Nowadays public policymakers are offered with opportunities to take data-driven evidence-based decisions by analyzing the very large volumes of policy-related data that are generated through different channels (e.g., e-services, mobile apps, social media). Machine learning (ML) and artificial intelligence (AI) tehcnologies ease and automate the analysis of large policy-related datasets, which helps policymakers to realize a shift toward data-driven decisions. Nevertheless, the deployment and use of AI tools for public policy development is also associated with significant technical, political, and operation challenges. For instance, AI-based policy development solutions must be transparent and explainable to policymakers, while at the same time adhering to the mandates of emerging regulations such as the AI Act of the European Union. This paper introduces some of the main technical, operational, regulatory compliance challenges of AI-based policymaking. Accordingly, it introduces technological solutions for overcoming them, including: (i) a reference architecture for AI-based policy development, (ii) a virtualized cloud-based tool for the specification and implementation of ML-based data-driven policies, (iii) a ML framework that enables the development of transparent and explainable ML models for policymaking, and (iv) a set of guidelines for using the introduced technical solutions to achieve regulatory compliance. The paper ends up illustrating the validation and use of the introduced solutions in real-life public policymaking cases for various local governments.

We develop a flexible Gaussian process (GP) framework for learning the covariance structure of Age- and Year-specific mortality surfaces. Utilizing the additive and multiplicative structure of GP kernels, we design a genetic programming algorithm to search for the most expressive kernel for a given population. Our compositional search builds off the Age–Period–Cohort (APC) paradigm to construct a covariance prior best matching the spatio-temporal dynamics of a mortality dataset. We apply the resulting genetic algorithm (GA) on synthetic case studies to validate the ability of the GA to recover APC structure and on real-life national-level datasets from the Human Mortality Database. Our machine learning-based analysis provides novel insight into the presence/absence of Cohort effects in different populations and into the relative smoothness of mortality surfaces along the Age and Year dimensions. Our modeling work is done with the PyTorch libraries in Python and provides an in-depth investigation of employing GA to aid in compositional kernel search for GP surrogates.

Cointegrating polynomial regressions (CPRs) include deterministic variables, integrated variables, and their powers as explanatory variables. Based on a novel kernel-weighted limit result and a novel functional central limit theorem, this paper shows that the fully modified ordinary least squares (FM-OLS) estimator of Phillips and Hansen (1990, Review of Economic Studies 57, 99–125) is robust to being used in CPRs. Being used in CPRs refers to a widespread empirical practice that treats the integrated variables and their powers, incorrectly, as a vector of integrated variables and uses textbook FM-OLS. Robustness means that this “formal” FM-OLS practice leads to a zero mean Gaussian mixture limiting distribution that coincides with the limiting distribution of the Wagner and Hong (2016, Econometric Theory 32, 1289–1315) application of the FM estimation principle to the CPR case. The only restriction for this result to hold is that all integrated variables to power one are included as regressors. Even though simulation results indicate performance advantages of the Wagner and Hong (2016, Econometric Theory 32, 1289–1315) estimator, partly even in large samples, the results of the paper give an asymptotic foundation to “formal” FM-OLS and thus enlarge the usability of the Phillips and Hansen (1990, Review of Economic Studies 57, 99–125) estimator implemented in many software packages.

We report an outbreak of confirmed Mycoplasma pneumoniae community-acquired pneumonia (CAP) in Nord Franche-Comté Hospital, France, from 14 November 2023 to 31 January 2024. All 13 inpatients (11 adults with a mean age of 45.5 years and 2 children) were diagnosed with positive serology and/or positive reverse transcription polymerase chain reaction (RT-PCR) on respiratory specimens. All patients were immunocompetent and required oxygen support with a mean duration of oxygen support of 6.2 days. Two patients were transferred to the intensive care unit (ICU) but were not mechanically ventilated. Patients were treated with macrolides (n = 12, 92.3%) with recovery in all cases. No significant epidemiological link was reported in these patients.

While driver telematics has gained attention for risk classification in auto insurance, scarcity of observations with telematics features has been problematic, which could be owing to either privacy concerns or favorable selection compared to the data points with traditional features.

To handle this issue, we apply a data integration technique based on calibration weights for usage-based insurance with multiple sources of data. It is shown that the proposed framework can efficiently integrate traditional data and telematics data and can also deal with possible favorable selection issues related to telematics data availability. Our findings are supported by a simulation study and empirical analysis in a synthetic telematics dataset.

