Benefit from Exclusive Early Bird Rates

Time-Limited Discounts Available

We’re excited to share the early bird deadlines for our upcoming CPD events over the next four weeks. Our early bird offers provide you with the ideal opportunity to secure your spot at a reduced rate, while planning your professional development well in advance.

Make sure to check the deadlines below – these special rates are only available for a limited time!

Our aim is to provide pension actuaries and other interested experts with an overview of topics and methods in relation to discussion of intergenerational fairness. 

The concept of equity requires that similar careers should result in similar benefits. Or insured persons should get their (socially) agreed level of pensions over long periods under the same conditions. On one end of the spectrum an argument is that the value of the benefits should be equal to the contributions. On the other end, socially agreed needs also should be financed from the fund. These approaches lead to different conclusions from actuarial fairness to social fairness. Both worth valuing their pros and cons. 

First of all, this definition focuses on adequacy of the pensions. It is best perceptible from individual perspective. However, the second part of the definition is setting long term feasibility actuarial-academy.com conditions which we usually call financial sustainability, and it should be met at population and economy level. 

This situation might be familiar to pension experts. The adequacy and sustainability objectives are contradicting by definition, and we have to balance between them. Pension reforms leading to restrictions start from financing issues and reversals or adequacy measures introduced only after crises or from political reasons. Their cycle is different. 

Intergenerational fairness might be discussed during policy dialogue. Most measures focus on one or two aspects of equity or feasibility. In intergenerational context balancing between adequacy and sustainability may be put into the context of intergenerational risk sharing.

The early-bird discount is valid for bookings made until today!

In this web session, we will introduce participants to market-linked insurance products and provide an overview of the developing product landscape across different European countries. 

We will focus on an analysis of some major product categories including hybrids, index-linked policies, private market products and market-linked annuities. How can such products be constructed efficiently? What are the current challenges and how can they be addressed? How should these products be positioned to make them attractive to both insurers and policyholders? 

The web session concludes with an outlook of where the market will be headed and how insurers need to further develop their product offering.

Early-bird discount is available for bookings made by tomorrow, 11 September 2025!

This web session focuses on the aggregation of individual risks to the overall level of an insurance company. To achieve this, we apply both deterministic and stochastic copula-based approaches, along with key risk measures such as Value-at-Risk (VaR) and Expected Shortfall (ES). The outcome of this process is the capital requirement, which must be covered by the company’s own funds—a limited and costly resource that necessitates careful management. 

Against this backdrop, we explore risk steering methods that support economically sound decision-making, addressing key questions such as: 

• How can we impose effective risk limits for business segments? 
• How can we identify value-enhancing and value-reducing business segments in the context of the firm’s overall risk profile? 
• How can we make informed decisions on risk mitigation tools? 
• How can we incorporate the cost of capital into insurance pricing? 

A fundamental concept underlying all these questions is capital allocation, and specifically the gradient (Euler) capital allocation principle. The principle is directly linked to “marginal capital requirements” and is compatible with the performance measures mentioned above.

Early-bird discount is available for bookings made by 15 September 2025.

In general, Machine Learning (ML) is the study of algorithms that improve through experience. These algorithms or models can make systematic, repeatable, validated decisions based on historical data. ML has come a long way in recent years, which is reflected in the methods available for time series forecasting (they are also important for assessing parameters for different kinds of liability provisions). 

Therefore, this type of analysis can help actuaries and members of pension fund boards of trustees to accurately assess different kinds of pension fund parameters for assets and liabilities and to prepare any kind of forecasts. Visualizing the evolution of pension fund parameters and forecasting them will help the board of trustees explain how to adjust them in the actuarial provision or what to expect in their future evolution. 

For this workshop, several examples for analyzing and providing such assumptions will be prepared and explained. Many useful visualization techniques will be presented with practical examples (via Python).

Early-bird discount is available for bookings made by 18 September 2025.

This web session will demonstrate how class imbalance in training data can be addressed with Python using a Life Insurance Lapse Prediction Case Study. 

Topics Covered:

• What class imbalance is, why it matters, and how it affects classification model performance (the ‘Accuracy Paradox’).
• Step-by-step demonstrations using Python libraries (pandas, scikit-learn, imbalancedlearn) for data preparation, rebalancing techniques, ML model development and model evaluation.
• A range of Rebalancing Techniques, including:
  • Oversampling (e.g. SMOTE)
  • Undersampling
  • Hybrid resampling
  • Cost-sensitive learning
• Application of Rebalancing Techniques across a range of ML classification models, including:
  • Naïve Bayes
  • Logistic Regression 
  • Decision Trees 
  • Random Forests
  • Gradient Boosting
  • Neural Networks
• A structured evaluation of rebalancing techniques, comparing their impact on model performance using metrics such as:
  • Precision
  • Recall
  • F1-score
  • ROC-AUC
  • Lift

Early-bird discount is available for bookings made by 22 September 2025.

