Category: DATA SCIENCE / AI - actuview - the international streaming platform for actuaries

AI Governance and Risk Management: Perspective from Insurance, Medicine and Space Sectors

Mon, 13 Apr 2026 13:35:30 +0000

Artificial intelligence is profoundly transforming several industries, including the insurance and space sectors as well as medicines regulation. Such transformation is both constrained and driven by the necessity to comply with EU legislative requirements (e.g. EU AI Act) and the availability of a wide range of tools. In this webinar, organised by the AAE, the speakers will explore how each profession is building frameworks for trustworthy and accountable governance around AI. The session will draw out the shared challenges such as the black box problem, bias and fairness, and professional accountability — and what each community can learn from the other.

Welcome and Introduction Esko Kivisaari, Chairperson of AAE AI and Data Science Working Group
Actuarial Governance & High-Risk AI Systems- Bogdan Tautan, Chairperson of AAE Risk Management Committee - Claudio Senatore Vice-Chairperson of AAE AI and Data Science Working Group
European Medicines Agency (EMA): AI in the Medicines Regulation — Perspective on Governance and emerging challenges Denise Umuhire and Orsolya Eotvos, EMA
European Space Agency (ESA): Impact Analysis of AI Regulation in the Navigation Sector Ora Buch Kornreich, ESA
Panel discussion AAE, EMA, ESA: Q&A All speakers & participants

DAVvorOrt | Generative KI - Was ist jetzt, bald und überhaupt möglich?

Wed, 08 Apr 2026 14:31:41 +0000

Simon Hatzesberger gibt einen praxisnahen Überblick über den Einsatz generativer Künstlicher Intelligenz in der Versicherungs‑ und Aktuarsarbeit. Anhand konkreter Beispiele und Live‑Demos zeigt er, wie Large Language Models, agentenbasierte Systeme und KI‑gestützte Tools bei der Analyse von Daten, der Erstellung von Berichten, der Automatisierung von Prozessen und der Modernisierung von IT‑Systemen unterstützen können. Zugleich werden Grenzen, Risiken und Sicherheitsaspekte beleuchtet. Der Vortrag ordnet die künftige Rolle von Aktuarinnen und Aktuaren ein und zeigt, warum Fachwissen, Validierung und verantwortungsvolle Entscheidungen auch im KI‑Zeitalter unverzichtbar bleiben.

Interpretable Ensembles: Enhancing Claim Frequency Modeling with External Socioeco-nomic Factors

Mon, 30 Mar 2026 09:18:42 +0000

The modeling of claim frequencies with interpretable risk factors is central for tariffing and risk classification in Non‑Life Insurance. Advanced ML can estimate the proven and interpretable (sparse) risk factors of a GLM in an automated and data‑driven approach [1]. Alongside the methodical advances, the value of high‑quality internal data histories is recognized by insurers. Additional external features, e.g. climate, spatial or socioeconomic information, can deliver further valuable insights for understanding the underlying risks [2,3,4]. The pooling of diverse external information and detailed internal claims creates a very comprehensive database for a more detailed claims analysis. However, most of the innovative methods are not designed to exploit the advantages of large datasets. Moreover, some of them have convergence difficulties with very large datasets in practice.In this work, we present a novel method to investigate the value of the combination of high‑quality data histories enriched with manifold socioeconomic information using a real dataset. Our approach, inspired by ensembles, enables an efficient modeling while the forecasts remain fully interpretable. In addition, the uncertainty and stability of the effects of single risk factors become visible. The results show quantitatively that both the addition of socioeconomic information and the utilization of concepts for large datasets significantly improve the forecasting quality of both established and innovative actuarial models. References.[1] Devriendt, S., Antonio, K., Reynkens, T., & Verbelen, R. (2021). Sparse regression with multi‑type regularized feature modeling. Insurance: Mathematics and Economics 96, 248‑261. [2] Tufvesson, O., Lindström, J., & Lindström, E. (2019). Spatial statistical modelling of insurance risk: a spatial epidemiological approach to car insurance. Scandinavian Actuarial Journal, 2019(6), 508‑522. [3] Knighton, J., Buchanan, B., Guzman, C., Elliott, R., White, E., & Rahm, B. (2020). Predicting flood insurance claims with hydrologic and socioeconomic demographics via machine learning: Exploring the roles of topography, minority populations, and political dissimilarity. Journal of Environmental Management 272, 111051. [4] NAIC (2025). 2021/2022 Auto Insurance Database Report. https://content.naic.org/sites/default/files/publication-aut-pb-auto-ins.... (Download on 11.08.2025)

