outputs from the data supplied from EA.
Collaborator Contribution Three requested datasets, and access to a piece of commercial software and its methodology.
Impact None yet.
Start Year 2019
 
Description Official Data Supplier 
Organisation Callcredit Limited
Country United Kingdom 
Sector Private 
PI Contribution I conducted what should have been a two week internship at callcredit, but it ended up being around 4-6 weeks. This was for the internship module in the first year, but I did so for a project proposed by callcredit.
Collaborator Contribution None. They were my official PhD partner, but have made no contributions to my project, they have supplied zero data, leading me to seek elsewhere (EA).
Impact Officially still active, but zero communication, zero data, thus zero outcomes from the partnership.
Start Year 2017