Predicting neighborhoods' socioeconomic attributes using restaurant data.
ABSTRACT: Accessing high-resolution, timely socioeconomic data such as data on population, employment, and enterprise activity at the neighborhood level is critical for social scientists and policy makers to design and implement location-based policies. However, in many developing countries or cities, reliable local-scale socioeconomic data remain scarce. Here, we show an easily accessible and timely updated location attribute-restaurant-can be used to accurately predict a range of socioeconomic attributes of urban neighborhoods. We merge restaurant data from an online platform with 3 microdatasets for 9 Chinese cities. Using features extracted from restaurants, we train machine-learning models to estimate daytime and nighttime population, number of firms, and consumption level at various spatial resolutions. The trained model can explain 90 to 95% of the variation of those attributes across neighborhoods in the test dataset. We analyze the tradeoff between accuracy, spatial resolution, and number of training samples, as well as the heterogeneity of the predicted results across different spatial locations, demographics, and firm industries. Finally, we demonstrate the cross-city generality of this method by training the model in one city and then applying it directly to other cities. The transferability of this restaurant model can help bridge data gaps between cities, allowing all cities to enjoy big data and algorithm dividends.
Project description:BACKGROUND:Dengue is a mosquito-borne virus that causes extensive morbidity and economic loss in many tropical and subtropical regions of the world. Often present in cities, dengue virus is rapidly spreading due to urbanization, climate change and increased human movements. Dengue cases are often heterogeneously distributed throughout cities, suggesting that small-scale determinants influence dengue urban transmission. A better understanding of these determinants is crucial to efficiently target prevention measures such as vector control and education. The aim of this study was to determine which socioeconomic and environmental determinants were associated with dengue incidence in an urban setting in the Pacific. METHODOLOGY:An ecological study was performed using data summarized by neighborhood (i.e. the neighborhood is the unit of analysis) from two dengue epidemics (2008-2009 and 2012-2013) in the city of Nouméa, the capital of New Caledonia. Spatial patterns and hotspots of dengue transmission were assessed using global and local Moran's I statistics. Multivariable negative binomial regression models were used to investigate the association between dengue incidence and various socioeconomic and environmental factors throughout the city. PRINCIPAL FINDINGS:The 2008-2009 epidemic was spatially structured, with clusters of high and low incidence neighborhoods. In 2012-2013, dengue incidence rates were more homogeneous throughout the city. In all models tested, higher dengue incidence rates were consistently associated with lower socioeconomic status (higher unemployment, lower revenue or higher percentage of population born in the Pacific, which are interrelated). A higher percentage of apartments was associated with lower dengue incidence rates during both epidemics in all models but one. A link between vegetation coverage and dengue incidence rates was also detected, but the link varied depending on the model used. CONCLUSIONS:This study demonstrates a robust spatial association between dengue incidence rates and socioeconomic status across the different neighborhoods of the city of Nouméa. Our findings provide useful information to guide policy and help target dengue prevention efforts where they are needed most.
Project description:This data article describes data from an Our Voice citizen science data collection aiming at identifying elements that facilitate or hinder physical activity among adolescents in a medium sized city in Sweden. Twenty-four adolescents from two neighborhoods with low socioeconomic status in Sweden used the Stanford Healthy Neighborhood Discovery Tool app on their phones to take photographs and record audio narratives of aspects of their neighborhood that they perceived as facilitating or hindering their physically activity. In total, 186 photos of the neighborhood elements were taken by the adolescents and thereafter the research group categorized the photos into a final set of 16 elements of which 12 described the built environment and 4 the social environment. The data collection included the combination of the following data collected using the app: photographs, geocoded data of where the photographs were taken, recorded narratives describing the photographs, positive and negative neighborhood attributes (portrayed as a happy or sad "smiley face"), and an 8-item survey. In addition, we used official statistics from the City of Västerås describing the two neighborhoods as well as the whole city. This data article is associated with the article titled "Using citizen science to understand the prerequisites for physical activity among adolescents in low socioeconomic status neighborhoods - the NESLA study" .
Project description:Spatial differences in urban environmental conditions contribute to health inequalities within cities. The purpose of the paper is to map environmental inequalities relevant for health in the City of Dortmund, Germany, in order to identify needs for planning interventions. We develop suitable indicators for mapping socioeconomically-driven environmental inequalities at the neighborhood level based on published scientific evidence and inputs from local stakeholders. Relationships between socioeconomic and environmental indicators at the level of 170 neighborhoods were analyzed continuously with Spearman rank correlation coefficients and categorically applying chi-squared tests. Reclassified socioeconomic and environmental indicators were then mapped at the neighborhood level in order to determine multiple environmental burdens and hotspots of environmental inequalities related to health. Results show that the majority of environmental indicators correlate significantly, leading to multiple environmental burdens in specific neighborhoods. Some of these neighborhoods also have significantly larger proportions of inhabitants of a lower socioeconomic position indicating hotspots of environmental inequalities. Suitable planning interventions mainly comprise transport planning and green space management. In the conclusions, we discuss how the analysis can be used to improve state of the art planning instruments, such as clean air action planning or noise reduction planning towards the consideration of the vulnerability of the population.
