•The DisCovER, a method able to improve diversity and accuracy of POI recommendation.•An adaptation of DisCovER able to personalize the diversity of POIs recomendation.•A deep experimental evaluation ...comparing DisCovER to the state-of-the-art algorithms.•An adaptation of the Multi-Attribute Utility (MAUT) for the Recommendation field.
Nowadays, recommender systems play an important role in several Location-Based Social Networks (LBSNs). The current advances have considered the trade-off between accuracy and diversity to help users to discover and explore new points-of-interest (POI). However, differently from traditional recommendation scenarios, other equally relevant dimensions (e.g., social and geographical user information) have to be considered to understand how the characteristics of services offered by each POI fit the user needs. Specifically, this work sheds light upon naive failures introduced by traditional recommendation methods while they handle this trade-off between diversity and accuracy in POI recommendations. We hypothesize that some efforts on POI recommendations somehow are deviating from basic learnings from the area. In this context, this work addresses four characteristics inherent to the POI domain that previous efforts have failed to recognize: (1) POI categories and locations are complementary dimensions of diversification that should be simultaneously addressed; (2) Diversity is a complex concept that should be modeled by distinct and non-orthogonal models; (3) Distinct users have different biases and willingness to move to fulfill their needs; (4) POI recommendation is a multi-objective task. In order to demonstrate the gains of properly addressing these aspects, we also propose DisCovER, a straightforward re-ordering method that linearly combines geographical and categorical diversification. DisCovER results demonstrate that even simple strategies to exploit simultaneously these complementary dimensions can increase diversification while keeping accuracy high. Differently from state-of-the-art diversification methods, DisCovER does not penalize any quality dimension in favor of others. It allows us to discuss future directions towards more robust user modeling and preference elicitation in POI domains.
Surgical volume was drastically reduced in many countries due to challenges imposed by the COVID-19 pandemic.
We sought to estimate the number of cancelled surgical and diagnostic procedures within ...the Brazilian private healthcare system between 2020 and 2021 over the course of the COVID-19 pandemic, and to project the procedural backlog generated for specific elective and time-sensitive surgeries, and diagnostic procedures.
Data were systematically extracted from the Brazilian national regulatory agency for the private healthcare system and included (i) quarterly and annual surgical and diagnostic volume, and (ii) the number of private health insurance beneficiaries between January 2016 and June 2021. Based on pre-pandemic data we estimated the expected number of surgical and diagnostic procedures that failed to be performed between 2020 and 2021.
The average quarterly surgical and diagnostic procedures declined by 29.5% in 2020 and by 21.5% in 2021 compared to 2019. In 2020, such reduction reflected a lower number of diagnostic procedures under anesthesia (-35.1%), as well as elective (-14.7%), time-sensitive (-18.8%), and urgent (-4.6%) surgeries. In the first half of 2021, though the surgical and diagnostic procedures increased compared to 2020, they remained significantly below their historical average. The estimated backlogs were 134.385,64 for total surgical procedures, 2.634,64 for bariatric surgery and arthroplasty revision (elective surgeries), 2.845,61 for oncologic (time-sensitive) surgeries, and 304.193,99 for diagnostic procedures, requiring 1.7, 15.9, and 6.8 years, respectively, to make up for such backlogs.
There was a major decline on the number of surgical and diagnostic procedures due to the COVID-19 pandemic. Despite a slight recovery of elective surgeries throughout the pandemic, many time-sensitive surgeries and diagnostic procedures were cancelled, with potential medium- to long-term consequences to patients and the system as a whole.
Two commonly used metrics for assessing progress toward universal health coverage involve assessing citizens' rights to health care and counting the number of people who are in a financial protection ...scheme that safeguards them from high health care payments. On these metrics most countries in Latin America have already "reached" universal health coverage. Neither metric indicates, however, whether a country has achieved universal health coverage in the now commonly accepted sense of the term: that everyone--irrespective of their ability to pay--gets the health services they need without suffering undue financial hardship. We operationalized a framework proposed by the World Bank and the World Health Organization to monitor progress under this definition and then constructed an overall index of universal health coverage achievement. We applied the approach using data from 112 household surveys from 1990 to 2013 for all twenty Latin American countries. No country has achieved a perfect universal health coverage score, but some countries (including those with more integrated health systems) fare better than others. All countries except one improved in overall universal health coverage over the time period analyzed.
