Geodemographic Classification Research Articles

Impact of net zero policy scenarios on air pollution inequalities in England and Wales

BackgroundThe UK is committed to achieve net zero greenhouse gas emissions by 2050. The suite of policies needed to reach net zero will lead to improvements in air quality and, consequently, could lessen air pollution inequalities. We assessed air pollution inequalities across different sociodemographic groups in England and Wales and explored how these might be differentially impacted by future air pollution projections in 2030 and 2040 under net zero policies. MethodsWe employed a geodemographic classification approach to categorise neighbourhoods into five distinct clusters based on 2021 UK Census sociodemographic variables. We modelled fine particulate matter (PM2.5) and nitrogen dioxide (NO2) concentrations for the year 2019, and predicted concentrations in 2030 and 2040. We compared a business-as-usual (BAU) scenario and two policy pathways to achieve net zero currently considered by the UK government. We aggregated air pollution concentrations to the neighbourhood level and assessed differential neighbourhood-level concentrations across the geodemographic groups using descriptive statistics and box plots. ResultsThe Urban Central Professionals group experienced 14 µg/m3 higher average NO2 concentrations compared with the Rural Elderly group in 2019. Despite substantial improvements to air quality in 2030 and 2040 of up to 6.3 µg/m3 for NO2 based on BAU, and further reductions of up to 2.4 µg/m3 NO2 under net zero policies, the overall pattern of inequality persists, but is predicted to be less pronounced. ConclusionsOur findings demonstrate the effectiveness of targeted policies and innovations in reducing both air quality and greenhouse gas emissions and in bridging the environmental inequality gap. Our findings are essential to develop targeted communication campaigns to secure acceptance and willingness across the sociodemographic spectrum to support the significant behavioural changes needed to achieve net zero, by highlighting the wider co-benefits to the environment and health of such policies.

Segmentation using large language models: A new typology of American neighborhoods

In the United States, recent changes to the National Statistical System have amplified the geographic-demographic resolution trade-off. That is, when working with demographic and economic data from the American Community Survey, as one zooms in geographically one loses resolution demographically due to very large margins of error. In this paper, we present a solution to this problem in the form of an AI based open and reproducible geodemographic classification system for the United States using small area estimates from the American Community Survey (ACS). We employ a partitioning clustering algorithm to a range of socio-economic, demographic, and built environment variables. Our approach utilizes an open source software pipeline that ensures adaptability to future data updates. A key innovation is the integration of GPT4, a state-of-the-art large language model, to generate intuitive cluster descriptions and names. This represents a novel application of natural language processing in geodemographic research and showcases the potential for human-AI collaboration within the geospatial domain.

Classifying and mapping residential structure through the London Output Area Classification

This paper outlines the creation of the London Output Area Classification (LOAC) from the 2021 Census, set within the broader context of geodemographic classification systems in the United Kingdom. The LOAC 2021 was developed in collaboration with the Greater London Authority (GLA) and offers an enhanced, statistically robust typology adept at capturing the unique spatial, socio-economic and built characteristics of London’s residential neighbourhoods. The paper asserts the critical importance of nuanced, area-specific geodemographic classifications for urban areas with unique geography relative to the national extent.

A graph neural network framework for spatial geodemographic classification

Geodemographic classifications are exceptional tools for geographic analysis, business and policy-making, providing an overview of the socio-demographic structure of a region by creating an unsupervised, bottom-up classification of its areas based on a large set of variables. Classic approaches can require time-consuming preprocessing of input variables and are frequently a-spatial processes. In this study, we present a groundbreaking, systematic investigation of the use of graph neural networks for spatial geodemographic classification. Using Greater London as a case study, we compare a range of graph autoencoder designs with the official London Output Area Classification and baseline classifications developed using spatial fuzzy c-means. The results show that our framework based on a Node Attributes-focused Graph AutoEncoder (NAGAE) can perform similarly to classic approaches on class homogeneity metrics while providing higher spatial clustering. We conclude by discussing the current limitations of the proposed framework and its potential to develop into a new paradigm for creating a range of geodemographic classifications, from simple, local ones to complex classifications able to incorporate a range of spatial relationships into the process.

