Category: ASTIN / NON-LIFE - actuview - the international streaming platform for actuaries

Assessing Driving Risk Through Unsupervised Detection of Anomalies in Telematics Time Series Data

Thu, 23 Apr 2026 14:02:44 +0000

With the advancement of technology, insurance companies are increasingly adopting usage-based insurance (UBI) supported by vehicle telematics. Vehicle telematics refers to data collected from in-vehicle sensors or smartphone applications during driving, such as speed, acceleration, braking, and steering. It provides a rich, high-frequency record of how a vehicle is driven, offering insights into driving habits, behaviour, safety, and potential risk. However, many current approaches rely on aggregated metrics and do not fully capture the detailed time-series patterns in telematics data. This presentation introduces a flexible framework based on a continuous-time hidden Markov model (CTHMM) to analyze trip-level telematics data directly. Our approach avoids predefined thresholds for harsh events or assumptions about accident probabilities, and uses only telematics data, requiring no traditional demographic covariates. Using an unsupervised anomaly detection technique, we identify deviations from normal driving patterns linked to higher accident risk. The framework is tested on both controlled and real-world datasets, and the results reveal clear behavioural differences between drivers with and without claims, offering practical insights for insurance, accident analysis, and prevention.

From Disaster Relief to Disaster Insurance: Premium Subsidies and the Development of Private Insurance Markets

Wed, 01 Apr 2026 12:48:52 +0000

Presentation from the DGVFM CPD Day in March 2026 on „Accumulation Risks and Risk Sharing in NatCat and Cyber“.

Evolving Climate Risks: Extreme Rainfall and Hail in Perspective

Wed, 01 Apr 2026 12:32:31 +0000

Presentation from the DGVFM CPD Day in March 2026 on „Accumulation Risks and Risk Sharing in NatCat and Cyber“.

Critical Point – A Milliman Podcast: So You Want To Be a P&C Actuary?

Thu, 26 Mar 2026 12:31:41 +0000

From climate change to self-driving cars, hear the range of projects two actuarial consultants are working on, the soft skills that have helped their careers, and more advice for students and non-actuaries who want to enter the profession.

Pools Development in APAC & Exploring Smart Driving Insurance Solutions for NEVs: OEM Cases and Insurance Perspectives

Wed, 25 Mar 2026 14:47:42 +0000

Pools Development in APAC
Natural catastrophes are an increasing concern across the Asia-Pacific (APAC) region, where rapid urbanisation, economic growth, and rising climate-related risks are amplifying exposure to natural hazards. At the same time, insurance penetration across many parts of the region remains relatively low, resulting in a significant protection gap between economic losses and insured losses.
This session will explore emerging risks and opportunities in the APAC non-life insurance market, with a particular focus on the role of catastrophe insurance pools in addressing protection gaps in vulnerable regions. The discussion will begin with an overview of existing property natural hazard pools across APAC, highlighting how these public–private initiatives have developed over time to improve access to catastrophe protection and enhance financial resilience.
We will examine how these pools differ in structure, governance, and coverage, and how newer pools are expanding beyond traditional earthquake coverage to include a wider range of natural hazards such as floods, cyclones, and other climate-related risks. The session will also discuss the broader factors driving the growth of such initiatives, including increasing catastrophe losses, affordability challenges in high-risk areas, and greater public-sector participation in disaster risk financing.
The presentation will also explore the scale of the insurance protection gap across APAC, including insights by country and catastrophe type. By examining patterns of economic losses and insurance coverage across the region, the session will highlight where protection gaps are most pronounced and what this means for insurers, governments, and communities.
Finally, the session will consider the potential role of catastrophe pools in shaping the future of disaster risk financing in the region. While pools can help address immediate coverage challenges, they are not a complete solution.

Exploring Smart Driving Insurance Solutions for NEVs: OEM Cases and Insurance Perspectives

As New Energy Vehicles (NEVs) evolve toward high-level automation, the insurance industry faces a profound risk reconstruction

This session, presented by Leona Li, a UK Chartered Actuary and founder of NexVantage Insurance & Advisory Consulting (Singapore), delves into how the shift from "human-led" to "system-led" driving is transforming the auto insurance landscape.