We consider estimation of the spot volatility in a stochastic boundary model with one-sided microstructure noise for high-frequency limit order prices. Based on discrete, noisy observations of an Itô semimartingale with jumps and general stochastic volatility, we present a simple and explicit estimator using local order statistics. We establish consistency and stable central limit theorems as asymptotic properties. The asymptotic analysis builds upon an expansion of tail probabilities for the order statistics based on a generalized arcsine law. In order to use the involved distribution of local order statistics for a bias correction, an efficient numerical algorithm is developed. We demonstrate the finite-sample performance of the estimation in a Monte Carlo simulation.

We present novel cross-sectional and longitudinal claim count models for vehicle insurance built upon the combinedd actuarial neural network (CANN) framework proposed by Wüthrich and Merz. The CANN approach combines a classical actuarial model, such as a generalized linear model, with a neural network. This blending of models results in a two-component model comprising a classical regression model and a neural network part. The CANN model leverages the strengths of both components, providing a solid foundation and interpretability from the classical model while harnessing the flexibility and capacity to capture intricate relationships and interactions offered by the neural network. In our proposed models, we use well-known log-linear claim count regression models for the classical regression part and a multilayer perceptron (MLP) for the neural network part. The MLP part is used to process telematics car driving data given as a vector characterizing the driving behavior of each insured driver. In addition to the Poisson and negative binomial distributions for cross-sectional data, we propose a procedure for training our CANN model with a multivariate negative binomial specification. By doing so, we introduce a longitudinal model that accounts for the dependence between contracts from the same insured. Our results reveal that the CANN models exhibit superior performance compared to log-linear models that rely on manually engineered telematics features.

This paper introduces gemact, a Python package for actuarial modeling based on the collective risk model. The library supports applications to risk costing and risk transfer, loss aggregation, and loss reserving. We add new probability distributions to those available in scipy, including the (a, b, 0) and (a, b, 1) discrete distributions, copulas of the Archimedean family, the Gaussian, the Student t and the Fundamental copulas. We provide an implementation of the AEP algorithm for calculating the cumulative distribution function of the sum of dependent, nonnegative random variables, given their dependency structure specified with a copula. The theoretical framework is introduced at the beginning of each section to give the reader with a sufficient understanding of the underlying actuarial models.

We establish the exponential nonuniform Berry–Esseen bound for the maximum likelihood estimator of unknown drift parameter in an ultraspherical Jacobi process using the change of measure method and precise asymptotic analysis techniques. As applications, the optimal uniform Berry–Esseen bound and optimal Cramér-type moderate deviation for the corresponding maximum likelihood estimator are obtained.

We show that an estimate by de la Peña, Ibragimov, and Jordan for ${\mathbb{E}}(X-c)^+$, with c a constant and X a random variable of which the mean, the variance, and $\mathbb{P}(X \leqslant c)$ are known, implies an estimate by Scarf on the infimum of ${\mathbb{E}}(X \wedge c)$ over the set of positive random variables X with fixed mean and variance. This also shows, as a consequence, that the former estimate implies an estimate by Lo on European option prices.

This review aims to assess the prevalence of malaria in pregnancy during antenatal visits and delivery, species-specific burden together with regional variation in the burden of disease. It also aims to estimate the proportions of adverse pregnancy outcomes in malaria-positive women. Based on the PRISMA guidelines, a thorough and systematic search was conducted in July 2023 across two electronic databases (including PubMed and CENTRAL). Forest plots were constructed for each outcome of interest highlighting the effect measure, confidence interval, sample size, and its associated weightage. All the statistical meta-analysis were conducted using R-Studio version 2022.07. Sensitivity analyses, publication bias assessment, and meta-regression analyses were also performed to ensure robustness of the review. According to the pooled estimates of 253 studies, the overall prevalence of malaria was 18.95% (95% CI: 16.95–21.11), during antenatal visits was 20.09% (95% CI: 17.43–23.06), and at delivery was 17.32% (95% CI: 14.47–20.61). The highest proportion of malarial infection was observed in Africa approximating 21.50% (95% CI: 18.52–24.81) during ANC and 20.41% (95% CI: 17.04–24.24) at the time of delivery. Our analysis also revealed that the odds of having anaemia were 2.40 times (95% CI: 1.87–3.06), having low birthweight were 1.99 times (95% CI: 1.60–2.48), having preterm birth were 1.65 times (95% CI: 1.29–2.10), and having stillbirths were 1.40 times (95% CI: 1.15–1.71) in pregnant women with malaria.

