As 2026 comes to an end, the European Actuarial Academy presents the final CPD opportunities of the year.
The November and December programme covers a wide range of topics that are relevant to current actuarial work. The upcoming sessions address pension risk, generative AI, health insurance, open-source tools, life insurance modelling, machine learning and mortality analysis. From practical sessions on R and Python to advanced topics such as stochastic projection models, non-life pricing and experience mortality tables, the programme offers several opportunities to deepen specialist knowledge before the end of the year. You can find all upcoming events here.
At a glance
November 2026
- 5–6 Nov – The ORA under IORP II: From EU Landscape to Board Conclusions
- 10 Nov – Generative AI for Synthetic Actuarial Data
- 13 Nov – Prospecting Health Similar to Life: Concepts, Techniques and Cases
- 23–24 Nov – Open-Source Tools R: Extending the Toolbox of the Actuary
- 25 Nov – Stochastic Projection Models in Life Insurance
- 27 Nov – From Excel Tariff Calculators to Python – Agentic Edition
- 30 Nov – 1 Dec – Open-Source Tools Python: Extending the Toolbox of the Actuary
Course details
The ORA under IORP II: From EU Landscape to Board Conclusions
This web session provides a structured and practical walkthrough of the Own Risk Assessment (ORA) under IORP II.
We begin with a concise overview of the European pension landscape and supervisory expectations, followed by a clear comparison between ORA and ORSA.
The core of the session focuses on the practical building blocks of a robust ORA:
- linking strategy to risk identification
- assessing risk appetite and risk-bearing capacity
- applying scenario analysis, stress testing and reverse stress testing
- defining management actions and trigger frameworks
- formulating defensible board conclusions
The emphasis throughout is on practical implementation and producing ORA outcomes that are coherent, defensible and aligned with board responsibility.
Generative AI for Synthetic Actuarial Data
This web session is designed to demonstrate how to build synthetic insurance datasets using various generative models.
Several models will be employed, starting with Gaussian Mixture Models and extending to the conditional format for the typical non-life insurance dataset used to model frequency and severity. Results will be compared with those of the Conditional Diffusion Model. The seminar will explore the Variational Autoencoder and Generative Adversarial Networks using other insurance datasets. Lastly, we will also see the use of Large Language Models to generate synthetic data by exploiting prompt engineering.
The data generation process will be conducted by running several trials: reproducing the full number of records in the data fed into the generative models, applying data augmentation, and then omitting sensitive variables to preserve privacy.
Several techniques will be used for the validation of the generated datasets:
- Consistency Tests: to verify that synthetic insurance records strictly adhere to industry business logic.
- Kolmogorov-Smirnov Test: to ensure that the generated data maintains the underlying statistical properties of the original datasets.
- Data Visualization: using univariate analysis, correlation matrices, and other spatial techniques.
- Actuarial Modelling: evaluating predictive utility also through feature importance comparisons.
Prospecting Health Similar to Life: Concepts, Techniques and Cases
In the first part of this training the actuarial concepts that constitute the core of what is practised as Health SLT are introduced. We will outline some of the differences between jurisdictions like Germany and Austria to indicate how the concepts introduced so far are adapted to different legislations. By exemplifying the impact of (potentially different) premium adjustment clauses, we give indications to the treatment of Health SLT in Solvency II and IFRS 17.
In the second part of the training more recent enhancements are delineated, such as embedding frequency/severity modelling and Markovian states (Thiele’s formula) to the Health SLT actuarial framework. A Case Study with hands-on examples (in Excel) will be presented illustrating actuarial methods to support a tariff, by which an insured person may choose deductibles from a range of values as well as the application of Thiele’s equation in combination with frequency/severity modelling of claims.
Open-Source Tools R & Python: Extending the Toolbox of the Actuary
Four half-day web sessions on 23, 24 and 30 November and 1 December 2026, 8:30–13:00 CET. The R part (23–24 November) and the Python part (30 November – 1 December) can also be booked on their own. The fee for the full series already includes a 10% discount.
Open-Source Tools R: Extending the Toolbox of the Actuary
Over the last few years, typical data science tasks like data manipulation and modelling have gained a stronger foothold in the day-to-day professional life of the actuary. Open-source languages are renowned to be especially equipped to deal with these kinds of tasks, but can also be tricky to get started with, especially without a proper introduction. This workshop offers the opportunity to become more familiar with the open-source environment and its applications, illustrated in detail by means of several hands-on modules, thereby enabling the actuary to tackle the data science tasks in an elegant manner.
