Long Term Care Case Studies

Introducing AI in Pension Planning: A Comparative Study of Deep Learning and Fuzzy Mamdani Inference Systems for Estimating Replacement Rates
Funded pensions have gained considerable attention as a strategy for securing supplementary income in retirement. This presentation aims to provide a comparative analysis of two methods for estimating the replacement rate: a deep learning model and a Fuzzy Mamdani Inference System (FIS). Since AI has gained considerable ground in the actuarial universe, an obvious step would be to investigate AI techniques, such as neural networks and fuzzy logic, in the realm of pension planning. Initial results indicate that these methods provide accurate estimations, warranting further analysis.
Speaker: Georgios Symeonidis
Moderator: Jennifer Alonso Garcia

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.
Speaker: Simone Farinelli
Session Moderator: Brian Fannin

This session on Parametric Insurance is focused on highlighting the key aspects, including the benefits of rapid, transparent payouts versus the challenge of basis risk. The presentation will detail the pricing methodologies, explore key selling points and how parametric insurance can be strategically used in a risk management framework.

Practical use cases will be presented with a specific focus in developing countries. These examples will demonstrate how parametric solutions could effectively mitigate the protection gap, offering vital financial resilience to smallholder farmers and governments against natural disasters.

Amidst the recent flurry of activity around AI, actuaries will be in good company as they consider how to extract the benefits of AI advancements, while avoiding their downside risks. Actuaries that develop and deploy AI systems must consider how to deliver the potential gains in accuracy and speed, while avoiding risks like biased decision-making. At the same time, they must carefully consider how AI systems will integrate into employee workflows. Responsible AI and human-centric AI offer valuable guidance to address these issues and can assist actuaries in realising the benefits of AI.


Speaker: Maura Feddersen
Moderator: Ernst Visser

This webinar explores the evolving cyber threat landscape, and the steps organizations can take to build resilience.

Drawing on insights from simulated sophisticated cyberattacks, we will share key lessons learned, highlight the most common pitfalls that leave businesses vulnerable, and provide actionable recommendations to reduce risk.

Framed in the context of current and emerging threats including ransomware, AI-driven attacks, and supply-chain vulnerabilities, this session aims to equip decision-makers with clear strategies to strengthen defenses, improve response readiness, and ensure business continuity in the face of an increasingly hostile digital environment.

The additive reserving model assumes the existence of volume measures such that the corresponding expected loss ratios are identical for all accident years. While classical literature assumes these volumes are known, in practice, accurate volume measures are often unavailable. The issue of uncertain volume measures in the additive model was addressed in a generalization of the loss ratio method published in 2018. The derivation is rather complex and the method computationally intensive, especially for large loss development triangles.
We present an alternative approach that leverages the well-established EM algorithm, significantly reducing computational requirements.


Speaker: Ulrich Riegel
Session moderator: Brian Fannin