Advanced Applications of Generative AI in Actuarial Science

Introduction & Programme

Organised by the EAA - European Actuarial Academy GmbH in cooperation with the Lietuvos Aktuarų Draugija.

Introduction
Generative artificial intelligence (GenAI) is rapidly changing how actuarial work can be done: from turning unstructured information into model-ready data, to accelerating analysis, documentation, and communication. Large language models (LLMs) enable workflows that go far beyond “chatting with ChatGPT” – but using them responsibly in actuarial practice requires a clear understanding of capabilities, limitations, evaluation, and robust integration into existing processes.

This two-day, hands-on seminar focuses on advanced, practically implementable applications of GenAI in actuarial science. After establishing a practical foundation (how modern LLMs work, where they succeed and fail, and how to assess output quality), participants will work through a series of case studies that reflect typical insurance realities: messy data, document-heavy processes, and the need for auditability, traceability, and human oversight. Throughout the programme, we will connect concepts such as prompting patterns, structured outputs, function calling, retrieval-augmented generation (RAG), fine-tuning, multimodal capabilities, and agentic AI to concrete actuarial use cases.

The core of the seminar is built around five applied case studies, each combining a clear business goal with hands-on implementation:

• Claims cost prediction enriched by text: using LLMs to derive meaningful features from unstructured claim descriptions, and integrating these into predictive models to improve performance and insight.
• Automated market comparisons with RAG: building an LLM-supported workflow that searches and synthesizes information from annual reports, product documents, policy wordings, etc. to speed up structured comparisons.
• Multimodal claims support for motor insurance: leveraging (fine-tuned) vision-enabled LLMs to classify car damage types from images and extract relevant contextual information for downstream processes.
• Agentic data analysis and reporting: demonstrating how an LLM-based multi-agent system can autonomously explore a dataset, run analyses, and draft a coherent report of key findings – with human control points and quality checks built in.
• Report generation and quality assurance with GenAI: designing a report pipeline that drafts actuarial narratives from inputs (results, tables, assumptions) and applies built-in checks (consistency, completeness, citation/trace-back to sources, and red-flag detection) before human review.

We conclude with an outlook and discussion that presents additional practical applications beyond the main case studies, without going into full implementation detail. We also address the challenges of applying generative AI in insurance and discuss future developments and their implications for actuarial work.

The seminar will be held in person, giving participants the opportunity to learn on site alongside other actuarial professionals, exchange ideas directly, and receive immediate support from the lecturers. The venue is the 4-star hotel Courtyard Vilnius City Centre (details below). The evening event on the first day is giving participants the opportunity to connect, discuss practical questions, and build their professional network in an informal setting.

Preliminary Programme
Thursday, 1 October 2026
08:45 – 09:00 Registration
09:00 – 09:15 Introduction & Welcome (EAA)
09:15 – 11:00 Foundations of Generative AI in Actuarial Practice
11:00 – 11:15 Coffee Break
11:15 – 12:45 Hands-on Case Study 1: Improving Claim Cost Prediction with LLM-Extracted Features from Unstructured Data
12:45 – 13:45 Lunch
13:45 – 15:15 Hands-on Case Study 2: Market Comparison Using Retrieval-Augmented Generation
15:15 – 15:30 Coffee Break
15:30 – 17:00 Hands-on Case Study 3: Image-based Vehicle Damage Classification and Localisation
approx. 18:30 Dinner

Friday, 2 October 2026
09:00 – 10:45 Hands-on Case Study 4: Agentic AI for Actuarial Data Analysis
10:45 – 11:00 Coffee Break
11:00 – 12:30 Hands-on Case Study 5: Report Generation and Quality Assurance with Generative AI
12:30 – 13:30 Lunch
13:30 – 15:00 Outlook and Discussion: Further Applications, Challenges, and Future Developments
15:00 Concluding Remarks, Closing of Seminar (EAA)

Learning Objectives & Approach

The purpose of this seminar is to equip participants with a practice-oriented understanding of generative AI and its most relevant applications in actuarial science and insurance. The seminar combines conceptual foundations with guided, hands-on coding to help participants move from “what is possible” to “what is reliable, measurable, and implementable” in real actuarial workflows. Emphasis is placed on responsible use: understanding strengths and failure modes, building guardrails and human review into workflows, and documenting assumptions and outputs so results remain reproducible and defensible. Participants work through actuarial case studies and reusable patterns (structured outputs, RAG, tool use, agents) and learn how to scope use cases, reduce hallucinations through workflow design, and integrate GenAI components into existing pipelines.

By the end of the seminar, participants will be able to:

• Understand the foundations of generative AI, with a focus on how large language models work, where they add value, and what risks they introduce (e.g., hallucinations, bias, data leakage, overreliance)
• Decide when GenAI is appropriate and when classical approaches (statistics, machine learning, or traditional programming) remain the better choice – based on feasibility, cost, explainability, and operational constraints.
• Build robust LLM-powered workflows using APIs or local setups, including function calling/tool use, structured outputs, retrieval-augmented generation, and, where suitable, fine-tuning – with attention to traceability and reproducibility.
• Understand and prototype agentic AI systems, including key concepts (e.g., agents, orchestration, tool use), practical safeguards, and realistic use cases in insurance and finance such as assisted analysis, document workflows, and reporting.