Maternity leave policies are designed to protect gender equality and the health of mothers in the workforce and their children. However, maternity leave schemes are often linked to jobs in the formal ...sector economy. In low- and middle-income countries a large share of women work in the informal sector, and are not eligible to such benefit. This is worrisome from a social justice and a policy perspective and suggests the need for intervening. Costing the implementation of potential interventions is needed for facilitating informed decisions by policy makers.
We developed and applied a costing methodology to assess the cost of a maternity leave cash transfer to be operated in the informal sector of the economy in Brazil and Ghana, two countries with very different employment structures and socioeconomic contexts. We conducted sensitivity analysis by modeling different numbers of weeks covered.
In Brazil, the cost of the maternity cash transfer would be between 0.004% and 0.02% of the GDP, while in Ghana it would range between 0.076% and 0.28% of the GDP. The relative cost of rolling out a maternity intervention in Brazil is between 2.2 to 3.2 times the cost in Ghana depending on the benchmark used to assess the welfare measure. The differences in costs between countries was related to differences in labor market structure as well as demographic characteristics.
Findings show how a standard methodology that relies on routinely available information is feasible and could assist policymakers in estimating the costs of supporting a maternity cash transfer for women employed in the informal sector, such intervention is expected to contribute to social justice, gender equity, and health trajectories.
Estudos com edições anteriores da Pesquisa de Orçamentos Familiares (POF) indicam que, no Brasil, pagar um plano de saúde aumenta o percentual da renda gasto com saúde e não reduz a probabilidade de ...ter gastos excessivos com saúde. Descrevem-se relações entre gastos com planos de saúde, renda e faixas etárias, destacando o efeito de ter plano sobre a probabilidade de comprometer mais de 40% da renda com despesas relacionadas à saúde. Análise de microdados da POF 2017/2018 para determinar o comprometimento da renda domiciliar per capita dos pagantes de planos por faixa etária e por tipo de plano, e regressão logística para fatores associados a comprometer mais de 40% da renda com despesas de saúde. Em 12 meses, R$ 78,1 bilhões foram gastos com planos médicos por 22,1 milhões de pessoas. O comprometimento da renda com planos individuais aumenta consistentemente com a idade, passando de 4,5% da renda domiciliar per capita (< 19 anos) para 10,6% dessa renda (79 anos ou mais). A probabilidade de comprometer mais de 40% da renda com despesas de saúde diminui com a renda, cresce com a idade e é maior para quem paga plano de saúde. A despesa apenas com os planos supera 40% da renda domiciliar per capita para 5,6% das pessoas com 60 anos ou mais que pagam planos individuais e para 4% das que pagam planos empresariais. As pessoas nas faixas de idade mais altas e faixas de renda mais baixas são as com maior probabilidade de comprometer mais de 40% da renda com despesas de saúde. Rever as regras de reajuste por idade dos planos é uma alternativa para tentar mitigar esse problema.
According to studies using previous editions of the Household Budgets Survey (POF) in Brazil, paying for a healthcare plan increases the percentage of income spent on health and fails to reduce the probability of incurring excessive health expenditures. The study’s objective was to describe relations between expenditures on healthcare plans, income, and age groups, highlighting the effect of having a plan on the probability of committing more than 40% of income on health-related expenditures. An analysis of the POF 2017/2018 determined the commitment of per capita household income for payers of plans by age group and type of plan and logistic regression for factors associated with committing more than 40% of income to health-related expenditures. In 12 months, 22.1 million Brazilians spent BRL 78.1 billion on private medical insurance. The share of income spent on individual plans increases consistently with age, from 4.5% of per capita household income (at < 19 years) to 10.6% of this income (at 79 years or older). The probability of committing more than 40% of income to health expenditures decreases with income, increases with age, and is higher for those paying for health plans. Spending on healthcare plans alone exceeds 40% of per capita household income for 5.6% of Brazilians 60 years or older who pay for individual plans and for 4% of those who pay for company plans. Persons in the oldest age groups and in the lowest income brackets show the highest likelihood of spending more than 40% of their income on healthcare. A revision of the plans’ adjustment by age is an alternative for attempting to mitigate this problem.
