Events Library

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

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

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

This webinar will explore new practice areas for actuaries in the context of climate change. It aims to provide a broad overview of areas where actuaries can apply their skills and expertise to assist with climate change risks and opportunities, and thereby support the transition to a low-carbon economy, whilst also helping to manage the risks associated with such a transition (including not transitioning). The session will draw on current literature, case studies, industry practice and stakeholder interviews. The session covers current and potential areas of practice relating to climate risk management, risk and emissions modelling, insurance, finance and investments, strategy setting, governance, reporting and regulation, government, and other areas of corporate support. The webinar also addresses, at a high level, areas in which actuaries will be required to enhance their technical climate knowledge to enable actuarial practice.


Speakers: Atiyya Ally and Kelvin Massingham
Session Moderator: Georgios Symeonidis

This talk presents a method for constructing insurable risk portfolios using a data-driven approach to devise risk retention programs that safeguard firms from a multitude of risks. Because firms face many risks, including fire damage to their buildings, liability from management misconduct, and external threats like cyber attacks, this talk treats these potential liabilities as a "portfolio." Drawing inspiration from Markowitz portfolio theory, it leverages techniques from probability, statistics, and optimization to build algorithms that construct optimal risk insurable portfolios under budget constraints. Through engaging case studies, viewers will learn how to build optimal insurable risk portfolios.
The talk illustrates a frontier that depicts the trade-off between the uncertainty of a portfolio and the cost of risk transfer. This visual representation, mirroring familiar Markowitz investment tools, enables informed decision-making and easy adoption by risk advisors. The talk outlines the mathematical groundwork for constructing optimal insurable risk portfolios in an effective and aesthetically pleasing manner.

Speaker: Edward (Jed) Frees
Moderator: Brian Fannin