Plenary Session 2: The AI Enabled Actuary & Farewell

Wed, 25 Mar 2026 12:40:30 +0000

This session brings together three complementary perspectives on how artificial intelligence is reshaping actuarial practice.
Bernard Wong demonstrates how modern data science and AI‑driven workflows unlock new actuarial insights, highlighting emerging techniques and practical applications across insurance domains.
Mike Callan examines how actuarial education is evolving to prepare future professionals, showing how data science, GenAI competencies, and ethical AI use are becoming core components of actuarial training and practice.
Tan Wei Chyin reflects on the IAA’s AI-assisted Kaggle Hackathon, illustrating how AI changes the way actuaries learn, reason and solve problems, and what differentiates exceptional analysts in an AI‑enabled environment.

These presentations offer a forward‑looking view of the AI‑enabled actuary, covering skills, tools, governance, education, and practical case studies across the actuarial value chain.

AI in Insurance: Practical Applications, Performance, and Trust

Wed, 25 Mar 2026 14:01:55 +0000

This webinar explores how artificial intelligence is being applied across the insurance value chain to enhance actuarial performance, operational efficiency, and decision-making—while maintaining trust and professionalism. Drawing on real-world examples from a leading health insurer and a global reinsurer, the session highlights practical AI use cases in pricing, underwriting, claims, risk assessment, portfolio management, and health management. It also addresses the critical role of actuaries in governing AI responsibly, managing bias and risk, and ensuring transparency and ethical use. Together, these perspectives demonstrate how trusted, scalable AI can drive meaningful impact in insurance when actuaries remain firmly in the loop.

Increasing Actuarial Performance while building trust with AI

Increasing Actuarial Performance While Building Trust with AI highlights how artificial intelligence—one of the SOA’s top three strategic initiatives for 2026—can enhance actuarial work when applied responsibly. The presentation emphasizes hat actuaries have a long-standing reputation for professionalism and judgment, providing a strong foundation for building trust with AI. It walks through key strategies for using AI effectively, including understanding AI risks, keeping the actuary firmly in the loop, and identifying appropriate use cases. The session also addresses professionalism, bias, and the critical role of education in ensuring AI supports sound, ethical, and transparent decision-making. Ultimately, the presentation positions actuaries as uniquely equipped to lead in high-stakes AI environments where trust truly matters.

AI Application in Ping An Health Insurance

During the presentation, the speaker will outline how AI is being applied across the health insurance value chain at Ping An Health Insurance (PAH) to support the “health insurance + health & wellness services” strategy. It demonstrates AI-enabled use cases in marketing, pricing, underwriting, claims settlement, and end-to-end health management. Through AI agents, multi-modal large models, and integrated data platforms, PAH enhances operational efficiency, personalization, risk management, and customer experience, shifting from passive claims handling to proactive health and risk management while enabling large-scale, personalized health services.

The AI Developments from A Reinsurers's Perspective

As risks grow more complex, actuarial sciences must improve risk assessment and protection, but data access remains a challenge. SCOR's AI Assistant, a generative AI tool, efficiently extracts and structures data from diverse documents with high accuracy, supporting key insurance workflows. This innovation enhances actuarial practices by enabling more precise assessments and better portfolio management, demonstrating the value of scalable AI in insurance and paving the way for future advancements with autonomous AI support.

Maximizing the Interpretation of Black-Box Models & From Black Box to Glass Box

Wed, 25 Mar 2026 13:21:03 +0000

Maximizing the Interpretation of Black-Box Models

We propose a novel global interpretable machine learning (IML) method for interpreting black-box models. One of the challenges actuaries face when applying machine learning in practice is the interpretability of the models, and our method contributes to solving it. Our method, called Maximum Interpretation Decomposition (MID), is designed to inherently maximize interpretability. MID addresses the limitations of existing global IML methods directly.