Key Topics and Insights:

Technology Evolution & Market Trends:The session begins with an analysis of the six levels of autonomous driving (L0-L5) and the core transition of the driving subject from humans to Automated Driving Systems (ADS) . We explore the "cost-performancesafety" trade-offs between Pure Vision and Multi-sensor Fusion technology paths, as well as the software revolution brought by End-to-End (E2E) architectures in systems like Tesla FSD v13 and Huawei ADS 3.0. Currently, the penetration rate of L2+ NEVs in China has reached 67.8%, supported by national policies for "Vehicle-Road-Cloud Integration" .
Risk Reconstruction:The advent of L3 autonomy marks a critical "liability transfer" point. The session identifies a four-dimensional risk matrix—Functional Safety, Safety of the Intended Functionality (SOTIF), Cybersecurity, and Data Security—that traditional insurance often fails to cover . This shift disrupts the three pillars of actuarial science: frequency, severity, and liability .
Reinsurance & Ecosystem Value: The speaker introduces a specialized Three-tier Progressive Risk Model (Mechanism-Dynamic-Insurance) designed for risk modeling. Furthermore, the session discusses how insurance collaboration can solve core pain points in the NEV market, such as overseas export insurance solutions and residual value protection for used NEVs.

Decoding the Next Era of Risks: Social Inflation, Climate Change and more

Wed, 25 Mar 2026 14:38:09 +0000

The General Insurance landscape in the APAC region is evolving rapidly, driven by complex, non-traditional risks that require modern solutions. This session is designed for actuaries across all functions - pricing, reserving, and capital modeling - who are seeking strategic, data-driven approaches to managing this new era of uncertainty.

Introduction and CAS Overview

An AI Approach to Quantifying Social Inflation

This session provides an overview of how an AI framework can be adopted to help insurers forecast jury verdicts and court case durations in a more granular manner. An overview of how the framework benefits multiple stakeholders (both actuarial and non-actuarial) within a company will also be discussed.

Learning Objectives:

Identify unstructured data sources pertinent to jury verdict modelling.
Assess their employer's readiness to implement AI driven transformation projects.
Understand the benefits and limits of generative AI.

The Dos and Don’ts of Climate Data and Catastrophe Modelling

This presentation will delve into what we do and don't know about using climate data from a climate science perspective, including how related intelligence has been integrated into cat models, and how the cat models are subsequently being used to answer regulatory requirements.

Learning Objectives:

Understand how catastrohpe models integrate climate change into model output
Understand what the current understanding of climate change is by peril and which perils have high certainty vs low certainty
Understand the potential magnitudes of climate change by peril and its effect on cat model output

Explainable AI for Claims Reserving: Bridging Actuarial Practice and Machine Learning

Thu, 05 Mar 2026 13:45:23 +0000

This session brings together actuarial and machine learning perspectives to explore how AI can support reserving practices.The actuarial perspective will cover the practical limitations of current reserving workflows, where judgment enters traditional methods and why consistency is difficult, and what actuaries need from AI, including transparency, validation, and governance. It will also include a case study comparing traditional results with AI-supported modeling and how ML results can serve as a second-opinion framework.The machine learning perspective will cover the Bayesian ML framework, including its architecture, model selection based on predictive power and cross-validation, and how explainability is built into the model. It will also discuss why full distributions matter more than point estimates and share technical lessons from applying ML to insurance triangles.

A data science approach to climate change risk assessment applied to pluvial flood occurrences for the United States and Canada

Thu, 05 Mar 2026 12:50:35 +0000

There is mounting pressure on (re)insurers to quantify the impacts of climate change, particularly on the frequency and severity of claims from weather events like flooding. This is challenging, as it requires modeling at portfolio scale with enough spatial detail to capture local climate effects.In this webinar, we present a data science approach to assessing pluvial flood risk for insurance portfolios across Canada and the United States. The flood occurrence model quantifies financial impacts of short-term precipitation dynamics under current and future climate conditions using statistical methods, machine learning, and climate model data. It is designed for applications that do not require street-level precision, such as scenario or trend analyses.Our analyses show that climate change and urbanization will generally increase losses across Canada and the United States, though impacts vary across regions. Portfolio applications highlight the importance for (re)insurers of distinguishing between changes in hazard and exposure, as exposure may amplify or reduce the effects of climate change on losses. Read the paper here: DOI: https://doi.org/10.1017/asb.2024.19

