Geodemographic Analysis Research Articles

Fuzzy geographically weighted clustering using artificial bee colony: An efficient geo-demographic analysis algorithm and applications to the analysis of crime behavior in population

Geo-demographic analysis is an essential part of a geographical information system (GIS) for predicting people's behavior based on statistical models and their residential location. Fuzzy Geographically Weighted Clustering (FGWC) serves as one of the most efficient algorithms in geo-demographic analysis. Despite being an effective algorithm, FGWC is sensitive to initialize when the random selection of cluster centers makes the iterative process falling into the local optimal solution easily. Artificial Bee Colony (ABC), one of the most popular meta-heuristic algorithms, can be regarded as the tool to achieve global optimization solutions. This research aims to propose a novel geo-demographic analysis algorithm that integrates FGWC to the optimization scheme of ABC for improving geo-demographic clustering accuracy. Experimental results on various datasets show that the clustering quality of the proposed algorithm called FGWC-ABC is better than those of other relevant methods. The proposed algorithm is also applied to a decision-making application for analyzing crime behavior problem in the population using the US communities and crime dataset. It provides fuzzy rules to determine the violent crime rate in terms of linguistic labels from socioeconomic variables. These results are significant to make predictions of further US violent crime rate and to facilitate appropriate decisions on prevention such the situations in the future.

A novel kernel fuzzy clustering algorithm for Geo-Demographic Analysis

Geo-Demographic Analysis (GDA) is a major concentration of various interdisciplinary researches and has been used in many decision-making processes regarding the provision and distribution of products and services in society. Machine learning methods namely Principal Component Analysis, Self-Organizing Map, K-Means, fuzzy clustering and fuzzy geographically weighted clustering were proposed to enhance the quality of GDA. Among them, the state-of-the-art method – Modified Intuitionistic Possibilistic Fuzzy Geographically Weighted Clustering (MIPFGWC) has some drawbacks such as: (i) using the Euclidean similarity measure often results in high error rate and sensitivity to noises and outliers; (ii) updating the membership matrix by the Spatial Interaction – Modification Model (SIM2) model leads to new centers not being “geographically aware”. In this paper, we present a novel fuzzy clustering algorithm named as Kernel Fuzzy Geographically Clustering (KFGC) that utilizes both the kernel similarity function and the new update mechanism of the SIM2 model to remedy the disadvantages of MIPFGWC. Some supported properties and theorems of KFGC are also examined in the paper. Specifically, the differences between solutions of KFGC and those of MIPFGWC and of some variants of KFGC are theoretically validated. Lastly, experimental analysis is performed to compare the performance of KFGC with those of the relevant algorithms in terms of clustering quality.

Inflated Granularity: Spatial Big Dataa and Geodemographics

Data analytics, particularly the current rhetoric around ‘big data’ tend to be presented as new and innovative, emerging ahistorically to revolutionize modern life. In this article, we situate one branch of ‘big data’ analytics, spatial ‘big data’, through a historical predecessor, geodemographic analysis. Spatial ‘big data’ promises an epistemic break in marketing, a leap from targeting geographic areas to targeting individuals. Yet it inherits characteristics from geodemographics, including an orientation towards and justification through the market, and a process of commodification through the black-boxing of technology. In addition, epistemological problems within geodemographics helped set the stage for the individual orientation in spatial ‘big data’ analytics. As researchers develop sustained critiques of data analytics and its affects on everyday life, it is important to do so with a grounding in the cultural and historical contexts from which data technologies emerged. This article and others (Barnes and Wilson, 2014) begin to detail a critical history of ‘big data’. Spatial ‘big data’ carries over critical issues from geodemographics: its roles in surveillance, redlining, and the production of consumer subjects and geographies. The shared histories and structural logics of spatial ‘big data’ and geodemographics create the space for a continued critique of data analyses’ role in society.