We prove that the local time of random walks conditioned to stay positive converges to the corresponding local time of three-dimensional Bessel processes by proper scaling. Our proof is based on Tanaka’s pathwise construction for conditioned random walks and the derivation of asymptotics for mixed moments of the local time.

Researchers have encountered many issues while studying rare illnesses such as lack of information, limited sample sizes, difficulty in diagnosis, and more. However, perhaps the biggest challenge is to recruit a large enough sample size for clinical studies; at the same time, obtaining chronological data for these patients is even more difficult. This has urged us to implement a decentralized crowdsourcing medical data sharing platform to obtain chronological rare data for certain diseases, providing both patients and other stakeholders an easier and more secure way of trading medical data by utilizing blockchain technology. This facilitates the obtention of the most elusive types of health data by dynamically allocating extra financial incentives depending on data scarcity. We also provide a novel framework for medical data cross-validation where the system checks the volunteer reviewer count. The review score depends on the count, and the more the reviewers, the bigger the final score. We also explain how differential privacy is used to protect the privacy of individual medical data while enabling data monetization.

The use of computer technology to automate the enforcement of law is a promising alternative to simplify bureaucratic procedures. However, careless automation might result in an inflexible and dehumanized law enforcement system driven by algorithms that do not account for the particularities of individuals or minorities. In this article, we argue that hybrid smart contracts deployed to monitor rather than blindly enforce regulations can be used to add flexibility. Enforcement is a suitable alternative only when prevention is strictly necessary; however, we argue that in many situations a corrective approach based on monitoring is more flexible and suitable. To add more flexibility, the hybrid smart contract can be programmed to stop to request the intervention of a human or of a group of them when human judgment is needed.

Antimicrobial resistance (AMR) remains a critical public health problem that pervades hospitals and health systems worldwide. The ongoing AMR crisis is not only concerning for patient care but also healthcare delivery and quality. This article outlines key components of the origins of AMR in the United States and how it presents across the American healthcare system. Numerous factors contributed to the crisis, including agricultural antibiotic use, wasteful prescribing practices in health care, conflicting behaviours among patients and clinicians, patient demand and satisfaction, and payment and reimbursement models that incentivize inappropriate antibiotic use. To combat AMR, clinicians, healthcare professionals, and legislators must continue to promote and implement innovative solutions, including antibiotic stewardship programmes (ASPs), hand hygiene protocols, ample supply of personal protective equipment (PPE), standardized treatment guidelines for antibiotic prescribing, clinician and patient educational programmes, and health policy initiatives. With the rising prevalence of multi-drug resistant bacterial infections, AMR must become a greater priority to policymakers and healthcare stakeholders.

We propose a flexible lattice model to evaluate the fair value of insurance contracts embedding both financial and actuarial risk factors. Flexibility relies on the ability of the model to manage different specifications of the correlated processes governing interest rate, mortality, and fund dynamics, thus allowing the insurer to make the most appropriate choices. The model is also able to handle additional guarantees like a surrender opportunity for which explicit formulae are not available being it similar to an American derivative. The model discretizes mortality and interest rate dynamics through two different binomial lattices and then combines them into a bivariate tree characterized by the presence of four branches for each node. The probability of each branch is defined to replicate the correlation affecting the two processes. The bivariate model is useful to compute the value of survival zero coupon bond. When adding another source of risk, such as the fund dynamics for evaluating fund-linked insurance products, we model it through a bivariate tree that captures the influence of the interest rate on its drift term. Then, the mortality risk is embedded by defining a trivariate tree presenting eight branches emanating from each node with probabilities defined in order to capture the correlations of the processes. Extensive numerical experiments assess the model accuracy by considering some stylized policies, but the model application is not limited to them being it able to manage different contract specifications.

A closed-form solution for zero-coupon bonds is obtained for a version of the discrete-time arbitrage-free Nelson-Siegel model. An estimation procedure relying on a Kalman filter is provided. The model is shown to produce adequate fit when applied to historical Canadian spot rate data and to improve distributional predictive performance over benchmarks. An adaptation of the mixed fund return model from Augustyniak et al. ((2021). ASTIN Bulletin: The Journal of the IAA, 51(1), 131–159.) is also provided to include the discrete-time arbitrage-free Nelson-Siegel model as one of its building blocks.