Parallel to the very dynamic development of machine learning methods in the recent years, the number of applications of the “learning from data” paradigm in the actuarial area has been steadily increasing. In this web session we plan to present the latest implementations of the machine learning methods – primarily decision tree based models and neural networks – for finding innovative solutions for the old actuarial problems.

Organised by the EAA - European Actuarial Academy GmbH.

The web session is intended for all interested actuaries. Although you do not need an extensive knowledge of the machine learning techniques, it is advantageous to have a general idea about the most important machine learning methods like neural networks and decision tree based models. These methods will be briefly introduced in the web session, but only at a high level, in order to allow for sufficient time for concrete applications.

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.

Our focus will be on recently implemented models. An important criterium for the machine learning applications which will be presented in the web session is that an actual model with a company’s data has been built.

In the beginning we will give a short introduction of machine learning and its best known and currently most widely used algorithms – decision trees derivatives and deep neural networks. Then we will introduce a few applications by presenting the context of the actuarial problem and the results. Our intention in this web session is not to present code or to actually go through the modelling process, but rather to offer as broad an overview as possible of the recent applications in the actuarial departments.

The language of the web session will be English.

Zoran Nikolić
Zoran Nikolic is a Certified Actuarial Data Scientist (DAV). At B&W Deloitte he is in charge of the actuarial data science area. He is also a member of the DAV Actuarial Data Science committee as well as the head of the Working Group Statistical Methods. In the last years he has supervised a large number of these in the area of actuarial science and published a few articles and use cases on machine learning and insurance risk management.