Enhancing clustering quality of geo-demographic analysis using context fuzzy clustering type-2 and particle swarm optimization

Geo-Demographic Analysis, which is one of the most interesting inter-disciplinary research topics between Geographic Information Systems and Data Mining, plays a very important role in policies decision, population migration and services distribution. Among some soft computing methods used for this problem, clustering is the most popular one because it has many advantages in comparison with the rests such as the fast processing time, the quality of results and the used memory space. Nonetheless, the state-of-the-art clustering algorithm namely FGWC has low clustering quality since it was constructed on the basis of traditional fuzzy sets. In this paper, we will present a novel interval type-2 fuzzy clustering algorithm deployed in an extension of the traditional fuzzy sets namely Interval Type-2 Fuzzy Sets to enhance the clustering quality of FGWC. Some additional techniques such as the interval context variable, Particle Swarm Optimization and the parallel computing are attached to speed up the algorithm. The experimental evaluation through various case studies shows that the proposed method obtains better clustering quality than some best-known ones.

Spatial interaction – modification model and applications to geo-demographic analysis

In this paper, we introduce a novel model so-called Spatial Interaction – Modification Model (SIM2), serving for the classification of spatially-referenced demographic data. It is integrated with the main part of the best fuzzy clustering algorithm for geo-demographic analysis problem – IPFGWC to form the new method named as MIPFGWC. Theoretical and experimental analyses show that MIPFGWC achieves better clustering quality than IPFGWC and other available algorithms.

Geodemographic analysis and estimation of early plug-in hybrid electric vehicle adoption

Electric vehicles and hybrids are expected to become increasingly common in the coming years. The implications of growing adoption depend on its geographical extent. For instance, vehicles that are chargeable from the electrical grid, such as plug-in hybrids, can introduce problems for the distribution network especially if the vehicle adoption is spatially concentrated. In this paper, the adoption of hybrid electric vehicles is analysed in heterogeneous areas. The main purpose is to study the interrelationships between early hybrid electric vehicle adoption and different demographic and socio-economic characteristics of the areas. It is further discussed how the results can be applied to estimate the upcoming plug-in hybrid adoption. As there is a vast amount of information in the various registers of the society, slowly being opened for free usage but not fully utilised so far, it is also of interest to study and demonstrate the usability of public register data in this context. Our analysis suggests that certain characteristics of the areas strongly correlate with the hybrid electric vehicle adoption. The results of this study could be relevant, e.g., for electric distribution network planning, targeting policies to support cleaner vehicle adoption, marketing hybrid vehicles and locating charging stations.

Cost implications, deprivation and geodemographic segmentation analysis of non-attenders (DNA) in an established diabetic retinopathy screening programme

AimTo ascertain the relationship between socioeconomic status and non attendance alongside the role of geodemographic analysis in identifying reasons for non attendance. To also ascertain the financial implications of non attendance on the service. MethodsRetrospective analysis of DNA patients between April 2009 and March 2010. Cost to the service was calculated based on Devon Primary Care Trust tariffs. Deprivation Analysis was based on the Indices of Multiple Deprivation 2007 for England. Geodemographic analysis was done using a commercially available software (MOSAIC Public Sector, Experian Information Solutions Inc.). Results22,651 patients were invited for screening with 20,514 screened and 2137 (9.4%) DNA's. Of these, 1757 (82.2%) were DNA 1's while 380 (17.7%) were DNA 2's. Mean age of screened patients was 68 (SD ±14.2), DNA 1's was 62 (SD ±17.3) and DNA 2's was 57 (SD ±18.7).1269 (59%) of DNA's were males and 868 (41%) were females. Cost to the service as calculated by lost earnings from missed appointments came to £78,259. Deprivation analysis showed increasing non attendance rates with increasing deprivation. Geodemographic segmentation analysis revealed that the lowest DNA rates were seen in successful professionals and active retired communities and the highest rates were seen in areas of social housing. ConclusionsThe study demonstrates an association between non attendance and socioeconomic deprivation. The use of geodemographic analysis programmes can help identify groups that do not respond to traditional postal reminders. More focused and customised strategies can then be developed for these groups to eliminate nonattendance.

The geodemographics of access and participation in Geography

Geography is not a compulsory subject of study beyond the age of 14 in English schools and this has had an impact on both absolute and relative participation rates over recent years. Geodemographic analysis reveals that pupils domiciled within more affluent and less ethnically diverse areas record the highest rates of participation and attainment in GCSE Geography, and that the stratified patterns of participation have increased between 2005 and 2009. Within this period, those schools that have stopped supplying successful GCSE Geography entries by 2009 were found to have overall low aggregate attainment and to draw pupils from more deprived areas. The profile of schools visited by the Royal Geographical Society (with the Institute of British Geographers) (RGS‐IBG) Ambassador Scheme was also considered to assess the extent that the schools visited are representative of pupils who are most at risk of non‐participation.