Predicting Gentrification in England: A Data Primitive Approach

Geodemographic classifications are useful tools for segmenting populations and have many applications but are not suitable for measuring neighbourhood change over time. There is a need for an approach that uses data of a higher spatiotemporal resolution to capture the fundamental dimensions of processes driving local changes. Data primitives are measures that capture the fundamental drivers of neighbourhood processes and therefore offer a suitable route. In this article, three types of gentrification are conceptualised, and four key data primitives are applied to capture them in a case study region in Yorkshire, England. These areas are visually validated according to their temporal properties to confirm the presence of gentrification and are then assigned to a high-level gentrification type. Ensemble modelling is then used to predict the presence, type, and temporal properties of gentrification across the rest of England. The results show an alignment of the spatial extent of gentrification types with previous gentrification studies throughout the country but may have made an overprediction in London. The periodicities of (1) residential, (2) rural, and (3) transport-led gentrification also vary throughout the country, but regardless of type, gentrification in areas within close proximity to one another have differing velocities such that they peak and complete within similar times. These temporal findings offer new, more timely tools for authorities in devising schedules of interventions and for understanding the intricacies of neighbourhood change.

Age and the 20-min city: Accounting for variation in mobility

The political popularity of the 20-min city is a result of its perceived equal treatment of all citizens, yet the ideal geography fails to consider the diversity of mobilities and needs of different age groups. If 20-min cities are to provide equality for people with limited mobility, they need to understand their location and proximity to the services which meet their needs. Considering older people as a subset of the population with diverse mobilities, this research provides a novel exploration of the issue of age and urban mobility through grounded analysis of the 20-min city against a geodemographic classification of older people in Liverpool City Region, England. We construct a new model of accessibility to services that takes into consideration varied mobilities for older residents. We find that reduced walking speed results in a significant diminution of service accessibility, but that this diminution is highly varied for different older person groups. This highlights the need for 20-min city planning to account for the needs of diverse older geodemographic groups and a tighter conceptualization of the 20-min city concerning equity to avoid the pitfalls of some similar urban planning concepts.

Геодемографическая классификация регионов Северо-Кавказского федерального округа

Introduction. The dynamics of the vital movement of the population of the North Caucasus for 2005-2020 is investigated. Research methods and materials. Both traditional and the latest geographic research methods are used - comparative geographical, spatial analysis, statistical, GIS technologies, population surveys, etc. Research results. The conducted studies have shown that despite the apparent well-being, a tense demographic situation is developing in the North Caucasus. Favorable demographic results are obtained only at the expense of three subjects - Dagestan, Ingushetia and Chechnya. In other regions, narrowed and negative reproduction is observed. The natural increase is getting lower and lower. The small generation born in the 1990s reached the fertile age. COVID-19 restrictions and a crisis in the economy have led to an even greater decline in the birth rate and an increase in mortality. The conducted geodemographic classification of the regions of the North Caucasus showed that the most favorable situation is observed in Ingushetia, the situation is slightly worse in Chechnya and Dagestan, narrowed reproduction in Kabardino-Balkaria and Karachay-Cherkessia and the most tense situation is in North Ossetia and the Stavropol Territory. Conclusion. To improve the situation, a differentiated approach is needed to different regions in the demographic sphere, the creation of new workplaces. The outflow of the able-bodied population from the regions of the North Caucasus leads to a violation of the population age composition and, thereby, undermines the fertility of the population. This leads to a decrease in the birth rate and, accordingly, natural increase. Resume. The article presents the results of studies of the natural movement of the population of Russia and the North Caucasus Federal District. At the same time, the multi-scale method of research and geodemographic classification was taken as the basis. It has been established that relatively favorable results on the scale of Russia were achieved in the North Caucasus Federal District, and on the scale of the North Caucasian Federal District - in Ingushetia, Chechnya and Dagestan. It was determined that along with the traditional factors of mortality, the factor of infectious morbidity began to play a significant role. It is shown that at the same time, mortality in working age has increased. It was revealed that there is a significant territorial differentiation of the natural movement of the population both in Russia as a whole and in the North Caucasus Federal District. The results of the research can be useful in developing programs for further demographic development of the regions.

