Prediction of consumers refill frequency of LPG: A study using explainable machine learning

Launched in 2016, the PMUY Programme of the Government of India aimed to provide 8 crore LPG connections to women in rural households over four years. After acquiring a new connection, some households appeared uninterested in ordering subsequent subsidized LPG refills, impacting programme's sustainability, and targeting strategy. We propose a prediction model using "Explainable Machine Learning" to anticipate the beneficiaries' refill frequency with a view to improving LPG-refills and social targeting. In this paper, we suggest an enhanced stacked SVM (ISS) model for classification, which is contrasted with state-of-art ML models: Random Forest (RF), SVM-RBF, Naive Bayes (NB), and Decision Tree (C5.0). Some of the performance matrices that are used to evaluate the models include accuracy, sensitivity, specificity, Cohen's Kappa statistics, Receiver Operating Characteristic curve (ROC), and area under the curve (AUC). The proposed approach, which was validated with 10-fold cross validation, produced the best overall accuracies for data splits of 50-50, 66-34, and 80-20. The "Explainable AI (XAI)" model has also been used to describe how models and features interact, and to discuss the importance of features and their contributions to prediction. The recommended XAI will aid in efficient "beneficiary targeting" and "policy interventions".

The economics of the COVID-19 pandemic: economic evaluation of government mitigation and suppression policies, health system innovations, and models of care

Background

The COVID-19 pandemic has impacted the scope of health economics literature, which will increasingly examine value beyond health care interventions such as government policy and broad health system innovations.

Aim

The study analyzes economic evaluations and methodologies evaluating government policies suppressing or mitigating transmission and reducing COVID-19, broad health system innovations, and models of care. This can facilitate future economic evaluations and assist government and public health policy decisions during pandemics.

Methods

The Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) was used. Methodological quality was quantified using the scoring criteria in European Journal of Health Economics, Consolidated Health Economic Evaluation Reporting Standards (CHEERS) 2022 Checklist and the National Institute for Health and Care Excellence's (NICE) Cost Benefit Analysis Checklist. PUBMED, Medline, and Google Scholar were searched from 2020-2021.

Results

Cost utility analysis (CUA) and cost benefit analysis (CBA) analyzing mortality, morbidity, quality adjusted life year (QALY) gained, national income loss, and value of production effectively evaluate government policies suppressing or mitigating COVID-19 transmission, disease, and impacting national income loss. The WHO's pandemic economic framework facilitates economic evaluations of social and movement restrictions. Social return on investment (SROI) links benefits to health and broader social improvements. Multi-criteria decision analysis (MCDA) can facilitate vaccine prioritization, equitable health access, and technology evaluation. Social welfare function (SWF) can account for social inequalities and population-wide policy impact. It is a generalization of CBA, and operationally, it is equal to an equity-weighted CBA. It can provide governments with a guideline for achieving the optimal distribution of income, which is vital during pandemics. Economic evaluations of broad health system innovations and care models addressing COVID-19 effectively use cost effectiveness analysis (CEA) that utilize decision trees and Monte Carlo models, and CUAs that effectively utilize decision trees and Markov models, respectively.

Conclusion

These methodologies are very instructive for governments, in addition to their current use of CBA and the value of a statistical life analytical tool. CUA and CBA effectively evaluate government policies suppressing or mitigating COVID-19 transmission, disease, and impacts on national income loss. CEA and CUA effectively evaluate broad health system innovations and care models addressing COVID-19. The WHO's framework, SROI, MCDA, and SWF can also facilitate government decision-making during pandemics.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10389-023-01919-z.

Understanding and Measuring Child Well-being in the Region of Attica, Greece: Round Five

