Events Library

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.

Motivated by insurance applications, we propose a new approach for the validation of real-world economic scenarios. This approach is based on the statistical test developed by Chevyrev and Oberhauser (2022) and relies on the notions of signature and maximum mean distance. This test allows to check whether two samples of stochastic processes paths come from the same distribution. Our contribution is to apply this test to a variety of stochastic processes exhibiting different pathwise properties (Hölder regularity, autocorrelation, and regime switches) and which are relevant for the modelling of stock prices and stock volatility as well as of inflation in view of actuarial applications.


Speaker: Hervé Andrès
Session Moderator: Łukasz Delong

Classical public pension schemes combine usually PAYG mechanism and Defined Benefit architecture. Aging threatens clearly this kind of structure and motivates the development of hybrid solutions mixing on one side PAYG and Fully funding and on the other side DB and DC (Defined Contribution). The purpose of this presentation is to develop some of these hybrid plans and introduce actuarial tools in order to implement inter-generational and intra generational fairness and sustainability in these public programs.

Speaker: Pierre Devolder
Session Moderator: Jennifer Alonso Garcia

Unlock how Artificial Intelligence is reshaping pensions and social security work. Join us for an insightful session featuring leading actuarial AI expert Ronald Richman, who will share practical applications of AI in longevity modelling, experience analysis, and actuarial workflow automation. This webinar will highlight real-world use insights, emerging opportunities, and what actuaries doing work in pensions and social security need to know to stay ahead in an AI-driven future.

Be sure to join us for what promises to be an informative and engaging discussion.

Speaker: Ronald Richman
Moderator: John Anderson

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.

Speakers: Ben Zickel and Yulia Nechay Moderator: Joana Raposo