Ageing in Place Classification: Creating a geodemographic classification for the ageing population in England

Population ageing is one of the most significant demographic changes underway in many countries. Far from being a homogenous group, older people and their experiences of ageing are diverse. A better understanding of the characteristics and geography of the older population, including the older workforce, is important. It allows policymakers and stakeholders to better adapt to the opportunities and challenges that the ageing population brings. This paper describes the implementation of the Ageing in Place Classification (AiPC) in England. AiPC is a multidimensional geodemographic classification, and it employs a wide range of spatially representative attributes of older people’s sociodemographic characteristics and their living environment at the small area level. The openly available product provides valuable insights that can be implemented in both local and national contexts, in particular to improve service delivery and inform targeted policy interventions. AiPC is readily updateable with the arrival of new Census data; the concept and framework are also transferable to other countries.

A new geodemographic classification of the influence of neighbourhood characteristics on crime: The case of Leeds, UK

Understanding spatial composition and characteristics of urban communities is an important factor determining the potential for social interactions between residents, greater chances for neighbourhood safety and policy planning. Until recently, neighbourhood classifications were traditionally census-based. This study presents a different approach in developing a community-based area classification for exploring the relationship between neighbourhood characteristics and crime through the integration of new data sources from social media with contextual variables from the traditional census. In this study, partition around medoids (PAM) clustering algorithm is used to partition 105 Leeds community areas into four distinct groups based on their crime rates. Silhouette index and adjusted rand index (ARI) were used to evaluate the validity of clusters internally and externally. The new typology developed, has revealed new insights demonstrating the relationship between social cohesion and crime rates in Leeds community areas. The new partitioned clusters also provide area-based specific information, on criminal activities that could help in policy planning for community building and better resource allocation towards reducing crime rates.

Mapping the geodemographics of racial, economic, health, and COVID-19 deaths inequalities in the conterminous US

A large number of studies have examined individual-level factors that increase COVID-19 fatalities. However, no research has focused on the geodemographic classification of the most susceptible communities to COVID-19. In this cross-sectional ecological study, we used local fuzzy geographically-weighted clustering to create the socioeconomic profile of the US counties in relation to COVID-19 death rates. We demonstrate that living in a county which has households with lower income, people with a lack of health insurance, a high African-American percentage, and lower education level, lead to 27.12% higher COVID-19 death rates than the national median, and 72.56% higher compared to the least vulnerable counties. Compared to counties with a high COVID-19 death rate, counties with a low COVID-19 death rate have 44.90% higher annual median household income and nearly double house worth (89.51% more). Results show that the effects of the COVID-19 pandemic are not universal and that the minoritised and impoverished populations suffer more. Our analysis can effectively pinpoint the most vulnerable counties and importantly allows for understanding the socioeconomic context in which tailored interventions can be applied to mitigate COVID-19 deaths.

Spatial and social disparities in the decline of activities during the COVID-19 lockdown in Greater London.

We use data on human mobility obtained from mobile applications to explore the activity patterns in the neighbourhoods of Greater London as they emerged from the first wave of COVID-19 lockdown restrictions during summer 2020 and analyse how the lockdown guidelines have exposed the socio-spatial fragmentation between urban communities. The location data are spatially aggregated to 1 km2 grids and cross-checked against publicly available mobility metrics (e.g. Google COVID-19 Community Report, Apple Mobility Trends Report). They are then linked to geodemographic classifications to compare the average decline of activities in the areas with different sociodemographic characteristics. We found that the activities in the deprived areas dominated by minority groups declined less compared to the Greater London average, leaving those communities more exposed to the virus. Meanwhile, the activity levels declined more in affluent areas dominated by white-collar jobs. Furthermore, due to the closure of non-essential stores, activities declined more in premium shopping destinations and less in suburban high streets.