This research paper aims to present the results of the implementation of the C.W.-SMILE tool that recorded child well-being in the second semester of the 2020-2021 school year. This is the fifth round of this ongoing diachronic research. The C.W.-SMILE tool consists of six dimensions: home conditions (D.1), nutrition (D.2), unemployment of guardians (D.3), free healthcare (D.4), moral education (D.5), and leisure (D.6). The first three dimensions concern children's economic well-being, while the latter three dimensions determine children's non-economic well-being. Based on welfare economics, the combination of economic well-being and non-economic well-being constitutes children's general (social) well-being. Each dimension consists of Simple Indicators. The paper also presents the results of the school year as a whole, to help investigate the evolving impact of the COVID-19 pandemic on children's well-being for more periods. The tool was used to measure the well-being of children in Attica, through questionnaires that were circulated in 22 public schools and three support centers of the organization 'The Smile of the Child' (25 units in total). The sample consisted of 509 children, belonging to three distinct school categories. The results of the second semester are mapped in seven clusters (relating to seven socio-economically homogenous groups of municipalities in Attica). Analysis of the results of the school year 2020-2021 was done based on the data collected from a sample of 1,623 children; in other words, it took into account the data relating to the entire samples that were surveyed in the first and second semesters. The central outcomes of all the previous rounds of the research are verified through a principal component analysis (PCA), and a multiple correspondence analysis (MCA) which are employed for the fifth round. Finally, the paper suggests an action plan of social welfare based on a ChoiCo game designed for the needs of the fifth round of the C.W.-SMILE research.

Policies for life sciences and healthcare in the global health framework

BACKGROUND

At a time when welfare contracts are in crisis, it is timely to discuss different forms of disruptive innovation and responses of medical finance and economic systems, especially adjusting with new instruments for recovery and innovative solutions for health reforms.

OBJECTIVE

The objective of this paper is to propose some ways to develop a framework for policy changes affecting life science sectors and healthcare. It aims to analyze the types of relationships between health or medical systems and the economic systems.

METHOD

Medical systems used to be generally closed systems, but the new forms of delivery, especially with increase of telehealth and Mobile health (Mhealth) solutions (boosted by the COVID-19 pandemic, such as online consultations), have open traditional boundaries and generate more interactions with economic systems. It also led to new institutional arrangements at federal, national, or local levels, with different power games according to the history of institutions and cultural differences between countries.

RESULTS

Which system dynamics prevail will also depend on the political systems in place, for instance very innovative open innovation systems dominated by private players such as the USA empower individuals and favor intuitive and entrepreneurial states. On the other hand, systems historically dominated by socialized insurance or former communist countries, have investigated "attunements" or adaptation mechanisms in system intelligence. However, systemic changes are not only implemented by traditional rulers (government agencies, federal reserve banks) but also face the emergence of systemic platforms dominated by Big Tech players. The new agendas expressed for instance in the United Nation (UN) framework and the set of Sustainable Development Goals (SDGs) for climate change and sustainable growth, also require global adjustment of supply and demand, in a context where the traditional drug/vaccine split is challenged by the new technologies (e.g., mRNA technologies). Investment for drug research led to the development of COVID-19 vaccines, but also potential cancer vaccines. Finally, welfare economics is increasingly criticized among economist circles; it requires new design for global value assessment framework, facing growing inequalities and inter-generational challenges in aging populations.

CONCLUSION

This paper contributes to new models of developments and different frameworks for multiple stakeholders with major technological changes.

Understanding and Measuring Child Well-being in the Region of Attica, Greece: Round four

This paper aims to present the results of implementing a new, multi-dimensional and cumulative tool that records the well-being of children in the 1st semester of the school year 2020-2021, which constitutes the fourth round of an ongoing research. The tool was implemented in Attica through questionnaires circulated in twenty-five schools and three support centers for children and families under the organization, "The Smile of the Child" (twenty-eight bodies in total). The total number of children who participated in the sample was 1,114, belonging to three distinct school categories: the 6th grade of elementary school (10-11 years old), the 3rd grade of junior high (13-14 years old), and the 3rd grade of high school (16-17 years old). The results, mapped out in seven clusters, reveal evident concerns over nutrition and the moral education of students. In addition, the results indicate the impact of the COVID-19 pandemic on the well-being of children and reveal with regard to national policy and legislation framework that the status of welfare state in Greece is ineffective and problematic. The theoretical and methodological framework of the study was confirmed through a multiple correspondence analysis (MCA) and a principal component analysis (PCA).The outputs of MCA reflect and confirm the good effect of "The Smile of the Child" for children in need. Finally, an action plan including the creation of policies based on public finance and fuzzy logic was suggested, the most important being the necessity of the establishment of a new Ministry for the protection of child well-being.