In this web session, we will dive into a specific algorithm that uses GLM regularisation in an easy yet powerful way. In this algorithm, we first postulate a complex model structure that represents all potential linear and non-linear patterns for the main effects (and possibly interaction effects) in the data. We then introduce a global penalty term which we apply to reduce the model to only the statistically significant effects at which model accuracy on unseen data performs best. 

From a theoretical point of view, we first substantially widen the GLM modelling space to reduce (or even eliminate) any model bias. This implicitly introduces a higher model variance which we counteract by continuously increasing the penalty term. Since the reduction in variance comes again at the cost of allowing some bias, the algorithm effectively allows us to control for the bias-variance trade-off in the GLM modelling space, and we aim for the GLM that simultaneously minimises the prediction error. 

Applying the algorithm results in a simple but generally more accurate model in which we adaptively learned the relevant effects in a data-driven, simultaneous and automated way. A actuarial-academy.com key feature is that we can account for all common types of explanatory variables (continuous, ordinal, nominal) both at the same time and in the same way. The desired balance between model simplicity and forecast accuracy can be set by means of a single control parameter. The final model has a proven GLM structure that is still explainable and allows seamless integration into existing pricing workflows. 

During the web session, we will first explore the theoretical foundations of both the biasvariance trade-off in predictive modelling and general GLM regularisation. We will then study the explicit design of the algorithm. The remainder will be hands-on as we provide extensive code that implements the algorithm in the statistical programming language R. We will discuss and run the code using a realistic case study in actuarial claims frequency modelling. You will learn how to use the programme and apply the algorithm to non-life claims data for pricing. Further focus will be on the visualisation of the results, especially on the insights gained from the learned meta-results of the algorithm, e.g., the implicit way how we selected, prioritised and pre-processed variables.

Early-bird discount is available for bookings made by 29 September 2025.

The online seminar will explore selected AI applications relevant to the actuarial profession, focusing not only on potential use cases but also on how actuaries can responsibly design, validate, and monitor AI models. Participants will learn how to build compelling business cases for AI initiatives and understand where actuarial expertise offers unique value in ensuring model quality, transparency, and alignment with ethical and regulatory standards. By combining technical actuarial skills with a deep understanding of AI methodologies, actuaries can play a key role in shaping and governing AI solutions, thereby creating significant value in a rapidly evolving landscape. 

Finally, the session will explore how to move from a general definition of harm to effectively detecting and managing it. It will incorporate both legal and quantitative perspectives—an approach especially valuable when addressing significant harm in AI systems. This will help bridge the gap between legal definitions and statistical evidence.

All in all, the web session will provide a better understanding of what it takes to implement AI models in practice, covering topics relating to definitions of AI and models, risk management practices, infrastructure set-ups and implementation standards. 

The participants will build a tool-kit of knowledge that will help them address an array of business cases in practice. The session will also help in increasing the know-how of implementing AI models, their impact within the organisations, given their challenges around explainability to the stakeholders, potential harm and relevance as a whole.

Early-bird discount is available for bookings made by 1 October 2025.

This session will notably have two main angles. Firstly, it will raise the question of data, their quality, and the necessary reliance on expert judgment, crucial for risks where experience is limited. Bayesian analysis notably allows for this integration, but does not exempt from a critical examination of the quality of expert data, and we will thus present some methods to attempt to evaluate it. 

Secondly, we will examine the shift from a "historical data" approach to a "scenario-based" approach. Because while the notion of scenario allows for anticipating situations never encountered before, their design must adhere to scientific standards to avoid being purely speculative. 

A simplified illustration of these issues will be provided during the training. An R notebook will allow participants to follow and adapt the implementation without needing an in-depth knowledge of the software.

Early-bird discount is available for bookings made by 2 October 2025.

This web session presents the general structure and components that projection models must have for the valuation of life insurance liabilities including their embedded options and guarantees within an economic / market-consistent balance sheet (MCBS). It explains the need for a simplified modelling of the life insurance contracts / portfolio in a stochastic context and introduces three conceptually different approaches currently observable in the market. The online training compares their key underlying ideas and introduces - based on concrete examples - the mathematical / actuarial methodologies used. This introduction also includes a qualitative discussion of their individual strengths & challenges with regards to both external financial reporting and internal business steering including aspects like movement analyses, planning and performance management. Concerning the application of the comparably littleknown Liability-2-Step approach, the session will present the operational experience of an Austrian insurance company.

Early-bird discount is available for bookings made by 8 October 2025.