Impact de la conjoncture économique sur l'activité d'un assureur-crédit

Wed, 25 Feb 2026 05:30:49 +0000

L'environnement économique actuel, marqué par une forte inflation, des taux d’intérêts qui, après avoir été très bas pendant plusieurs années, ont atteint un niveau plus vu depuis plus de 10 ans, et des conflits géopolitiques, ainsi que le rattrapage du « retard de défaillances » observé pendant la période Covid, met aujourd'hui à l’épreuve les assureurs-crédit. Les méthodes actuarielles traditionnellement utilisées pour prédire la survenance des défauts se basent principalement sur des scores affectés aux entreprises, censés refléter la solidité financière de celles-ci. Cependant, ces modèles peinent à intégrer en temps réel les évolutions de l’environnement économique. Dans ce mémoire, nous proposons une modélisation de la fréquence des défauts par secteur d’activité en utilisant les processus de Hawkes, permettant de modéliser des effets de contagion tant intra-sectoriel qu’inter-sectoriels. Après une présentation de l’assurance-crédit et de ses spécificités, nos travaux se concentreront sur la capacité des processus de Hawkes à modéliser la structure de dépendance des défaillances entre secteurs d’activité. Nous développerons ensuite un modèle utilisant ces processus pour modéliser les pertes attendues d'un assureur-crédit fictif. Enfin, à l’aide du modèle développé, nous étudierons l’impact de la conjoncture économique sur les pertes de l’assureur en fonction de la répartition de son activité dans les différents secteurs via divers scénarios économiques. Une attention particulière sera portée sur la capacité du modèle à évaluer l'ampleur de l'effet de rattrapage de la crise Covid sur le nombre de défaillances attendues d'ici la fin de l'année. Les résultats obtenus permettront de mettre en évidence l’intérêt de la prise en compte des effets de contagion sectoriels dans un cadre de gestion des risques.

Insuring The Uninsurable - Enabling Regulations For Pooling Arrangements

Thu, 19 Feb 2026 08:59:27 +0000

...

Balancing Pricing Sophistication with Simplicity

Thu, 19 Feb 2026 08:50:08 +0000

...

Premium Risk, Standard Error? Challenging the Fit Of Standard

Thu, 19 Feb 2026 08:21:00 +0000

...

Actuarial Valuation of Living Annuities Related to Maintenance and Accrual in Divorce and Deceased Estate Contexts

Tue, 17 Feb 2026 11:51:43 +0000

...

How AV’S are Revving up Changes in SA

Fri, 13 Feb 2026 09:33:25 +0000

...

The Stochastic Model Underlying Sam’s Non-Life Underwriting-Risk Module

Fri, 13 Feb 2026 08:42:33 +0000

...

YAWC 2026 Eastern Semifinals

Thu, 12 Feb 2026 12:33:57 +0000

Watch this YAWC 2026 Eastern Semifinals and find out who will move to the finals taking place in Tokyo in November.

YAWC 2026 Western Hemisphere Semifinals

Thu, 12 Feb 2026 12:02:53 +0000

Watch the YAWC Western Hemisphere Semifinals and find out who will move on to the final round taking place in Tokyo in November.

Enfoques Prácticos para la Revisión y Estimación de Reservas

Thu, 05 Feb 2026 10:14:46 +0000

Revisaremos las mejores prácticas para estimar Siniestros no Pagados y establecer reservas en una aseguradora de daños. Hablaremos también de pruebas de razonabilidad de datos, identificación rápida de ramos que requieren análisis más profundos y métodos para establecer reservas entre estudios actuariales.

Driving Wellness: The Next Big Thing for Motor

Fri, 09 Jan 2026 13:54:26 +0000

Discover how “Driving Wellness” programs can transform motor insurance by reducing accidents and improving driver behavior. This session explores the role of telematics, gamification, and behavioral incentives in creating safer roads and delivering immediate impact. Learn from case studies, understand the keys to success—controllable behaviors, engagement, and scalable rewards—and see how insurers can design programs that balance economics, customer experience, and regulatory compliance.