Open-source tools like R, Python and more recently Julia have gained a lot of momentum in recent years, not just in popularity but also in the amount of contributed code. Their respective communities are nowadays no longer exclusively composed of academic researchers and scientists, but also of professionals of all sorts of backgrounds, especially since the industry and corporate world have understood the added value of ‘community driven software’ and started to plug open-source tools into their processes and corporate tissue.
On top of this, actuaries are confronted with the same issues as academic researchers and scientists: the production of readable, shareable and reproducible code and results. This workshop will only focus on the ‘scientific stack’ of R.
This session is Part 1 of the full series ‘Open-Source Tools R & Python: Extending the Toolbox of the Actuary‘, scheduled for 23/24/30 November and 1 December 2026, from 08:30 to 13:00 CET and may also be attended as an independent part of the series. The sessions on 23 and 24 November will cover R, while the sessions on 30 November and 1 December will cover Python. The training fee for the full series already includes a 10% discount. You can book the full series here.
Stochastic Projection Models in Life Insurance
With the introduction of new accounting frameworks, the corresponding alignment of planning and performance management and with the increasing need for sophisticated asset liability management, the stochastic assessment of risk and value in connection with participating life insurance portfolios has become the industry standard over the last decade. The underlying basis for such an assessment is a cash flow projection model, simulating the way the life insurance undertaking is working and reflecting it by projecting local GAAP balance sheets and income statements. Due to the complexity associated with such calculations, simplifications are required especially regarding the modelling of the insurance contracts to meet operational and technical constraints. Therefore, it has become an area of actuarial research to develop methodologies that allow stochastic cash flow models to achieve results of adequate accuracy based on acceptable run times with affordable IT capabilities.
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 little-known Liability-2-Step approach, the session will present the operational experience of an Austrian insurance company.
From Excel Tariff Calculators to Python – Agentic Edition
Excel-based tariff calculators remain a cornerstone of actuarial work in life insurance, and in early 2026 we showed in our first EAA web session ‘From Excel Tariff Calculators to LLM-Powered Python Code’, how Large Language Models (LLMs) can help to port them into structured Python code. The feedback was encouraging, and the field has moved forward quickly since then. Tools have matured, reasoning quality has improved, and, most importantly, the working practice has shifted from a single actuary prompting an LLM into an orchestrated collaboration between actuary and AI agents.
This second edition takes that step forward. Instead of a craftsmanship-style workflow, we present an industrial, agent-based pipeline for calculator porting: structured extraction from Excel and VBA, preparation of actuarial context, LLM-driven code and test generation, and built-in quality assurance, all orchestrated so that the actuary keeps the lead and the LLM handles bounded subtasks autonomously. The pipeline itself has been built inside our DAV working-group context on AI-assisted calculation-engine development.
Participants will see the framework in action on a real-life insurance tariff calculator, from raw Excel input to a ported Python module with a matching test harness. We will not only show the happy path, but also the places where quality control hooks in, how disagreements between LLM-generated output and reference values are resolved, and how the actuary stays firmly accountable for what the pipeline produces.
This web session closes with a hands-on exercise in which each participant uses the pipeline to build a test comparison layer for a given piece of ported code. Because the pipeline is already in place, the LLM focuses narrowly on generating the test framework and the reference calculations needed to validate the port. A well-scoped task that gives participants an immediate, tangible experience of what agentic actuarial work feels like in practice.
Open-Source Tools Python: Extending the Toolbox of the Actuary
This session is Part 2 of the full series ‘Open-Source Tools R & Python: Extending the Toolbox of the Actuary‘, scheduled for 23/24/30 November and 1 December 2026, from 08:30 to 13:00 CET and may also be attended as an independent part of the series. The sessions on 23 and 24 November will cover R, while the sessions on 30 November and 1 December will cover Python. The training fee for the full series already includes a 10% discount. You can book the full series here.
The goal of this two half-day training is to introduce the participants to the Python open-source ecosystem and to get a good understanding of the language. However, the ecosystem is way too vast to be covered in merely two half-days, the participants will be asked to go through the basics of the language themselves, prior to the web session. During the first half day of the web session, these basics which will be shortly revised, but at a higher pace. The course material, containing the basics of the language, will be provided by the organizers several weeks before the beginning of the web session, such that the participants will have plenty of time to go through the material at her/his ease.
