Unlocking Actuarial Data Insights: A Practical Guide on RAG and Advanced Techniques
In the continuously evolving landscape of Artificial Intelligence (AI), Retrieval Augmented Generation (RAG) has emerged as a disruptive technology transforming how we interact with AI systems. RAG combines the strengths of information retrieval and Large Language Models to create powerful applications that can access and use vast amounts of data to generate contextually relevant and informative responses. This web session is designed to equip actuarial professionals with a solid understanding of RAG and its practical applications in the actuarial field. The session will be split into a theoretical deep dive and a hands-on session. Participants will discover the theory behind RAG and its core components, including the key role played by vectors and vector stores, and explore advanced engineering techniques that drive superior performance, such as query decomposition, re-ranking, prompt engineering, and agents.

• Actuarial analysts, consultants, and data scientists working in insurance or finance who want to improve their skills in the disruptive RAG technology
• Actuarial managers and directors interested in leveraging AI to improve their workflows
• Anyone with a basic knowledge of Large Language Models and Python.

Participants should have access to Google Colaboratory.

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.

The web session aims to equip actuarial professionals with the knowledge and skills behind Retrieval Augmented Generation (RAG), from basic to advanced techniques. By the end of the course, participants will understand how to exploit and interact with AI systems to improve decision-making processes in actuarial tasks.

The language of the web session will be English.

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 data science activities. In the past, he was an assistant professor of Insurance Statistics at the Catholic University of Milan. He collaborated with the IAA and IFoA in several working parties and attended several data science competitions. He held workshops and talks at several conferences/meetups. He’s a member of the Astin and the Italian Actuarial Body Association.