Building Sustainable Value in General Insurance: A Strategic Approach

Fri, 09 Jan 2026 13:40:59 +0000

Discover strategic approaches to building sustainable value in general insurance. This session examines the importance of Return on Equity (ROE), the impact of excess capital, and how underwriting performance and portfolio mix influence profitability. Learn from case studies on optimizing lines of business, managing capital efficiency, and identifying value-destroying segments. Gain insights into how insurers can balance growth, risk, and shareholder expectations in a competitive market.

Hodge Conjecture Millennium Problem Solved?

Thu, 11 Dec 2025 08:45:27 +0000

In the twentieth century, mathematicians developed powerful methods to study the shapes of complex objects by approximating them with simple geometric building blocks of increasing dimension. These techniques proved so useful that they were widely generalized, producing tools that helped classify many mathematical objects—though the geometric origins became obscured, and some added pieces lost direct geometric meaning.The Hodge Conjecture claims that for certain well-behaved spaces called projective manifolds (smooth projective algebraic varieties), the pieces known as Hodge cycles are actually rational linear combinations of geometric pieces called algebraic cycles.Although the topic seems far from actuarial science, applications may arise through discrete Hodge theory on graphs and simplicial complexes, which turns these geometric ideas into computable linear-algebraic tools.

Combining GLMs with GBMs for the Best of Your Pricing Models

Tue, 02 Dec 2025 17:07:57 +0000

In the ever-evolving landscape of P&C insurance pricing, actuaries are increasingly challenged to strike a balance between model transparency and predictive accuracy. This presentation explores how two leading methodologies - Generalised Linear Models (GLMs) and Gradient Boosting Machines (GBMs) - can be leveraged together to achieve just that.

We begin with a brief overview of the P&C pricing process, setting the stage for a deeper dive into GLMs & GBMs: their theoretical foundations, strengths, limitations, and practical applications in pricing. The core of the session focuses on hybrid modelling strategies that combine the stability and interpretability of GLMs with the accuracy of GBMs. Attendees will be introduced to several techniques for integrating these models, along with real-world examples and considerations for implementation.

If you're a pricing professional seeking a trade-off between model performance and interpretable results, this session offers a forward-thinking look at how the future of pricing lies in combining the best of both worlds.

Vorstellung Ergebnisbericht stochastische Einzelschadenreservierung

Mon, 24 Nov 2025 10:32:23 +0000

In der Juni-Ausgabe 2022 des Aktuar stellten Dirk Skowasch und Torsten Grabarz ihre Ideen zu einer stochastischen Einzelschadenreservierung für große Personenschäden vor. Aufbauend darauf gründete die AG Schadenreservierung eine Unterarbeitsgruppe, um die neue Methode anhand verschiedener Schadenbestände zu erproben und ihre Praxistauglichkeit zu bewerten. Die wichtigsten Erkenntnisse aus dem 2025 veröffentlichten Ergebnisbericht werden in diesem Vortrag vorgestellt.

Vorstellung Ergebnisbericht „Auswirkung von extremen NatCat-Ereignissen auf die Reservierung“

Mon, 24 Nov 2025 10:27:53 +0000

Der Ergebnisbericht „Auswirkung von extremen NatCat-Ereignissen auf die Reservierung“ behandelt Fragestellungen zum Umgang mit und zur Bewertung von Naturkatastrophenereignissen im Rahmen der Reservierung und betrifft Aktuarinnen und Aktuare, die im Rahmen der Abschlusserstellung, Validierung, Prüfung oder in anderer Rolle mit der Bewertung von Schadenrückstellungen befasst sind. Der Vortrag stellt die wichtigsten Ergebnisse des Berichts dar.

Advancing Actuarial Science: Leveraging Synthetic Data for Privacy-Preserving Modeling

Mon, 24 Nov 2025 10:22:39 +0000

The actuarial profession increasingly relies on detailed data for risk assessment and decision-making, yet balancing data utility with privacy remains a key challenge, particularly under the GDPR. Traditional anonymization methods often degrade dataset quality, hindering actuarial modeling. We propose a novel synthetic data approach using kernel density estimation to generate datasets that preserve the multivariate statistical properties of original actuarial data. We discuss use cases for synthetic data in actuarial settings and demonstrate the fidelity, as well as the privacy, of the data generated. Our approach can enable actuaries to leverage realistic datasets without compromising privacy, and conduct collaborative research while maintaining regulatory compliance.