Modelling the future opportunities for deep discount food retailing in the UK

In the last few years, the discount retail food market in the UK has grown to record levels. This followed a period of gradual increase in store numbers and also more favourable trading characteristics for discounters given the recession and global financial problems of the late 2000s. Although market share dipped a little in 2010, the deep discounters still have impressive growth plans for their UK store networks. Given this context, the aim of this paper is twofold. First, we wish to explore the recent growth of the discounters in the UK and analyse the dynamics of customer patronage based on geodemographics in the late 2000s using data from Acxiom's Research Opinion Poll survey. We believe that this fills a major gap in the literature as there has been little reported on the spatial expansion of discounters since work in the 1990s (especially in the UK). Second, we wish to use this geodemographic analysis to look for potential new sites for discount retailers in two selected areas of the UK. The geodemographic analysis will be supplemented by more detailed revenue forecasting obtained from a retail location model. Again, there is little in the literature using spatial analysis to look for market opportunities in this way. We also introduce a novel method for validating retail models using the Acxiom data. The study areas are Yorkshire and Humber, and London, two very different regions in terms of current discount retail market share. The research shows that there are still opportunities for growth in so-called saturated markets especially if the retailers concerned consider a potential expansion into ‘middle’ Britain, moving the focus from deep discounting to serving more middle markets (a potential change in the value-platform growth strategies through which companies such as Aldi now seem to be championing).

Bailing Out Collapsing Social Infrastructure in Developing Countries Through Sports: How Football is Contributing to Healthcare Improvement in Urban Nigeria

Bailing Out Collapsing Social Infrastructure in Developing Countries Through Sports: How Football is Contributing to Healthcare Improvement in Urban Nigeria Although the role of sports in shaping/changing urban and regional landscapes through megalomaniac building of stadia, golf courses, among other spectacular artifacts have recently attracted tremendous academic research interests, sports' role in improving collapsing health-care infrastructure in developing countries is poorly documented. Here, we show the potentials of football in multi-stakeholder mobilization for financing/improving/ in urban health-care Nigeria using contributions towards heart diseases treatment by Kanu Heart Foundation and campaigns by Nigeria's international footballers. Geo-demographic analysis of secondary data is applied to highlight inadequacy of healthcare in urban Cross River State, like of urban (like rural) Nigeria. How various diplomacy concepts could be employed by urban managements to mobilize sports-heroes, stakeholders (professionals: players, managers, clubs; civil society, etc) for fund-raising towards improving healthcare in Nigeria is described. The policy implication of this paper includes employing multi-dimensional diplomacy for managing multi-stakeholder urban sports and health development programmes as a means of surmounting the problem of inadequate funding for urban health development in Cross River State, Nigeria. Although this article focuses on Nigeria, its description of health-care deficits and findings speak for much of sub-Saharan Africa and developing countries.

A novel intuitionistic fuzzy clustering method for geo-demographic analysis

Geo-Demographic Analysis (GDA) is an important tool to explore the underlying rules that regulate our world, and therefore, it has been widely applied to the development of effective socio-economic policies through the analysis of data generated from Geographic Information Systems (GIS). In GDA applications, clustering plays a major role however, the current state-of-the-art algorithms, namely the Fuzzy Geographically Weighted Clustering (FGWC), have demonstrated several limitations both in terms of speed and in terms of quality of the achieved results. Accordingly, in this paper, we propose a novel clustering algorithm for GDA application, based on recent results regarding intuitionistic fuzzy sets and the possibilistic fuzzy C-means, that aims at overcoming some of the limitations of the existing methods.

Data Mining in GIS: A Novel Context-Based Fuzzy Geographically Weighted ClusteringAlgorithm

Geographic Information Systems (GIS) play a very important role to researches and industries. In fact, there have been some studies related to the development of this kind of systems as well as methods of mining attribute GIS data. In this paper, we will explore an aspect of Data Mining in GIS, that is, GIS Clustering for Geo-Demographic Analysis and present a novel context-based fuzzy geographically weighted clustering algorithm to solve such task.

