EAA Web Session: "A Machine Learning Approach to Assumption Setting"

Einleitung/Dauer

A Machine Learning Approach to Best Estimate Assumption Setting: Life Insurance Case Study

This web session will explore how Python's Machine Learning libraries and Explainable AI (XAI) techniques can be used to enhance best estimate assumption setting in life insurance. Attendees will gain an understanding of the intersection between Machine Learning, XAI, and actuarial science, with a focus on practical applications and real-world case studies.

Topics Covered:

• An introduction to Machine Learning concepts relevant to life insurance assumption setting.
• Demonstration of Python libraries for exploratory data analysis and model building.
• Step-by-step guidance on building, training, and validating predictive models for assumption setting.
• Techniques to mitigate against overfitting
• Evaluation metrics to assess model performance
• Explainable AI techniques to ensure transparency and interpretability of Machine Learning models.
• Examples of successful implementations in assumption setting.
• Best practices and common pitfalls in integrating Machine Learning and XAI into actuarial processes.
  

Vorgehensweise und Ziele

By the end of the online training, participants will leave with an understanding of how Python machine learning libraries can be used for best estimate assumption setting in a life insurer. Participants will also understand how XAI (Explainable AI) techniques can be used for model validation and model comparison.

Teilnehmer

This web session is intended for all actuaries, statisticians and data scientists in the life insurance industry who wish to augment the traditional statistical approach to best estimate assumption setting with Machine Learning. A basic knowledge of Machine Learning concepts and some programming skills (e.g. Python or R) are helpful prerequisites but are not necessary.

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

Jennifer Loftus
Jennifer is an actuary and accountant with over 20 years’ experience in the insurance industry. She currently serves as Executive Director, Group CFO, Chief Risk Officer and Head of Actuarial Function with Acorn Life in Ireland. She is also an Independent Non Executive Director of Vhi, the Irish state-owned health insurer.  Jennifer is a Fellow of the Institute and Faculty of Actuaries (UK), the Society of Actuaries in Ireland and the Association of Chartered Certified Accountants. She is a member of the IFoA Actuarial Data Science Working Group and is an active member of the Society of Actuaries in Ireland through the Data Science Committee and the Diversity, Equity, Accessibility and Inclusion Committee. Jennifer holds an MSc in Data Analytics and is an Ambassador for Women in Data Science.

Sprache/Kurztitel

The language of the web session will be English.