Extending Geodemographics Using Data Primitives: A Review and a Methodological Proposal

This paper reviews geodemographic classifications and developments in contemporary classifications. It develops a critique of current approaches and identifiea a number of key limitations. These include the problems associated with the geodemographic cluster label (few cluster members are typical or have the same properties as the cluster centre) and the failure of the static label to describe anything about the underlying neighbourhood processes and dynamics. To address these limitations, this paper proposed a data primitives approach. Data primitives are the fundamental dimensions or measurements that capture the processes of interest. They can be used to describe the current state of an area in a multivariate feature space, and states can be compared over multiple time periods for which data are available, through for example a change vector approach. In this way, emergent social processes, which may be too weak to result in a change in a cluster label, but are nonetheless important signals, can be captured. As states are updated (for example, as new data become available), inferences about different social processes can be made, as well as classification updates if required. State changes can also be used to determine neighbourhood trajectories and to predict or infer future states. A list of data primitives was suggested from a review of the mechanisms driving a number of neighbourhood-level social processes, with the aim of improving the wider understanding of the interaction of complex neighbourhood processes and their effects. A small case study was provided to illustrate the approach. In this way, the methods outlined in this paper suggest a more nuanced approach to geodemographic research, away from a focus on classifications and static data, towards approaches that capture the social dynamics experienced by neighbourhoods.

Goals and persistence of sustainability experiments in divergent urban contexts: urban agriculture and a geodemographic classification in London

ABSTRACT This paper critically engages with the increasingly prevalent concept and practice of “urban experimentation” and associated transformations towards sustainability. Too often, the paper argues, urban experiments are assessed from a diffusion-oriented perspective which foregrounds questions of how to replicate lessons from (similar) experiments across (similar) places. This common perspective implies an over-emphasis of unifying visions and rationales at the expense of diverging interpretations of “sustainability”; a neglect of “unsuccessful” experiments and questions of persistence; and an over-focus on certain types of – “green” or “creative” – places while disregarding the emergence and characteristics of experiments in more ordinary urban geographies. To address these issues, the paper introduces a novel methodological approach, combining a metropolitan geodemographic typology with qualitative data on 166 active and inactive urban agriculture initiatives across London. Varying socio-spatial patterns of experimentation are discussed, illustrating how contextual differences at neighbourhood levels matter. The paper demonstrates that neglecting the diversity of urban socio-economic, demographic, and physical contexts may lead to the erroneous suggestion that only places privileged by certain demographics can “achieve” sustainability and points to the significance of experiments beyond narrow ideas of novelty and innovation.

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.

Urban Morphology and Residential Differentiation across Great Britain, 1881–1901

The nineteenth century saw rapid urbanization and dramatic social change in Great Britain, some of which can now be viewed at national scales for the first time through linkage of georeferenced digital historical data to contemporary and historical framework data. Here, we attempt to georeference every individual address record from the 1881, 1891, and 1901 censuses for Great Britain and to define the fast-growing historical street networks and residential geographies of every urban settlement. We next devise a scale-free historical geodemographic classification using variables common to these three censuses and assign cluster group characteristics to every urban street segment. We also link the evolution of the urban street morphology with changes in residential differentiation and the geodemographic assignments over the twenty-year study period. The results of this intensive data processing make it possible to chart the development of urban residential areas across Great Britain and bring focus to the changing social structures of the cities. We examine these changes with examples drawn from the entire British urban settlement system. Our conclusions discuss the implications of this extensive analysis for improved understanding of the evolution of Great Britain’s urban system.

Dynamic hazards modelling for predictive longevity risk assessment

Predictive risk assessment and risk stratification models based on geodemographic postcode-based consumer classification are widely used in the pension and life insurance industry. However, these are static socio-economic models not directly related to health information. Health information is increasingly used for annuity underwriting in the UK, using health status when the annuity is purchased. In real life, people develop new health conditions and lifestyle habits and can start and stop a certain treatment regime at any time. This requires the ability to dynamically classify clients into time-varying risk profiles based on the presence of evolving health-related conditions, treatments and outcomes. We incorporate landmark analysis of electronic health records (EHR), in combination with the baseline hazards described by Gompertz survival distributions, for dynamic prediction of survival probabilities and life expectancy. We discuss a case-study based on landmark analysis of the survival experience of a cohort of 110,243 healthy participants who reached age 60 between 1990–2000.