Comparison of two fuzzy algorithms in geodemographic segmentation analysis: The Fuzzy C-Means and Gustafson–Kessel methods

Clustering techniques are frequently used to analyze census data and obtain meaningful large-scale groups. Geodemographic segmentation involves classifying small geographic areas – for example, block groups, census tracts, or neighborhoods - into relatively homogeneous segments. Most studies concerning geodemographic analysis and fuzzy logic employ the Fuzzy C-Means algorithm. In this paper, we compare two algorithms for fuzzy clustering in geodemographic analysis, and their structures, as well as their pros and cons, are analyzed. These are the Fuzzy C-Means algorithm and the Gustafson–Kessel algorithm The main objective of this paper is to evaluate the performance of the Fuzzy C-Means and Gustafson–Kessel algorithms in the clustering problem, under specific conditions. An experimental approach to this problem is adopted through the use of a real-world dataset describing 52 attributes of the 285 postal codes in the Athens metropolitan area.

Geodemographic analysis and the identification of potential business partnerships enabled by transit smart cards

Smart card automated fare payment systems are being adopted by transit agencies around the world. The data-storage characteristics of smart cards present novel opportunities to enhance transit services. On the one hand, there are fare policies, where smart card holders are given specific rebates on the use of the service based on usage patterns or levels. On the other, there are non-fare policies, for instance if holders receive advantages, such as rebates and offers, from commercial partners. The purpose of this paper is to present a geodemographic framework to identify potential commercial partnerships that could exploit the characteristics of smart cards. The framework is demonstrated using data from Montreal, Canada. Household survey data, specifically trip ends, and business data points are jointly used to determine the exposure of various types of establishments to users of the Montreal Metro network. Spatial analysis of business establishments in the neighborhood of metro stations helps to identify potential commercial partners. The results illustrate the potential of geodemographic analysis to generate intelligence of commercial interest.

Geodemographics and spatial interaction: an integrated model for higher education

Spatial interaction modelling and geodemographic analysis have each developed as quite separate research traditions. In this paper, we present an integrated model that harnesses the power of spatial interaction modelling to behavioural insights derived from a geodemographic classification. This approach is applied to the modelling of participation in higher education (HE). A novel feature of the paper is the integration of national schools, colleges and HE data; a national model is then calibrated and tested against actual recorded flows of students into HE. The model is implemented within a Java framework and is presented as a first step towards providing a quantitative tool that can be used by HE stakeholders to explore policies relating to such topics as widening access to under-represented groups.

Use of geospatial neighborhood control locations for epidemiological analysis of community-level pet adoption patterns

To explore the joint effect of distance and neighborhood-level demographics on pet adoptions from an animal shelter by means of client segmentation, geospatial tools, and epidemiological techniques. Geocoded locations of 1,563 adoptions from an animal shelter in eastern Massachusetts and 4,700 geospatial control locations. Pet adoptions were geocoded to addresses by use of spatial analysis software for area-based analysis. A population of neighborhood control locations (proportional to human population at the level of the block group) was randomly generated. Adoption and control locations were spatially joined to census data and to defined lifestyle segments. The association of geodemographic variables with adoption was assessed by use of multivariate logistic regression. The shelter service area was not well described by individual geopolitical boundaries such as county. Locations that were < 9.7 km (6 miles) from the shelter, had higher block group median income, or had a greater proportion of households that were composed of married couples with children in the block group were associated with increased odds of being an adoption location. Neighborhood lifestyle characteristics affected the association between affluence and adoption. Controlling for distance of a location to the shelter markedly affected the strength of association with adoption. Results suggested that distance as well as neighborhood lifestyle characteristics profoundly influences shelter adoption patterns. Client segmentation and geodemographic analysis can reveal communities with increased likelihood of pet adoption from a shelter and help clarify adoption patterns.

