Dataset Information

Leveraging insurance customer data to characterize socioeconomic indicators of Swiss municipalities.

ABSTRACT: The availability of reliable socioeconomic data is critical for the design of urban policies and the implementation of location-based services; however, often, their temporal and geographical coverage remain scarce. We explore the potential for insurance customers data to predict socioeconomic indicators of Swiss municipalities. First, we define a features space by aggregating at city-level individual customer data along several behavioral and user profile dimensions. Second, we collect official statistics shared by the Swiss authorities on a wide spectrum of categories: Population, Transportation, Work, Space and Territory, Housing, and Economy. Third, we adopt two spatial regression models exploring both global and local geographical dependencies to investigate their predictability. Results show consistently a correlation between insurance customer characteristics and official socioeconomic indexes. Performance fluctuates depending on the category, with values of R2 > 0.6 for several target variables using a 5-fold cross validation. As a case study, we focus on predicting the percentage of the population using public transportation and we discuss the implications on a regional scope. We believe that this methodology can support official statistical offices and it could open up new opportunities for the characterization of socioeconomic traits at highly-granular spatial and temporal scales.

SUBMITTER: Donadio L

PROVIDER: S-EPMC7928527 | biostudies-literature | 2021

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Leveraging insurance customer data to characterize socioeconomic indicators of Swiss municipalities.

Donadio Lorenzo L Schifanella Rossano R Binder Claudia R CR Massaro Emanuele E

PloS one 20210303 3

The availability of reliable socioeconomic data is critical for the design of urban policies and the implementation of location-based services; however, often, their temporal and geographical coverage remain scarce. We explore the potential for insurance customers data to predict socioeconomic indicators of Swiss municipalities. First, we define a features space by aggregating at city-level individual customer data along several behavioral and user profile dimensions. Second, we collect official ...[more]

PMID: 33657089

Similar Datasets

Project description:BackgroundAs universal health coverage becomes the norm in many countries, it is important to determine public priorities regarding benefits to include in health insurance coverage. We report results of participation in a decision exercise among residents of Switzerland, a high-income country with a long history of universal health insurance and deliberative democracy.MethodsWe adapted the Choosing Healthplans All Together (CHAT) tool, an exercise developed to transform complex healthcare allocation decisions into easily understandable choices, for use in Switzerland. We conducted CHAT exercises in twelve Swiss cities with recruitment from a range of socio-economic backgrounds, taking into account differences in language and culture.ResultsCompared to existing coverage, a majority of 175 participants accepted greater general practice gatekeeping (94%), exclusion of invasive life-sustaining measures in dying patients (80%), longer waiting times for non-urgent episodic care (78%), greater adherence to cost-effectiveness guidelines in chronic care (66%), and lower premium subsidies (51%). Most initially chose greater coverage for dental care (59%), quality of life (57%), and long-term care (90%). During group deliberations, participants increased coverage for out-of-pocket costs (58%) and mental health to current levels (41%) and beyond current levels for rehabilitation (50%), and decreased coverage for quality of life to current levels (74%). Following group deliberation, they tended to change their views back to below current coverage for help with out-of-pocket costs, and back to current levels for rehabilitation. Most participants accepted the plan as appropriate and fair. A significant number would have added nothing.ConclusionSwiss participants who have engaged in a priority setting exercise accept complex resource allocation trade-offs in healthcare coverage. Moreover, in the context of a well-funded healthcare system with universal coverage centered on individual choice, at least some of our participants believed a fully sufficient threshold of health insurance coverage was achieved.

Project description:BackgroundAn emergent group of studies have examined the extent under which ridesharing may decrease alcohol-related crashes in countries such as United States, United Kingdom, Brazil, and Chile. Virtually all existent studies have assumed that ridesharing is equally distributed across socioeconomic groups, potentially masking differences across them. We contribute to this literature by studying how socioeconomic status at the municipal level impacts Uber's effect on alcohol-related crashes.MethodsWe use data provided by Chile's Road Safety Commission considering all alcohol-related crashes, and fatal and severe alcohol-related injuries that occurred between January 2013 and September 2013 (before Uber) and January and September 2014 (with Uber) in Santiago. We first apply spatial autocorrelation techniques to examine the level of spatial dependence between the location of alcohol-related crashes with and without Uber. We then apply random-effects meta-analysis to obtain risk ratios of alcohol-related crashes by considering socioeconomic municipality differences before and after the introduction of Uber.ResultsIn both analyses, we find that the first 9 months of Uber in Santiago is associated with significant rate ratio decreases (RR = 0.71 [95% Confidence Interval (C.I.) 0.56, 0.89]) in high socioeconomic municipalities in all alcohol-related crashes and null (RR = 1.10 [95% C.I. 0.97, 1.23]) increases in low socioeconomic municipalities. No concomitant associations were observed in fatal alcohol-related crashes regardless of the socioeconomic municipality group.ConclusionsOne interpretation for the decline in alcohol-related crashes in high socioeconomic municipalities is that Uber may be a substitute form of transport for those individuals who have access to credit cards, and thus, could afford to pay for this service at the time they have consumed alcohol. Slight increases of alcohol-related crashes in low socioeconomic municipalities should be studied further since this could be related to different phenomena such as increases in alcohol sales and consumption, less access to the provision of public transport services in these jurisdictions, or biases in police reports.

Project description:Background: The reduction of child and adolescent deaths (defined as decedents aged 0-19 years) remains a crucial public health priority also in high-income countries such as Finland. There is evidence of a relationship between socioeconomic gradients and child mortality, but the association is considered complex and relatively poorly understood. Exploiting a Finnish dataset with nationwide coverage, the present study aimed to shed light on the sociodemographic predictors of child and adolescent mortality at the municipality level. Methods: A public database of Statistics Finland was queried for municipality-level data on sociodemographic traits and child and adolescent deaths in Finland during the years 2011-2018. The sociodemographic indicators included total population size, child and adolescent population size, sex distribution, mean age, education, unemployment, median income, population density, rurality, percentage of individuals living in their birth municipality, household size, overcrowded households, foreign language speakers, divorce rate, car ownership rate, and crime rate. The sociodemographic indicators were modeled against child and adolescent mortality by means of generalized estimating equations. Results: A total of 2,371 child and adolescent deaths occurred during the 8-year study period, yielding an average annual mortality rate of 26.7 per 100,000 individuals. Despite a fluctuating trend, the average annual decline in child and adolescent deaths was estimated to be 3% (95% confidence interval 1-5%). Of the sociodemographic indicators, population density was associated with higher child and adolescent mortality (rate ratio 1.03, 95% confidence interval 1.01-1.06), whereas the percentage of foreign language speakers was associated with lower child and adolescent mortality (0.96, 0.93-0.99). Conclusion: Densely populated areas should be the primary focus of efforts to reduce child and adolescent mortality. Of note is also the apparently protective effect of foreign language speakers for premature mortality. Future studies are welcomed to scrutinize the mediating pathways and individual-level factors behind the associations detected in this study.

Dataset Information

Leveraging insurance customer data to characterize socioeconomic indicators of Swiss municipalities.

Publications

Leveraging insurance customer data to characterize socioeconomic indicators of Swiss municipalities.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets