Large datasets, combined with modeling techniques, provide a quantitative way to estimate when known archaeological sites will be impacted by climatological changes. With over 4,000 archaeological sites recorded on the coast of Georgia, USA, the state provides an ideal opportunity to compare methods. Here, we compare the popular passive “bathtub” modeling with the dynamic Sea Level Affecting Marshes Model (SLAMM) combined with the Marshes Equilibrium Model (MEM). The goal of this effort is to evaluate prior modeling and test the benefits of more detailed ecological modeling in assessing site loss. Our findings indicate that although rough counts of archaeological sites destroyed by sea-level rise (SLR) are similar in all approaches, using the latter two methods provides critical information needed in prioritizing site studies and documentation before irrevocable damages occur. Our results indicate that within the next 80 years, approximately 40% of Georgia's coastal sites will undergo a loss of archaeological context due to wetlands shifting from dry ecological zones to transitional marshlands or submerged estuaries and swamps.

In this paper, we construct interpretable zero-inflated neural network models for modeling hospital admission counts related to respiratory diseases among a health-insured population and their dependants in the United States. In particular, we exemplify our approach by considering the zero-inflated Poisson neural network (ZIPNN), and we follow the combined actuarial neural network (CANN) approach for developing zero-inflated combined actuarial neural network (ZIPCANN) models for modeling admission rates, which can accommodate the excess zero nature of admission counts data. Furthermore, we adopt the LocalGLMnet approach (Richman & Wüthrich (2023). Scandinavian Actuarial Journal, 2023(1), 71–95.) for interpreting the ZIPNN model results. This facilitates the analysis of the impact of a number of socio-demographic factors on the admission rates related to respiratory disease while benefiting from an improved predictive performance. The real-life utility of the methodologies developed as part of this work lies in the fact that they facilitate accurate rate setting, in addition to offering the potential to inform health interventions.

A machine learning approach to zero-inflated Poisson (ZIP) regression is introduced to address common difficulty arising from imbalanced financial data. The suggested ZIP can be interpreted as an adaptive weight adjustment procedure that removes the need for post-modeling re-calibration and results in a substantial enhancement of predictive accuracy. Notwithstanding the increased complexity due to the expanded parameter set, we utilize a cyclic coordinate descent optimization to implement the ZIP regression, with adjustments made to address saddle points. We also study how various approaches alleviate the potential drawbacks of incomplete exposures in insurance applications. The procedure is tested on real-life data. We demonstrate a significant improvement in performance relative to other popular alternatives, which justifies our modeling techniques.

Transition cow diseases can negatively impact animal welfare and reduce dairy herd profitability. Transition cow disease incidence has remained relatively stable over time despite monitoring and management efforts aimed to reduce the risk of developing diseases. Dairy cattle disease risk is monitored by assessing multiple factors, including certain biomarker test results, health records, feed intake, body condition score, and milk production. However, these factors, which are used to make herd management decisions, are often reviewed separately without considering the correlation between them. In addition, the biomarkers that are currently used for monitoring may not be representative of the complex physiological changes that occur during the transition period. Predictive modeling, which uses data to predict future or current outcomes, is a method that can be used to combine the most predictive variables and their interactions efficiently. The use of an effective predictive model with relevant predictors for transition cow diseases will result in better targeted interventions, and therefore lower disease incidence. This review will discuss predictive modeling methods and candidate variables in the context of transition cow diseases. The next step is to investigate novel biomarkers and statistical methods that are best suited for the prediction of transition cow diseases.

While Bayesian methods have attracted considerable interest in actuarial science, they are yet to be embraced in large-scaled insurance predictive modeling applications, due to inefficiencies of Bayesian estimation procedures. The paper presents an efficient method that parallelizes Bayesian computation using distributed computing on Apache Spark across a cluster of computers. The distributed algorithm dramatically boosts the speed of Bayesian computation and expands the scope of applicability of Bayesian methods in insurance modeling. The empirical analysis applies a Bayesian hierarchical Tweedie model to a big data of 13 million insurance claim records. The distributed algorithm achieves as much as 65 times performance gain over the non-parallel method in this application. The analysis demonstrates that Bayesian methods can be of great value to large-scaled insurance predictive modeling.

Siamweed is an asteraceous shrub native to the Neotropics that ranks among the world's most widespread and troublesome invasive species. It was introduced in several regions of Africa, Southeast Asia, and the Pacific Islands, where it severely infests natural habitats and plantation crops. Although extensive data document the weed's abundance and distribution throughout the invaded continents, the details of its current range are not fully known, especially within its native region. In this study, we used point-occurrence data and digital maps summarizing relevant environmental parameters to generate predictions for the species' geographic distributional potential—specifically, we modeled the native range of siamweed in the Neotropics using the genetic algorithm for rule-set prediction, an evolutionary computing approach. The native range occurrence data set contained 239 published and herbarium records. Models were trained on a random subset of half the points and tested using the other half. The rule sets of the native-range models were projected onto the invaded continents to predict the weed's potential for invasion, blind to its known occurrences in such regions. Native-range models predicted a wide potential distribution of siamweed throughout tropical America, from southern United States to northern Argentina and southern Brazil. The weed's occurrence has been confirmed on the northern Pacific coast, in southeast Brazil, and in other South American areas, where it was supposed to be absent. Independent model projections to Africa, Asia, and Oceania are supported by known occurrence records. Four regions are predicted to be susceptible to siamweed spread: (1) Central Africa, currently being invaded from Western Africa; (2) Infestations spreading northward from South Africa, which have already reached Swaziland and Mozambique and may extend to East Africa and Madagascar; and (3) northern New Zealand and (4) Australia, which are at risk from uncontrolled infestations on several western Pacific islands.