Analysing Socio-Economic Change Using a Time Comparable Geodemographic Classification: England and Wales, 1991–2011

Geodemographic classifications are used to understand social phenomena. Within the private sector, for business planning accounting for underlying spatial differences in economic, social and demographic composition of geographical areas. In the public sector geodemographics is used in health, local governance and social research. Bespoke geodemographic systems help public health authorities to target neighbourhoods most at need of health campaigns. Geodemographic classifications are invariably cross-sectional and static. Having comparable geodemographic classifications over a period of time will help demonstrate changes in socio-economic and demographic structures. A time-comparable geodemographic scheme can bring out changes in multivariable compositional characteristics which are otherwise hidden by cross-sectional measures. This paper reports on variable selection, the conversion of inputs to a consistent geography and the creation of directly comparable geodemographic classifications of small areas across England and Wales for 1991, 2001 and 2011. Changes and stability in area characteristics are then analysed. The results show that most neighbourhoods are allocated into the same area type over time. Where there is change, this can be themed as: Socio-economic polarisation, characterised by a decrease in neighbourhoods found in the middle of the socio-economic spectrum, with an increase in number of areas at either end; Growth in the number of neighbourhoods with non-White ethnic residents, mainly Black ethnic minorities and Asian based communities and; Reorganisation and increase in classifications relating to urban areas, signalling development or growth of metropolitan areas.

Geodemographic Patterns of Meat Expenditure in Great Britain

The future of the meat industry will require the management of important trade-offs between economic, environmental and health aspects of both humans and animals. Understanding the patterns and trends of meat expenditure and consumption is crucial for assessing the current resilience of the system and for economic, planning, health and environmental applications. Here, we show how the technique of geodemographic classification, combined with fine scale expenditure estimates can be used to explore temporal and spatial patterns of meat expenditure in Great Britain between 2008 and 2017. Whilst the expenditure patterns of some food categories such as sausages remained relatively consistent, others such as lamb show a trend towards a reduced proportion of expenditure and increased inequality of purchases. Short term changes in expenditure patterns also occurred, potentially due to product specific price variability, price elasticities or zoonotic disease scare. Environmental attitudes, financial constraints and the prominence of communities who do not eat meat for religious or cultural reasons are likely to be driving the differences between geodemographic groups. The methodology and results could be a valuable tool for policy makers in the meat industry and beyond.

Open Geodemographics: Classification of Small Areas, Ireland 2016

Geodemographics is a tool to summarize the characteristics of spatial units based on socio-economic data. It has been used over several decades to classify the characteristics of areas based on the similarities in such data, generally working by identifying groups or clusters of similar areas. It has seen use in the academic and private sectors but mostly became popular by 1980s for market research purposes – this rise in use drew attention to many issues that needed to be addressed in the literature. The purpose of this paper is to provide a geodemographic classification for the smallest scale administrative units in Ireland (Small Areas) based on the latest 2016 census population data. A further aim is to support reproducible research by following the methodology of an earlier study for the 2011 Census and to bring up the opportunity to compare the cluster results between the 2011 and 2016 census data. The comparison output provides useful insights for policy discussions in the Irish context. One of the other focal points of this study is to bring some clarity regarding some criticisms of geodemographics from an academic perspective. The paper also argues for the use of open data, open source software and supports open analysis.

Mapping the geodemographics of digital inequality in Great Britain: An integration of machine learning into small area estimation

Geographic variation in digital inequality manifests as a result of a range of demographic, attitudinal, behavioural and locational factors. To better understand this multidimensional geography, our paper develops a new geodemographic classification for the spatial extent of Great Britain. In this model, we integrate a range of new small area measures that are drawn from multiple new forms of data including consumer purchasing data, survey and open data sources. Our analytical approach innovatively provides an integration of machine learning into a small-area estimation technique to obtain Lower Super Output Area / Data Zone estimates of Internet use, alongside a range of online engagement and consumption measures. Following the collation of a range of input measures, we implemented a more standard geodemographic framework that utilises the unsupervised clustering algorithm k-means to produce a map of the multidimensional characteristics of digital inequality for Great Britain; creating the Internet User Classification (IUC). Our outputs provide a new and nuanced understanding of the contemporary salient characteristics of digital inequality in Great Britain, which we evaluate both internally and externally within the context of preparations for the 2021 UK Census of the Population, exploring the geodemographic patterns of Census test response rates and the prevalence to complete the survey online. Our innovative work illustrates the strength of a geodemographic approach in mapping spatial patterns of digital inequality, and through the presented application concerning Census response rates and characteristics we demonstrate how the IUC can be operationalised within such settings for local intervention or benchmarking.