In the first part, we will discuss the theoretical background of this method. In the second part, we demonstrate how MID can be used to interpret black-box models using the open-source tools {midr} and {midlearn}. The demonstration highlights the practical utility of MID rather than focusing on implementation details.

Actuarial Digital Twin with Ontology-Driven Graph Database and Agentic AI

Actuaries face the “AI Paradox”: needing the speed of generative AI while requiring deterministic transparency for regulatory compliance. This session introduces an ontology-driven GraphRAG approach that moves beyond traditional document-based RAG by enabling structured reasoning across interconnected actuarial data. The Glass Box framework separates AI reasoning (“the Brain”) from actuarial calculation engines (“the Muscle”), enabling structured reasoning and automation of complex workflows such as product specification and reconciliation with full transparency. By applying a human-in-the-loop “Sandwich Workflow,” insurers can safely scale AI adoption while ensuring auditability and regulatory confidence, allowing actuaries to focus on high-value strategic decision-making.

AI for Pension Funds: Insights and Use Cases

Fri, 06 Mar 2026 17:16:08 +0000

Unlock how Artificial Intelligence is reshaping pensions and social security work. Join us for an insightful session featuring leading actuarial AI expert Ronald Richman, who will share practical applications of AI in longevity modelling, experience analysis, and actuarial workflow automation. This webinar will highlight real-world use insights, emerging opportunities, and what actuaries doing work in pensions and social security need to know to stay ahead in an AI-driven future.Be sure to join us for what promises to be an informative and engaging discussion.

DENK LAUT – der Podcast: FIT4AI, Episode 7: KI im Management von Versicherungsunternehmen

Wed, 04 Mar 2026 12:06:52 +0000

In dieser Episode von DENK LAUT – FIT4AI sprechen wir mit den Vorständen Ralf Oestereich und Michael Krebbers (beide Stutttgarter Leben / Süddeutsche Krankenversicherung) über die strategische Bedeutung von Künstlicher Intelligenz in Versicherungsunternehmen.Gemeinsam spannen wir den Bogen von Automatisierung und organisatorischer Transformation über Kulturwandel und Führung bis hin zu regulatorischen Fragen rund um den EU AI Act.Unsere Gäste geben offen Einblick, wie künstliche Intelligenz das Management, die Zusammenarbeit zwischen IT und Fachbereichen und die Skill-Anforderungen verändert – und warum Regulierung nicht nur Bremse, sondern auch Chance sein kann.Zum Abschluss wird es ganz konkret: Welchen Rat haben die Vorstände an junge, wie auch ältere Aktuare?

The European Actuary No. 45 | Using Modelling for a Healthy Future – Interview with Camilla Holm

Thu, 26 Feb 2026 16:09:24 +0000

In this interview with TEA's Jennifer Baker, Camilla Holm of PFA Denmark spoke to The European Actuary about PFA’s successful strategy combining health professionals’ experience with data scientists’ modelling, leading to a 70% reduction in long-term sickness. She highlighted the importance of using measures focused on operational relevance while ensuring human contact to build customer trust. The approach involved early intervention, combining psychological and physical care. Future plans include refining models and using AI for case handling. Holm emphasised the need for industry standards for preventive impact and highlighted the Nordic model’s success in integrating labour market policies, health systems and pension security.

You can find the full TEA issue No. 45 here: https://actuary.eu/the-european-actuary-issues/.

Justice As Fair Discrimination

Thu, 19 Feb 2026 09:27:46 +0000

...

Balancing Pricing Sophistication with Simplicity

Thu, 19 Feb 2026 08:50:08 +0000

...

The Convergence of MLOps and Actuarial Control

Thu, 19 Feb 2026 08:29:20 +0000

...

There’s a Snake In My Sheets! How Actuaries can Use Python to Level Up Their Excel

Tue, 17 Feb 2026 09:18:26 +0000

...

In-Context Learning Enhanced Credibility Transformer

Tue, 17 Feb 2026 09:09:40 +0000

...

Practical Considerations for Elasticity Modelling and Price Optimisation

Tue, 17 Feb 2026 07:50:19 +0000

...

Unlock Value From Reserving – Putting the Back Office On the Front Foot

Tue, 17 Feb 2026 07:41:36 +0000

...

Modern ML Approaches to Actuarial Risk Management Challenges: from NLP Risk Discovery to Neural Optimization

Fri, 13 Feb 2026 09:02:34 +0000

...