Project description:Socioeconomic inequalities in cities are embedded in space and result in neighborhood effects, whose harmful consequences have proved very hard to counterbalance efficiently by planning policies alone. Considering redistribution of money flows as a first step toward improved spatial equity, we study a bottom-up approach that would rely on a slight evolution of shopping mobility practices. Building on a database of anonymized card transactions in Madrid and Barcelona, we quantify the mobility effort required to reach a reference situation where commercial income is evenly shared among neighborhoods. The redirections of shopping trips preserve key properties of human mobility, including travel distances. Surprisingly, for both cities only a small fraction (?5%) of trips need to be modified to reach equality situations, improving even other sustainability indicators. The method could be implemented in mobile applications that would assist individuals in reshaping their shopping practices, to promote the spatial redistribution of opportunities in the city.
Project description:While urban systems demonstrate high spatial heterogeneity, many urban planning, economic and political decisions heavily rely on a deep understanding of local neighborhood contexts. We show that the structure of 311 Service Requests enables one possible way of building a unique signature of the local urban context, thus being able to serve as a low-cost decision support tool for urban stakeholders. Considering examples of New York City, Boston and Chicago, we demonstrate how 311 Service Requests recorded and categorized by type in each neighborhood can be utilized to generate a meaningful classification of locations across the city, based on distinctive socioeconomic profiles. Moreover, the 311-based classification of urban neighborhoods can present sufficient information to model various socioeconomic features. Finally, we show that these characteristics are capable of predicting future trends in comparative local real estate prices. We demonstrate 311 Service Requests data can be used to monitor and predict socioeconomic performance of urban neighborhoods, allowing urban stakeholders to quantify the impacts of their interventions.
Project description:Evidence of the association of built environment (BE) attributes with the spread of COVID-19 remains limited. As an additional effort, this study regresses a ratio of accumulative confirmed infection cases at the city level in China on both inter-city and intra-city BE attributes. A mixed geographically weighted regression model was estimated to accommodate both local and global effects of BE attributes. It is found that spatial clusters are mostly related to low infections in 28.63 % of the cities. The density of point of interests around railway stations, travel time by public transport to activity centers, and the number of flights from Hubei Province are associated with the spread. On average, the most influential BE attribute is the number of trains from Hubei Province. Higher infection ratios are associated with higher values of between-ness centrality in 70.98 % of the cities. In 79.22 % of the cities, the percentage of the aging population shows a negative association. A positive association of the population density in built-up areas is found in 68.75 % of county-level cities. It is concluded that the countermeasures in China could have well reflected spatial heterogeneities, and the BE could be further improved to mitigate the impacts of future pandemics.
Project description:<h4>Background</h4>Most heat-related deaths occur in cities, and future trends in global climate change and urbanization may amplify this trend. Understanding how neighborhoods affect heat mortality fills an important gap between studies of individual susceptibility to heat and broadly comparative studies of temperature-mortality relationships in cities.<h4>Objectives</h4>We estimated neighborhood effects of population characteristics and built and natural environments on deaths due to heat exposure in Maricopa County, Arizona (2000-2008).<h4>Methods</h4>We used 2000 U.S. Census data and remotely sensed vegetation and land surface temperature to construct indicators of neighborhood vulnerability and a geographic information system to map vulnerability and residential addresses of persons who died from heat exposure in 2,081 census block groups. Binary logistic regression and spatial analysis were used to associate deaths with neighborhoods.<h4>Results</h4>Neighborhood scores on three factors-socioeconomic vulnerability, elderly/isolation, and unvegetated area-varied widely throughout the study area. The preferred model (based on fit and parsimony) for predicting the odds of one or more deaths from heat exposure within a census block group included the first two factors and surface temperature in residential neighborhoods, holding population size constant. Spatial analysis identified clusters of neighborhoods with the highest heat vulnerability scores. A large proportion of deaths occurred among people, including homeless persons, who lived in the inner cores of the largest cities and along an industrial corridor.<h4>Conclusions</h4>Place-based indicators of vulnerability complement analyses of person-level heat risk factors. Surface temperature might be used in Maricopa County to identify the most heat-vulnerable neighborhoods, but more attention to the socioecological complexities of climate adaptation is needed.
