Advanced Applications of Generative AI in Actuarial Science: Case Studies Beyond ChatGPT

This talk will explore the transformative impact of Generative AI (GenAI) on actuarial science, illustrated by case studies including a live demo.
We begin with a historical overview of AI, tracing its evolution from machine learning through early neural networks to modern GenAI technologies. Subsequently, we showcase four practical case studies that demonstrate how Large Language Models (LLMs) can enhance actuarial processes:
First, we show how LLMs improve claims cost prediction by deriving significant features from unstructured textual data. We then examine the automation of market comparisons using Retrieval-Augmented Generation, a GenAI concept designed to identify and process relevant information from documents. The third case study highlights the capabilities of fine-tuned vision-enabled LLMs in classifying car damage types and extracting contextual information. Lastly, we present a multi-agent system that autonomously analyzes datasets to generate comprehensive reports detailing key findings.
The presentation concludes with insights into further potential applications of GenAI within the insurance industry.