Causal AI for Actuarial Models

Einleitung/Dauer

For years, correlation has been central to the actuarial profession's practice. Actuaries have mastered the art of identifying patterns in historical data to price risk and predict future losses. However, in the era of "Big Data" and increasingly complex algorithms, there is a critical limitation: traditional statistical models can tell us what is happening, but they often struggle with why. While a predictive model may identify a strong association between a specific variable and a loss, it does not establish a direct cause-and-effect relationship. Building on Judea Pearl’s ideas, Causal AI helps actuaries move from correlations in historical data to causal relationships.

Is causal inference a fashion of the moment? No—for the modern actuary, it represents a step toward actively influencing outcomes. Instead of asking, "What usually happens?" actuaries can now answer, "What would happen if we changed this specific factor?". By using causal diagrams (DAGs) and the "Ladder of Causation," actuaries can distinguish true risk drivers from collider bias.

Causal AI enables product designs that reflect contemporary lifestyle habits. For instance, it can support creating adaptive premiums, improving transparency and fairness in underwriting by embedding causal reasoning directly into the sales process, and leveraging IoT data with updated causal analysis to provide a flexible subscription that reacts to the user’s changing risk profile.

Preliminary Programme
Wednesday, 17 June 2026
10:00-11:00 Foundations of Causal AI and Introduction to Causal AI in Actuarial Science
11:00-12:00 Causal AI in the Actuarial Toolkit and Applied Case Studies

All the above times are given in CEST (Central European Summer Time).

Vorgehensweise und Ziele

In this web session, we will explore the formal scientific discipline of causal inference and the transition into the actuarial field. We will explore new actuarial toolkits needed to address challenges of the changing nature of actuarial work.

Teilnehmer

• Actuarial Analysts, Risk Professionals, and Data Scientists: any technical practitioners in insurance who wish to evolve their skill set beyond traditional correlation, mastering the "why" behind predictive models.
• Actuarial Managers and Directors: created for forward-thinking leaders interested in leveraging Causal AI to drive revolutionary product designs, dynamic pricing strategies, and enhanced underwriting transparency.
• Technical Practitioners: open to any professional with knowledge of statistical modelling and Python.

Participants should have access to Google Colab and a basic understanding of Python.

Technical Requirements
Please check with your IT department if your firewall and computer settings support web session participation (the programme Zoom will be used for this online training). Please also make sure to join the web session with a stable internet connection.

Dozierende

Claudio Giorgio Giancaterino
Claudio Giancaterino is a qualified Actuary who works during the day with Intesa Sanpaolo Assicurazioni, an Italian Insurance Company based in Milan. In his free time, he is involved in AI & Data Science activities. Previously, he served as an assistant professor of Insurance Statistics at the Catholic University of Milan. He collaborated with the IAA and the IFoA on several working parties and participated in data science competitions. He holds workshops and talks at several conferences and meetups. He’s a member of the Astin Actuarial Group and the Italian Actuarial Body Association.

Sprache/Kurztitel

The language of the web session will be English.

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

• Austria: 2 points
• Belgium:  2 points
• Bulgaria:  3 points
• Croatia: individual accreditation
• Czechia:  2 hours
• Denmark 2 credits
• Estonia:  2 hours
• Finland: 2 points
• France:  12 points
• Germany:  2 hours
• Greece: 3 points
• Hungary:  2 hours
• Iceland: 2 credits
• Ireland: 2 hours
• Italy: individual accreditation
• Latvia: 2 hours
• Lithuania: 2 hours
• Netherlands:  approx. 2 points (individual accreditation)
• Norway: 2 points
• Poland: 2 hours
• Portugal: 2 hours
• Serbia: 2 hours
• Slovakia:  individual accreditation
• Slovenia:  individual accreditation
• Spain: CAC: 2 hours, IAE: 2 hours
• Switzerland:  individual accreditation
• USA: SOA (Section B): up to 2.4 hours

No responsibility is taken for the accuracy of this information.