Project description:BACKGROUND:Latin America is one of the most unequal regions in the world, but evidence is lacking on the magnitude of health inequalities in urban areas of the region. Our objective was to examine inequalities in life expectancy in six large Latin American cities and its association with a measure of area-level socioeconomic status. METHODS:In this ecological analysis, we used data from the Salud Urbana en America Latina (SALURBAL) study on six large cities in Latin America (Buenos Aires, Argentina; Belo Horizonte, Brazil; Santiago, Chile; San José, Costa Rica; Mexico City, Mexico; and Panama City, Panama), comprising 266 subcity units, for the period 2011-15 (expect for Panama city, which was for 2012-16). We calculated average life expectancy at birth by sex and subcity unit with life tables using age-specific mortality rates estimated from a Bayesian model, and calculated the difference between the ninth and first decile of life expectancy at birth (P90-P10 gap) across subcity units in cities. We also analysed the association between life expectancy at birth and socioeconomic status at the subcity-unit level, using education as a proxy for socioeconomic status, and whether any geographical patterns existed in cities between subcity units. FINDINGS:We found large spatial differences in average life expectancy at birth in Latin American cities, with the largest P90-P10 gaps observed in Panama City (15·0 years for men and 14·7 years for women), Santiago (8·9 years for men and 17·7 years for women), and Mexico City (10·9 years for men and 9·4 years for women), and the narrowest in Buenos Aires (4·4 years for men and 5·8 years for women), Belo Horizonte (4·0 years for men and 6·5 years for women), and San José (3·9 years for men and 3·0 years for women). Higher area-level socioeconomic status was associated with higher life expectancy, especially in Santiago (change in life expectancy per P90-P10 change unit-level of educational attainment 8·0 years [95% CI 5·8-10·3] for men and 11·8 years [7·1-16·4] for women) and Panama City (7·3 years [2·6-12·1] for men and 9·0 years [2·4-15·5] for women). We saw an increase in life expectancy at birth from east to west in Panama City and from north to south in core Mexico City, and a core-periphery divide in Buenos Aires and Santiago. Whereas for San José the central part of the city had the lowest life expectancy and in Belo Horizonte the central part of the city had the highest life expectancy. INTERPRETATION:Large spatial differences in life expectancy in Latin American cities and their association with social factors highlight the importance of area-based approaches and policies that address social inequalities in improving health in cities of the region. FUNDING:Wellcome Trust.
Project description:BACKGROUND: Epidemiologic studies have linked exposure to traffic-generated air and noise pollution with a wide range of adverse health effects in children. Children spend a large portion of time at school, and both air pollution and noise are elevated in close proximity to roads, so school location may be an important determinant of exposure. No studies have yet examined the proximity of schools to major roads in Canadian cities. METHODS: Data on public elementary schools in Canada's 10 most populous cities were obtained from online databases. School addresses were geocoded and proximity to the nearest major road, defined using a standardized national road classification scheme, was calculated for each school. Based on measurements of nitrogen oxide concentrations, ultrafine particle counts, and noise levels in three Canadian cities we conservatively defined distances < 75 m from major roads as the zone of primary interest. Census data at the city and neighborhood levels were used to evaluate relationships between school proximity to major roads, urban density, and indicators of socioeconomic status. RESULTS: Addresses were obtained for 1,556 public elementary schools, 95% of which were successfully geocoded. Across all 10 cities, 16.3% of schools were located within 75 m of a major road, with wide variability between cities. Schools in neighborhoods with higher median income were less likely to be near major roads (OR per $20,000 increase: 0.81; 95% CI: 0.65, 1.00), while schools in densely populated neighborhoods were more frequently close to major roads (OR per 1,000 dwellings/km²: 1.07; 95% CI: 1.00, 1.16). Over 22% of schools in the lowest neighborhood income quintile were close to major roads, compared to 13% of schools in the highest income quintile. CONCLUSIONS: A substantial fraction of students at public elementary schools in Canada, particularly students attending schools in low income neighborhoods, may be exposed to elevated levels of air pollution and noise while at school. As a result, the locations of schools may negatively impact the healthy development and academic performance of a large number of Canadian children.
Project description:Few studies have considered the role of immigration in the rise of gentrification in the late twentieth century. Analysis of U.S. Census and American Community Survey data over 24 years and field surveys of gentrification in low-income neighborhoods across 23 U.S. cities reveal that most gentrifying neighborhoods were "global" in the 1970s or became so over time. An early presence of Asians was positively associated with gentrification; and an early presence of Hispanics was positively associated with gentrification in neighborhoods with substantial shares of blacks and negatively associated with gentrification in cities with high Hispanic growth, where ethnic enclaves were more likely to form. Low-income, predominantly black neighborhoods and neighborhoods that became Asian and Hispanic destinations remained ungentrified despite the growth of gentrification during the late twentieth century. The findings suggest that the rise of immigration after 1965 brought pioneers to many low-income central-city neighborhoods, spurring gentrification in some neighborhoods and forming ethnic enclaves in others.