Understanding and Measuring Child Well-Being in the Region of Attica, Greece: Round Three

This research paper aims to present the results of implementing a new multi-dimensional and cumulative tool that records child well-being, in the 2nd semester of the school year 2019-2020, which is the third round of an ongoing research. It also presents the results of the same year as a whole, in order to investigate the impact of the COVID-19 pandemic on the well-being of children. The tool was applied in Attica through questionnaires, addressing 22 public schools and three support centers of the organization, The Smile of the Child (25 units in total). The number of children in the sample was 560, belonging to three distinct school categories. The results of the 2nd semester were mapped out in seven clusters. The analysis of the results of the school year 2019-2020 as a whole was applied on a sample of 1,731 children; in other words, it incorporated almost the entire sample of the surveys conducted in the 1st and 2nd semesters. Finally, an action plan, based on the legal framework, focusing on mitigating the negative effects of the pandemic on child well-being is suggested.

SUPPLEMENTARY INFORMATION

The online version contains supplementary material available at 10.1007/s12187-021-09910-4.

Higher-Order Optimality Conditions in Set-Valued Optimization with Respect to General Preference Mappings

We present higher order necessary conditions for a model of welfare economics, where the preference mapping has a star-shape property. We assume that the preferences can be satiable and can be described by an arbitrary preference set, without the use of utility functions. These conditions are formulated in terms of higher-order directional derivatives of multivalued mappings, and the variable domination structure is not given by cones.

Estimating the costs of non-medical consumption in life-years gained for economic evaluations

Including the costs of non-medical consumption in life years gained in economic evaluations of medical interventions has been controversial. This paper focuses on the estimation of these costs using Dutch data coming from cross-sectional household surveys consisting of 56,569 observations covering the years 1978-2004. We decomposed the costs of consumption into age, period and cohort effects and modelled the non-linear age and cohort patterns of consumption using P-splines. As consumption patterns depend on household composition, we also estimated household size using the same regression modeling strategy. Estimates of non-medical consumption and household size were combined with life tables to estimate the impact of including non-medical survivor costs on an incremental cost-effectiveness ratio (ICER). Results revealed that including non-medical survivor costs substantially increases the ICER, but the effect varies strongly with age. The impact of cohort effects is limited but ignoring household economies of scale results in a significant overestimation of non-medical costs. We conclude that a) ignoring the costs of non-medical consumption results in an underestimation of the costs of life prolonging interventions b) economies of scale within households with respect to consumption should be accounted for when estimating future costs.

The dangers of performative scientism as the alternative to anti-scientific policymaking: A critical, preliminary assessment of South Africa's Covid-19 response and its consequences

At the onset of the Covid-19 pandemic South Africa was praised for decisive political leadership based on scientific advice and the strictness of the measures it imposed to limit domestic spread of the virus. This paper critically examines the South African response through two conceptual frameworks. The first frames an optimal policy response as a solution to an intertemporal welfare-optimisation problem. The need for governments to balance epidemiological considerations and public health measures with the negative consequences of non-pharmaceutical interventions to limit transmission is particularly acute in developing countries. The second considers the use of scientific evidence and expertise through the lens of scientism - undue deference to science. The South African government erred towards drastic action in the face of predictions by some scientific advisors of a catastrophe, but initially without a clear, public long-term plan. Its lockdown has caused serious economic and societal harm across a range of measures. But these costs have not been matched by proportional benefits in health system preparedness or, based on evidence three months into the epidemic, a definitive improvement in expected long-term epidemic outcomes. This failure, and the questionably confident basis for the original lockdown decision, has been obscured by the government's performative scientism - a public performance of deference to science - even in the absence of transparent decision-making. One consequence was a slower correction of strategy than merited by evidence of limited benefits and high costs of the lockdown. Another was an unwillingness to admit and explain errors after the fact. The latter, combined with the convincingness of the initial performance undermined the behavioural dimension of policy - leading to beliefs among citizens that confounded efforts by the state to adapt its policy stance through reopening schools, reducing the stringency of clinical guidelines and resuming various economic activities while nevertheless observing basic social distancing precautions.

A welfare-theoretic model consistent with the practice of cost-effectiveness analysis and its implications

I look at three debates in the health economics literature in the context of cost-effectiveness analysis (CEA): 1) inclusion of future costs, 2) discounting, and 3) consistency with a welfare-economic perspective. These debates thus far have been studied in isolation leading to confusion and lingering questions. I look at these three debates holistically and present a welfare theoretic model that is consistent with the practice of CEA and can help inform all of these three debates. It shows rationales for the recommendations of the Second Panel and clarifies some nuanced implications for the practice of CEA when taking a societal perspective in the context of distributional CEA and multi-sectorial budgets.