As such, less time needs to be spent on the basic elements of the language, hereby enabling us to organize a hands-on exercise session to more easily assimilate the course material. Note that the participants need to bring along a laptop on which Python is installed. Instructions on how to do so, will be provided by the organizers at the same moment as the course material of Python basics, hence several weeks in advance.
As a result, a jump start on how to truly use this language in practice will be provided to the participants, by focusing on solutions for problems that they will surely regularly encounter in their day-to-day job, by handing over lots of links to online resources and a very rich course material and by even organizing hands-on exercise sessions.
Solvency II Review – A Practical Case
The amended Solvency II Directive entered into force on 28 January 2025 and will apply from 30 January 2027 following national transposition. The Solvency II reporting as of the first quarter of 2027 will be under the new framework.
This session will provide a thorough understanding of the key changes on pillar 1 by illustrating the impact of each component on a fictive insurer in a dedicated template. Possible optimizations will be illustrated.
The objective of this web session is to allow the participants involved in Solvency II work to experience some key changes being introduced by the Solvency II Review through a practical case study. We will make this session interactive by virtue of breakout discussions and polls, so that the participants can also actively share their views and experiences.
CERA 0: A Refresher Course in Financial Mathematics & Risk Measurement
The European Actuarial Academy is one of the main providers of actuarial education – especially when it comes to Enterprise Risk Management (ERM). The concept of ERM has gained significant momentum in the insurance industry and beyond.
We offer a series of four training courses and exams (through DAV) to all actuaries who want to deepen their knowledge in Enterprise Risk Management and gain the international ERM-credential CERA.
The web session ‘A Refresher Course in Financial Mathematics’ gives an introduction to modern financial mathematics and derivative pricing. It is designed to prepare actuaries without adequate training in these fields for the quantitative parts of the CERA education. The web session is moreover an ideal learning opportunity for actuaries who want to become acquainted with or refresh their knowledge in these highly relevant fields.
The online course begins with a repetition of basic concepts in probability theory including characteristics of random variables such as moments and quantiles. In order to prepare the analysis of dynamic financial models we introduce the idea of conditional expectations and we discuss stochastic processes in discrete time. The online session continues with an introduction to financial mathematics. We study risk neutral valuation and the hedging of derivatives in discrete-time models. The last part of the web session is devoted to an introduction to financial mathematics in continuous time. Topics covered include stochastic processes in continuous time such as Brownian motion and the Ito formula, the Black Scholes model and the Greeks very basic term structure models and the pricing and hedging of simple stock and bond options. The web session consists of lectures interspersed by short exercise sessions where participants can apply the probabilistic techniques hands-on.
(9–10 December: until 13:45)
Non-Life Pricing Using Machine Learning Techniques with R Applications
Non-Life insurance is facing many challenges ranging from fierce competition in the market or evolution in the distribution channel used by consumers to evolution of the regulatory environment.
Pricing is the central link between solvency, profitability and market shares (volume). Improving pricing practice encompasses several dimensions:
- Technical: is our pricing adequate to cover the underlying cost of risk of my policyholders and the other costs we are facing? Which are the key variables driving the risk? Are they adequately taken into account in our pricing? What’s the impact of the claims history of my policyholder on its expected risk? In which segment are we profitable and in which are we not profitable?
- Competition: at what price will we attract the segments that we target and price out those that we do not want? Is the positioning of our competitors influencing our pricing practice and our profitability? What’s my position with respect to my competitors in terms of pricing? What are the segments in which I am well positioned and the segments where I am not well positioned?
- Elasticity: what price (evolution) are our existing customers prepared to accept? Does the sensitivity to price evolution depend on the profile of my customer?
- Segmentation: is our segmentation granular enough for our purposes?
The aim of this web session is to present some advanced actuarial techniques used in non-life pricing, competition analysis and profitability analysis. The web session focuses on some practical problems faced by pricing actuaries and product managers and presents some new techniques used in non-life pricing in order to open new perspectives for product development (competition analysis, profitability analysis,…).
This content was created with the help of an AI agent (a large language model), and was then checked and edited by a human.