Estudios con ediciones anteriores de la Encuesta de Presupuestos Familiares (POF) indican que, en Brasil, pagar un plan de salud aumenta el porcentaje de la renta gastado con salud y no reduce la probabilidad de tener gastos excesivos con la salud. El objetivo fue describir las relaciones entre gastos con planes de salud, renta y franjas de edad, destacando el efecto de tener un plan sobre la probabilidad de comprometer más de un 40% de la renta con gastos relacionados con la salud. Se realizó un análisis de microdatos de la POF 2017/2018 para determinar el comprometimiento de la renta domiciliaria per cápita de los pagadores de planes por franja etaria y por tipo de plan, así como una regresión logística para factores asociados con comprometer más de un 40% de la renta con gastos de salud. En 12 meses, BRL 78,1 mil millones se gastaron con planes médicos por 22,1 millones de personas. El comprometimiento de la renta con planes individuales aumenta consistentemente con la edad, pasando de 4,5% de la renta domiciliaria per cápita (< 19 años) al 10,6% de esa renta (79 años o más). La probabilidad de comprometer más de un 40% de la renta con gastos de salud disminuye con la renta, crece con la edad y es mayor para quien paga un plan de salud. El gasto solo con los planes supera un 40% de la renta domiciliaria per cápita para un 5,6% de las personas con 60 años o más que pagan planes individuales y para un 4% de los que pagan planes empresariales. Las personas en las franjas de edad más altas y franjas de renta más bajas son las que tienen mayor probabilidad de comprometer más de un 40% de la renta con gastos de salud. Revisar las reglas de reajuste por edad de los planes es una alternativa para intentar mitigar ese problema.
In 1988, the Brazilian Constitution defined health as a universal right and a state responsibility. Progress towards universal health coverage in Brazil has been achieved through a unified health ...system (Sistema Único de Saúde SUS), created in 1990. With successes and setbacks in the implementation of health programmes and the organisation of its health system, Brazil has achieved nearly universal access to health-care services for the population. The trajectory of the development and expansion of the SUS offers valuable lessons on how to scale universal health coverage in a highly unequal country with relatively low resources allocated to health-care services by the government compared with that in middle-income and high-income countries. Analysis of the past 30 years since the inception of the SUS shows that innovations extend beyond the development of new models of care and highlights the importance of establishing political, legal, organisational, and management-related structures, with clearly defined roles for both the federal and local governments in the governance, planning, financing, and provision of health-care services. The expansion of the SUS has allowed Brazil to rapidly address the changing health needs of the population, with dramatic upscaling of health service coverage in just three decades. However, despite its successes, analysis of future scenarios suggests the urgent need to address lingering geographical inequalities, insufficient funding, and suboptimal private sector–public sector collaboration. Fiscal policies implemented in 2016 ushered in austerity measures that, alongside the new environmental, educational, and health policies of the Brazilian government, could reverse the hard-earned achievements of the SUS and threaten its sustainability and ability to fulfil its constitutional mandate of providing health care for all.
Recommender Systems (RSs) have assumed a crucial role in several digital companies by directly affecting their key performance indicators. Nowadays, in this era of big data, the information available ...about users and items has been continually updated and the application of traditional batch learning paradigms has become more restricted. In this sense, the current efforts in the recommendation field have concerned about this online environment and modeled their systems as a Multi-Armed Bandit (MAB) problem. Nevertheless, there is not a consensus about the best practices to design, perform, and evaluate the MAB implementations in the recommendation field. Thus, this work performs a systematic literature review (SLR) to shed light on this new topic. By inspecting 1327 articles published from the last twenty years (2000–2020), this work: (1) consolidates an updated picture of the main research conducted in this area so far; (2) highlights the most used concepts and methods, their core characteristics, and main limitations; and (3) evaluates the applicability of MAB-based recommendation approaches in some traditional RSs’ challenges, such as data sparsity, scalability, cold-start, and explainability. These discussions and analyzes also allow us to identify several gaps in the current literature, providing a strong guideline for future research.
•A literature review of studies about MAB in recommender systems from 2000 to 2020.•A discussion about MAB algorithms, datasets, and evaluation metrics.•An updated panorama about the current practices and models applied in MAB researches.•Discussion on the applicability of MAB models in the main recommendation challenges.•Future directions to be explored by using MAB in the recommendation field.