Related topics – such as regulation, governance, deployment architecture, and model risk management – are not the main focus of the programme, but will be addressed where they naturally arise from the case studies and implementation choices.

Overall, the seminar balances conceptual clarity, hands-on implementation, and forward-looking perspectives, providing participants with a concrete toolkit for applying generative AI effectively and responsibly in actuarial practice.

Participants

This seminar is designed for actuaries, data scientists, statisticians, and other professionals in the insurance and financial sectors who wish to deepen their knowledge of generative AI and its practical applications. Basic programming knowledge (e.g., Python) is recommended, while familiarity with generative AI concepts is a plus but not required. Most coding will be provided and guided by the instructors, allowing participants to experiment with, modify, and extend the examples to gain hands-on experience.

To fully benefit from the seminar, participants are strongly encouraged to bring a laptop. All coding will be done in Python using Jupyter notebooks, with live coding sessions forming an integral part of the programme. Exercises can be completed either via provided online platforms or on participants’ own setups, and detailed installation instructions will be shared in advance to ensure a smooth start.

Lecturers

Dr Simon Hatzesberger
Simon Hatzesberger is an actuary working as a Manager in Actuarial & Insurance Services at Deloitte, with a focus on GenAI applications in the insurance industry. During his previous tenure in the actuarial department at Allianz Private Health, he was responsible for various data- and AI-related topics for several years. He holds an MSc degree in Financial Mathematics and Actuarial Sciences from the Technical University of Munich, as well as an MSc degree in Computer Science and a PhD in Mathematical Stochastics from the University of Passau. Additionally, he is a member of the German Association of Actuaries, a Certified Actuarial Data Scientist, and a Certified Enterprise Risk Actuary. He is actively involved in several Actuarial Data Science committees of the German Association of Actuaries, serves as a workstream lead in the Artificial Intelligence Task Force of the International Actuarial Association, and is a member of EIOPA’s Consultative Expert Group on Data Use in Insurance.

Language & CPD Credits

The language of the seminar will be English.

CPD Credits
For this seminar, the following CPD credits are available under the CPD scheme of the relevant national actuarial association:

• Austria: 11 points
• Belgium:  11 points
• Bulgaria:  15 points
• Croatia: individual accreditation
• Czechia:  11 hours
• Denmark: 11 credits
• Estonia:  11 hours
• Finland: 7.5 points
• France:  63 points
• Germany:  11 hours
• Greece: 15 points
• Hungary:  11 hours
• Iceland: 11 credits
• Ireland: 11 hours
• Italy: approx. 4 credits (individual accreditation)
• Latvia: 11 hours
• Lithuania: 11 hours
• Netherlands:  approx. 11 points (individual accreditation)
• Norway: 11 points
• Poland: 11 hours
• Portugal: 11 hours
• Serbia: 5 hours
• Slovakia:  8 points
• Slovenia:  50 points
• Spain: CAC: 11 hours, IAE: 11 hours
• Switzerland:  15 points
• USA: SOA (Section B): up to 13.20 hours

No responsibility is taken for the accuracy of this information.

Fees & Registration Details

The coffee-breaks and lunches as well as the seminar dinner are included in the seminar fee. The accommodation is not included in the seminar fee and must be booked directly with the hotel.

Early Bird Registration Fee (until 1 August 2026):

• For private customers: € 1,173.70 (€970.00 + 21% VAT)
• For businesses with a billing address in Lithuania (with valid UID number): €970.00 (net, reverse charge applies)

Regular Registration Fee (from 2 August 2026):

• For private customers: €1,548.80 (€1,280.00 + 21% VAT)
• For businesses with a billing address in Lithuania (with valid UID number): €1,280.00 (net, reverse charge applies)

Important VAT Information:
Due to tax regulations, we are unfortunately unable to issue invoices to businesses based outside of Lithuania. Please enter your private billing address when completing the registration form.

Please submit your registration using our online form below. We recommend registering for the seminar as soon as possible because of the expected demand. If there are more persons interested in this seminar than places available, we will give priority to the registrations received first.

Your registration is binding. Cancellation is only possible up to 6 weeks before the first day of the event. If you cancel later, the full participation fee is due. You may appoint someone to take your place but must notify us in advance. EAA has the right to cancel the event if the minimum number of participants is not reached.

Prepayment is mandatory. Please make sure you enter the correct and final billing details when registering below. We will send you an invoice via email. Please allow a few days for handling and always give your invoice number when you effect payment. All bank charges are to be borne by the participant.

Registration is open until 24 September 2026. If registration has already been closed for this event, please call us or send an e-mail to contact@actuarial-academy.com in order to find out whether a late registration is still possible.

Venue & Accommodation

The seminar will take place at the hotel

Courtyard Vilnius City Centre
Rinktines str. 3
LT-09234 Vilnius, Lithuania
Hotel website

We have arranged special prices for accommodation. The special rate for a single room is €140.00 per night, including breakfast and VAT. It is valid for bookings by 31 August 2026 out of our allotment “EAA Seminar”. Our allotment includes a limited number of rooms. Kindly book your accommodation directly with the hotel using the hotel's booking form, and note the hotel’s cancellation policy.