Machine Learning (ML) allows computers to process data, analyse it in real time and learn and make decisions based on data. Diverse applications from self-driving cars to chess computers have successfully relied on ML.

While the insurance industry is not necessarily known for being particularly innovative, insurance companies are increasingly embracing approaches commonly used in ML to address business challenges in different areas. Actuaries and data scientists apply ML to claim management, underwriting or customer service.

Nowadays, both data and models can be processed much faster than before which means data-driven approaches to actuarial modelling are being increasingly adopted by the insurance companies. The amount of data being used by insurance companies for different purposes has increased exponentially. As such, it is becoming more difficult for actuaries to identify anomalies in data, models and outputs. For example, some insurers apply Least Square Monte Carlo methods to derive their Net Asset Value and Best Estimate Liability proxy models. These models take a huge amount of data to perform complex calculations. It is not possible for actuaries to understand bad data and model behaviour by using traditional methods given the amount of data involved.

In this web session, we are going to discuss how techniques commonly used by data scientist in ML applications can help actuaries detect/remove bad data and significantly improve forecasting abilities of modern actuarial models.

Organised by the EAA - European Actuarial Academy GmbH.

This course is for professionals who process large amounts of data in actuarial models and would like to apply Machine Learning techniques to detect anomalies in their data in an automated way. No prior Machine Learning knowledge is a prerequisite for our course.

Technical requirements
Please check with your IT department if your firewall and computer settings support web session participation (the programme Zoom is used for this online training). Please also make sure that you are joining the web session with a stable internet connection.

In our first lecture, we will introduce our audience to some useful data clustering and anomaly detection techniques. On this foundation, our second lecture will be dedicated to practical applications of these methods in an automated Solvency II Internal Model calculation workflow. In particular, we discuss the interpretability of ML approaches and their validation.

The language of the web session will be English.

Abdal Chaudhry
Abdal is a consultant at Barnett Waddingham with over 10 years of experience working in the life insurance industry in the United Kingdom. Abdal specializes in Solvency II reporting, risk calibrations, proxy modelling and capital management and has delivered a number of projects in these areas for large UK based life insurance companies. Abdal has been working on the applications of Machine Learning techniques to the optimization of the Solvency II Internal Model SCR calculations.

Miruna Dudceac
Miruna is an Associate Actuary at Milliman with 4 years of experience working in both life and general insurance in the United Kingdom. Miruna worked on several projects involving Machine Learning applications and analytics in proxy modelling and risk pricing.

Re-Mi Hage
Re-Mi is an associate professor at Notre Dame University-Louaize and Academic Advisor for graduate and undergraduate program in Actuarial Sciences with more than ten years of experience in modelling, estimation, prediction, analysis, econometrics and computational statistics. Re-Mi’s research interests and teaching topics include non-parametric estimation, statistical learning, statistical inference, computational statistics, optimisation, Machine Learning, modelling in actuarial science, engineering, finance and biology.

Michael Leitschkis
Michael is a Principal with Milliman with over 15 years of experience working in the life insurance industry, notably in Germany and the United Kingdom. Michael specializes in risk modelling, e.g. in the context of Solvency II Internal Models, and actuarial systems transformation. Michael leads an R&D task force developing Machine Learning applications to actuarial modelling and reporting.