Local and Application-Specific Geodemographics for Data-Led Urban Decision Making

This work seeks to introduce improvements to the traditional variable selection procedures employed in the development of geodemographic classifications. It presents a proposal for shifting from a traditional approach for generating general-purpose one-size-fits-all geodemographic classifications to application-specific classifications. This proposal addresses the recent scepticism towards the utility of general-purpose applications by employing supervised machine learning techniques in order to identify contextually relevant input variables from which to develop geodemographic classifications with increased discriminatory power. A framework introducing such techniques in the variable selection phase of geodemographic classification development is presented via a practical use-case that is focused on generating a geodemographic classification with an increased capacity for discriminating the propensity for Library use in the UK city of Leeds. Two local classifications are generated for the city, one a general-purpose classification, and the other, an application-specific classification incorporating supervised Feature Selection methods in the selection of input variables. The discriminatory power of each classification is evaluated and compared, with the result successfully demonstrating the capacity for the application-specific approach to generate a more contextually relevant result, and thus underpins increasingly targeted public policy decision making, particularly in the context of urban planning.

Developing a National Geodemographic Classification of Workplace Zones

Geodemographics conventionally refers to the classification of geographical areas based on the socioeconomic characteristics of their residents. In this paper, we develop the novel concept of a classification based on the characteristics of workers and workplaces. The paper describes the implementation of this concept at the small area level for the whole of the UK, which has involved reconciliation of three slightly different national censuses. It presents a summary of the resulting classification (a Classification of Workplace Zones for the UK (COWZ-UK)) and an innovative validation exercise based on comparison with a very large digital mapping dataset containing specific workplace locations. The openly available classification provides important new insights into the characteristics of workers and workplaces at the small area level across the UK, which will be useful for analysts in a range of sectors, including health, local government, transport and commerce. The generic concept of a classification based on the characteristics of workers and workplaces within a set of workplace zones is transferable to other countries, with refinement to reflect context- and country-specific phenomena. The concept can be readily implemented by census agencies or other data providers where individual level worker and workplace data are available.

Creating a geodemographic classification model within geo-marketing: the case of Eskişehir province

Businesses today face great competition in their operations, making it necessary for them to adopt a “customer-oriented” approach. In this competitive environment, where customers are more valuable, enterprises accrue great advantages from an understanding of the characteristics of the target audience in all dimensions. This is where the importance of geo-marketing and demographic segmentation for enterprises emerges. This study performed a geo-demographic segmentation of the urban neighbourhoods of Eskişehir province and sought to determine the characteristics of the people living in these neighbourhoods at the household level. The Groups created using the SPSS package program as well as Principal Components Analysis (PCA) and Hierarchical Clustering Analysis were then mapped on the GIS platform as urban neighbourhoods.