EAA Web Session: "The UBI Motor Insurance Telematics Pipeline Blueprint"

Einleitung/Dauer

The nature and requirements of motor telematics remain somewhat elusive to the industry as many skills and concepts are not part of the classical syllabus of the profession; while time series data has a fixed place in the profession, dealing with (physical) sensor data has not, much less when extracting risk measure features from it.

This web session will allow actuaries to gain an introductory understanding of the relevant concepts that are required to enable usage-based insurance in the motor line of business from the technical and pricing point of view.

Vorgehensweise und Ziele

The purpose of the seminar is to establish the possible steps from data collection to pricing in order to highlight both the unique challenges as well as opportunities of usage-based insurance (UBI). To this end, a possible pipeline from data collection and feature engineering to risk profiling and finally pricing will be central to this training, but an outlook toward actual motor pricing that incorporates telematic observables is included as well.

The topic is broken down into an introduction of general concepts and some aspects from the relevant literature, a chapter on data collection and preprocessing, a chapter on feature engineering incorporating the unique sensor qualities in play and a chapter on evaluating risk with telematic risk measures extracted from driving data.

Teilnehmer

It will be helpful for participants to have a basic idea about the usage and potential of Machine Learning / Artificial Intelligence in the insurance context. The specific methods relevant to the subject will be introduced and referenced alongside the training material.

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

Prof Dr Fabian Transchel
Fabian is a professor for Data Science at the Harz University of Applied Sciences, Department AI, where his research focus is Insurance and Finance, most notably motor telematics and pricing. He is active in the development of the new Actuarial Data Science subjects at the German Actuarial Association (DAV) and a lecturer for the German Actuarial Academy (DAA).

Sprache/Kurztitel

The language of the web session will be English.