YAWC 2026 Eastern Semifinals

Thu, 12 Feb 2026 12:33:57 +0000

Watch this YAWC 2026 Eastern Semifinals and find out who will move to the finals taking place in Tokyo in November.

YAWC 2026 Western Hemisphere Semifinals

Thu, 12 Feb 2026 12:02:53 +0000

Watch the YAWC Western Hemisphere Semifinals and find out who will move on to the final round taking place in Tokyo in November.

DENK LAUT – der Podcast: FIT4AI, Episode X.2: KI-Begriffe unterhaltsam erklärt

Mon, 19 Jan 2026 15:13:56 +0000

In dieser zweiten Sonderausgabe der Reihe "FIT4AI" widmen wir uns der Klärung weiterer Begriffe des Themenbereichs Künstliche Intelligenz - und das auf ganz spezielle Art und Weise. Wir drehen das Glücksrad und erläutern was ist:

Explainable AI (XAI) & Black-Box-Modelle
Natural Language Processing (NLP)
Künstliche Neuronale Netze & Deep Learning
Große Sprachmodelle (LLMs) & Token
Trainings-, Validierungs- & Testdaten
Transformer-Modelle & Attention-Mechanismus

DENK LAUT – der Podcast: FIT4AI, Episode 6: Generative KI Anwendungen für das Aktuariat?

Wed, 17 Dec 2025 10:29:35 +0000

In dieser Episode sprechen wir mit zwei führenden Experten über echte Use Cases von GenAI in der Versicherungsbranche. Wir zeigen, wie KI die Arbeit von Aktuar:innen unterstützt, diskutieren Chancen, Herausforderungen und Risiken. Es geht vor allem darum, welche Aufgaben können abgegeben werden und welche nicht. Jetzt reinhören und erfahren, wie die Zukunft des Aktuariats aussieht!

Die in der Episode angesprochenen Notebooks finden sich unter:
https://github.com/IAA-AITF
Bzw. die Starter-Notebooks hier:
https://github.com/DeutscheAktuarvereinigung

Future of Analytics in Commercial Lines

Mon, 12 Jan 2026 08:18:02 +0000

Discover how AI and automation are transforming commercial lines underwriting. This session explores the evolution from manual processes to AI-augmented and algorithmic underwriting, highlighting use cases such as data ingestion, risk scoring, fraud detection, and portfolio management. Learn how generative AI enhances insight and monitoring, enabling faster decisions and strategic portfolio steering. Gain practical insights into reducing friction across the value chain and building a unified decision environment for the insurer of the future.

Outcome Focused AI - How to Cut Through the Hype to Get to Practical Solutions

Mon, 12 Jan 2026 07:33:23 +0000

Cut through the hype and discover practical strategies for implementing AI in actuarial science. This session explores what AI really means for actuaries, including data readiness, machine learning applications, and deployment considerations. Learn about opportunities for predictive modeling, automation, and risk management, as well as ethical challenges and transparency requirements. Real-world examples illustrate how actuaries can combine technical expertise with professionalism to deliver outcome-focused AI solutions.

AI middle office empowers long term value creation by actuaries

Fri, 09 Jan 2026 14:07:52 +0000

Learn how AI-powered middle office solutions can create long-term value for life and health insurers. This session explores the integration of predictive AI engines across underwriting, claims, agent management, persistency, and sales processes. Discover how risk-driven AI frameworks enhance efficiency, reduce fraud, improve customer experience, and optimize profitability. Real-world case studies demonstrate the impact of predictive models on underwriting automation, claim fraud detection, agent risk management, and purchase propensity prediction.

Artificial Intelligence (AI) Agents in Asset and Liability Management (ALM)

Fri, 09 Jan 2026 14:02:45 +0000

Discover how Agentic AI is transforming Asset and Liability Management (ALM). This session explains the foundations of large language models (LLMs), techniques like Retrieval-Augmented Generation (RAG) and Chain-of-Thought reasoning, and how AI agents can automate data ingestion, optimize algorithms, and synthesize outputs for better decision-making. Learn from the Solvencii Copilot case study - a multi-agent AI assistant designed to enhance ALM modeling and empower actuaries with real-time insights and automation.