ENSAE Paris - École d'ingénieurs pour l'économie, la data science, la finance et l'actuariat

Artificial Intelligence in Insurance and Actuarial Studies

Objectif

This course explores how AI is transforming the insurance industry. We start with the essential technical tools—Git, APIs, and Docker—to help students build, collaborate on, and deploy AI models in practical insurance settings. Next, we dive into actuarial science with a focus on life insurance, using survival analysis to understand and predict biometric risks.

From there, we move into neural networks, unpacking their structure and how they’re applied in insurance. We then introduce Natural Language Processing (NLP), where we look at attention mechanisms and transformers, tools that are reshaping areas like underwriting automation and customer service. Finally, we cover large language models (LLMs) and discuss how they’re being used in the industry.

By the end of the course, students will have a strong grasp of the technical foundations and a clear view of how AI is being used across the insurance industry. We’ll also discuss critical regulatory topics like GDPR and give an inside look at career paths in data science within insurance, along with the skills that are most in demand.

Plan

The course is made of a mix of lessons and hands-on sessions.

During lessons we cover the topics below:

  • Reminder of the context of AI during the past 10 years and all challenges that came out (regulation, transparency, bias, cloud usage, etc.).
  • Best practices with deployment tools (Git, Docker, APIs).
  • What Life Insurance is and how is survival analysis done using ML-based techniques.
  • Advanced deep learning and NLP techniques (Transformers) applied to insurance.
  • Introduction to LLMs and use cases.
  • What are the "new" skills we can expect from an actuarial data scientist?

Hands-on sessions are in Python and usage of Git is essential (you might want to install it before sessions [Git (git-scm.com)](https://git-scm.com/) ) to illustrate some notions mentionned during the lessons.  
  
Advised to people who have never used python to perform a quick training on it (will be provided during first session otherwise).