Federal government assistance for web-based secondary education under poor socio-economic development conditions in Nigeria: Geodemographic and qualitative analyses

Within barely 15 to 20 years, information and communication technologies (ICTs)-driven new digital economy and high competition for global market share has engendered hunger for knowledge as one of the main drivers of economic development factor for cities, states, nations and organizations in advanced nations. For Nigeria, presenting scandalous poverty, afflicting 70 to 89% of its mostly rural and digitally excluded people, the need for building capacity in ICT is urgent and imperative. This paper examines the problem of lopsidedness in web assistance to secondary schools by Nigeria’s Federal Government through the Schoolnet’s Diginet programme. Models for promoting Internet use in Africa and Asia are presented. The method of geodemographic analysis was used to highlight inequalities in web assistance to Nigerian secondary (high) schools by computing per capita web assistance for secondary schools in Nigeria’s 36 states and Federal Capital Territory (Abuja). The results show that the highest share of web assistance to schools went to Nigeria’s Federal Capital Territory (Abuja), with a per capita web assistance of 3.56 x 10-6. The lowest web assistance shares were given to Kano and Lagos with per capita web assistance of 4.26 x 10-7 and 4.44 x 10-7 respectively. The value added by geodemographic analysis is demonstrated by highlighting the lowest per capita shares for Kano and Lagos highlighting interaction between high population sizes of these two most populous states (Kano: 9,383,682 and Lagos: 9,013,534) compared to other Nigerian states. It is argued that greater success in delivering social justice is achievable by applying evidence-based policy derived from geodemographic analysis in sharing web assistance that is commensurate with the populations’ need. While the use of population size is the starting point of this geodemographic method, other demographic variables (school aged youth, gender and so forth) may be used in further studies of this and related subjects. Such a transparent method promises to attract public-private partnership that Nigeria’s Federal Government has been inviting to manage schools in the country. Moreover, it avoids recurrent problems of inequality in resource allocation that has perpetually decimated Nigeria’s development programmes and processes. Key words: Information and communication technologies (ICTs), internet, high schools, geo-demographic analysis.

Neighborhoods, Ethnicity and School Choice: Developing a Statistical Framework for Geodemographic Analysis

Geodemographics as the “analysis of people by where they live” has origins in urban sociology and social mapping, and is experiencing a renaissance in applied spatial demography. However, some commentators have expressed reservations about the statistical limitations of common geodemographic practices, especially focusing on the potential internal heterogeneity of the geodemographic groupings, as well as the problem of clearly identifying predictor variables that might account for or explain the socioeconomic patterns revealed by geodemographic analyses. In this paper we argue that geodemographic typologies are structured methods for making sense of the spatial and socioeconomic patterns encoded within complex datasets such as national census data. By treating geodemographics as more a framework than a tool for analysis in its own right we are able to integrate it with the flexibility and statistical conventions offered by multilevel modeling. We demonstrate this with a case study of whether pupils from different types of neighborhood in Birmingham, England are more or less likely to attend their nearest state-funded secondary school and how that likelihood varies with the ethnic composition of the neighborhood. In so doing we build on previous research suggesting that ethnic segregation between schools is at least equal to that between neighborhoods in England and speculate in this regard on the consequences of current government plans to extend choice to parents within a schools market.

Schools, Pupil Behaviour and Young Offenders

This article is concerned with the role and potential of school as a site for programmes designed to prevent and reduce anti-social and criminal behaviour from young people. It sets out to evaluate the relevance of ‘geodemographic’ analysis, based on the MOSAIC postcode classification system, for the targeting and development of appropriate behaviour support and youth crime prevention programmes in and around schools in different circumstances. We use youth crime data from Nottinghamshire, for a four-and-a-half-year period (1999–2003), as a case study,1 in order to demonstrate the relationship between patterns of youth offending and type of residential neighbourhood. The paper draws upon research from diverse sources in the fields of criminology, education and social policy in order to consider the possible use of geodemographic analysis to target school and neighbourhood programmes. It concludes by presenting some of the tensions in this role for schools.

Policing Neighbourhoods: Exploring the Geographies of Crime, Policing and Performance Assessment

Recent developments under the Public Service Reform agenda in the United Kingdom have increasingly focused upon public accountability and the needs of local communities. Similarly, crime, fear of crime and the efficacy of public service delivery have become central to the domestic political debate in recent years, with all three main political parties campaigning on local policing issues in the run up to the 2005 General Election. This article explores the drive for robust performance assessment frameworks across different policing geographies and highlights some of the inconsistencies between the new localism agenda and current data infrastructures and analytical techniques. The significance of neighbourhood composition is expressed, and the potential of local analytical techniques for both performance assessment and resource determination is highlighted. Specifically, the value of geodemographic neighbourhood typologies, spatial analysis and geographical expertise in the evaluation of policing performance and the refinement of local service delivery is discussed.