Search Results (7)

The claims resolution process is a cornerstone of the insurance industry, aiming to fairly and accurately determine the economic losses caused by adverse events. Traditionally, adjusters have relied heavily on expert judgment to perform this task. While this approach is essential, it often suffers from subjectivity, inconsistent criteria, and difficulty integrating complex data sources into objective analyses. In this context, Smart Industry tools—such as Artificial Intelligence (AI), Machine Learning (ML), Computer Vision (CV), and the Internet of Things (IoT)—have demonstrated high potential to automate damage detection and assessment; however, their effective integration into loss determination remains uneven across different productive sectors. This study addresses this problem through two objectives. First, we conducted a systematic literature review following PRISMA guidelines to identify which Smart Industry tools are currently used in the insurance sector for loss determination and to analyze their level of maturity in different productive sectors. We searched the Web of Science and Scopus databases, identifying 253 studies, of which 23 met our inclusion criteria. Second, based on the gaps we identified between the construction sector and more advanced industries such as automotive, we propose a methodological framework based on Building Information Modeling (BIM). Our results show that most solutions focus on the detection and technical classification of damage, especially in the automotive sector, while construction lacks methods to convert these technical findings into operational economic estimates. The proposed framework addresses this gap by standardizing technical and economic data from the underwriting stage, enabling more automated, traceable, and objective loss determination for infrastructure claims. Full article

Background: Genetic data play a crucial role in diagnosing and treating various diseases, reflecting a growing imperative to integrate these data into clinical care. However, significant barriers such as the structure of electronic health records (EHRs), insurance costs for genetic testing, and the interpretability of genetic results impede this integration. Methods: This paper explores solutions to these challenges by combining recent technological advances with informatics and data science, focusing on the diagnostic potential of artificial intelligence (AI) in cancer research. AI has historically been applied in medical research with limited success, but recent developments have led to the emergence of large language models (LLMs). These transformer-based generative AI models, trained on vast datasets, offer significant potential for genetic and genomic analyses. However, their effectiveness is constrained by their training on predominantly human-written text rather than comprehensive, structured genetic datasets. Results: This study reevaluates the capabilities of LLMs, specifically GPT models, in performing supervised prediction tasks using structured gene expression data. By comparing GPT models with traditional machine learning approaches, we assess their effectiveness in predicting cancer subtypes, demonstrating the potential of AI models to analyze real-world genetic data for generating real-world evidence. Full article

Machine learning, a subfield of artificial intelligence, emphasizes the creation of algorithms capable of learning from data and generating predictions. However, in actuarial science, the interpretability of these models often presents challenges, raising concerns about their accuracy and reliability. Explainable artificial intelligence (XAI) has emerged to address these issues by facilitating the development of accurate and comprehensible models. This paper conducts a comparative analysis of various XAI approaches for tackling distinct data-driven insurance problems. The machine learning methods are evaluated based on their accuracy, employing the mean absolute error for regression problems and the accuracy metric for classification problems. Moreover, the interpretability of these methods is assessed through quantitative and qualitative measures of the explanations offered by each explainability technique. The findings reveal that the performance of different XAI methods varies depending on the particular insurance problem at hand. Our research underscores the significance of considering accuracy and interpretability when selecting a machine-learning approach for resolving data-driven insurance challenges. By developing accurate and comprehensible models, we can enhance the transparency and trustworthiness of the predictions generated by these models. Full article

In this paper, we investigated rates of admission to hospitals (or other health facilities) due to respiratory diseases in a United States working population and their dependence on a number of demographic and health insurance-related factors. We employed neural network (NN) modelling methodology, including a combined actuarial neural network (CANN) approach, and model admission numbers by embedding Poisson and negative binomial count regression models. The aim is to explore the gains in predictive power obtained with the use of NN-based models, when compared to commonly used count regression models, in the context of a large real data set in the area of healthcare insurance. We used nagging predictors, averaging over random calibrations of the NN-based models, to provide more accurate predictions based on a single run, and also employed a k-fold validation process to obtain reliable comparisons between different models. Bias regularisation methods were also developed, aiming at addressing bias issues that are common when fitting NN models. The results demonstrate that NN-based models, with a negative binomial distributional assumption, provide improved predictive performance. This can be important in real data applications, where accurate prediction can drive both personalised and policy-level interventions. Full article

Many actuarial science researchers on stochastic modeling and forecasting of systematic mortality risk use Cairns-Blake-Dowd (CBD) Model (2006) due to its ability to consider the cohort effects. A three-factor stochastic mortality model has three parameters that describe the mortality trends over time when dealing with future behaviors. This study aims to predict the trends of the model, $k_t^{\left(2\right)}$ by applying the Recurrent Neural Networks within a Short-Term Long Memory (an artificial LSTM architecture) compared to traditional statistical ARIMA (p,d,q) models. The novel deep learning (machine learning) technique helps integrate the CBD model to enhance its accuracy and predictive capacity for future systematic mortality risk in countries with limited data availability, such as Kenya. The results show that Long Short-Term Memory network architecture had higher levels of precision when predicting the future systematic mortality risks than traditional methods. Ultimately, the results can be implemented by Kenyan insurance firms when modeling and forecasting systematic mortality risk helpful in the pricing of Annuities and Assurances. Full article

The paper describes a new non-iterative linear supervised learning predictor. It is based on the use of Ito decomposition and the neural-like structure of the successive geometric transformations model (SGTM). Ito decomposition (Kolmogorov–Gabor polynomial) is used to extend the inputs of the SGTM neural-like structure. This provides high approximation properties for solving various tasks. The search for the coefficients of this polynomial is carried out using the fast, non-iterative training algorithm of the SGTM linear neural-like structure. The developed method provides high speed and increased generalization properties. The simulation of the developed method’s work for solving the medical insurance costs prediction task showed a significant increase in accuracy compared with existing methods (common SGTM neural-like structure, multilayer perceptron, Support Vector Machine, adaptive boosting, linear regression). Given the above, the developed method can be used to process large amounts of data from a variety of industries (medicine, materials science, economics, etc.) to improve the accuracy and speed of their processing. Full article

Historical maps are unique sources of retrospective geographical information. Recently, several map archives containing map series covering large spatial and temporal extents have been systematically scanned and made available to the public. The geographical information contained in such data archives makes it possible to extend geospatial analysis retrospectively beyond the era of digital cartography. However, given the large data volumes of such archives (e.g., more than 200,000 map sheets in the United States Geological Survey topographic map archive) and the low graphical quality of older, manually-produced map sheets, the process to extract geographical information from these map archives needs to be automated to the highest degree possible. To understand the potential challenges (e.g., salient map characteristics and data quality variations) in automating large-scale information extraction tasks for map archives, it is useful to efficiently assess spatio-temporal coverage, approximate map content, and spatial accuracy of georeferenced map sheets at different map scales. Such preliminary analytical steps are often neglected or ignored in the map processing literature but represent critical phases that lay the foundation for any subsequent computational processes including recognition. Exemplified for the United States Geological Survey topographic map and the Sanborn fire insurance map archives, we demonstrate how such preliminary analyses can be systematically conducted using traditional analytical and cartographic techniques, as well as visual-analytical data mining tools originating from machine learning and data science. Full article