The emergence of Location-based social networks (LBSNs) in recent years has boosted improvements in Recommender Systems for a new and specific task: the recommendation of points-of-interest (POI). ...Despite all the blunt advances recently observed, the area still lacks an updated and consolidated view about the main limitations, common assumptions, and directions we are following as a community. Thus, this paper aims to provide an updated picture of POI recommendation, identifying relevant efforts, results, contributions, and limitations. In this sense, through a systematic mapping, we selected 74 relevant papers published in the last three years (2017, 2018, and 2019) in the main conferences and journals of the area. Most of these studies have focused on the general POI recommendation problem, although we still could identify a significant number of efforts addressing specific problems in the area, such as Time-Aware, Next POI, and In/Out-of-Town Recommendations. Also, we found user contexts, such as social network and geolocation, as recurring data types used to improve preference elicitation when exploring different methods (e.g., collaborative filtering, factorization, probabilistic, link-based, and hybrid methods). As major limitations, first, we identified that these studies prioritize accuracy over other quality dimensions, despite the consensus in the RS community that accuracy alone is not enough to assess the practical effectiveness of Recommender Systems. Further, we found a low intersection of metrics and datasets used to evaluate the proposed solutions, along with a large number of metrics used in a few distinct studies. These observations point out the potential damage to reproducibility and straightforward comparison of results in the area, motivating us to propose an extensible POI recommendation benchmark. Through this benchmark, we showed that when proper evaluations are carried out, by considering different datasets, metrics, and baselines, identifying which algorithm is the best one becomes non-trivial. Finally, we highlight as a promising future work the in-depth exploitation of textual data since just a few evaluated studies marginally use this rich data source.
•A systematic mapping of the POI recommendation area.•An analysis of 74 studies of the main conferences and journals from lat three years.•A discussion of contributions/limitations of recent studies on POI recommendation.•An extensible POI recommendation benchmark.•Directions for future works highlighting the needs of the reproducibility of results.
This work is a companion reproducibility paper that presents a framework to reproduce our previous experiments and results reported in Werneck et al. (2021). In that previous paper, we introduced a ...systematic mapping process of points-of-interest (POI) recommendation methods and provided a uniform evaluation methodology based on metrics covering different aspects besides accuracy. Due to the lack of reproducible and extensible benchmarks, our work introduces a reproducibility framework for POI methods based on a collection of Python software libraries and a Docker image. Our proposal is composed of: (1) a package to perform a protocol that reproduces our systematic mapping process Werneck et al. (2021), containing all collected data, insightful views on current advances and opened challenges; and (2) an extensible benchmark to perform a protocol to reproduce experimental evaluations on POI recommendation, considering different datasets, metrics, and the strongest baselines in the literature. This work also demonstrates all processes required to instantiate its framework. Moreover, our work can be considered at least weakly reproducible, since we were able to reproduce the results of the previous paper, leading us to the same conclusions.
•A companion reproducibility paper about POI recommendation.•An extensible benchmark about POI recommendation.•A collection of Python software libraries and a Docker image.•A package to perform a protocol that reproduces our systematic mapping process.•A detailed reproducibility analysis of the primary work.
According to studies using previous editions of the Household Budgets Survey (POF) in Brazil, paying for a healthcare plan increases the percentage of income spent on health and fails to reduce the ...probability of incurring excessive health expenditures. The study's objective was to describe relations between expenditures on healthcare plans, income, and age groups, highlighting the effect of having a plan on the probability of committing more than 40% of income on health-related expenditures. An analysis of the POF 2017/2018 determined the commitment of per capita household income for payers of plans by age group and type of plan and logistic regression for factors associated with committing more than 40% of income to health-related expenditures. In 12 months, 22.1 million Brazilians spent BRL 78.1 billion on private medical insurance. The share of income spent on individual plans increases consistently with age, from 4.5% of per capita household income (at < 19 years) to 10.6% of this income (at 79 years or older). The probability of committing more than 40% of income to health expenditures decreases with income, increases with age, and is higher for those paying for health plans. Spending on healthcare plans alone exceeds 40% of per capita household income for 5.6% of Brazilians 60 years or older who pay for individual plans and for 4% of those who pay for company plans. Persons in the oldest age groups and in the lowest income brackets show the highest likelihood of spending more than 40% of their income on healthcare. A revision of the plans' adjustment by age is an alternative for attempting to mitigate this problem.