Actuarial Data Science

An initiative of the Swiss Association of Actuaries

Actuarial Data Science Tutorials

On this page we present all the tutorials that have been prepared by the working party. We are intensively working on additional ones and we aim to have approx. 10 tutorials, covering a wide range of Data Science topics relevant for actuaries.

All tutorials consist of an article and the corresponding code. In the article, we describe the methodology and the statistical model. By providing you with the code you can easily replicate the analysis performed and test it on your own data.

Case Study 1: French Motor Third-Party Liability Claims

Article on SSRN

Code on GitHub, consisting of standard R, R using TensorFlow and R using H2O.

Case Study 2: Insights from Inside Neural Networks

Article on SSRN

Code on GitHub

Updates

Below, we provide the most recent changes to the website:

25th Oct 18: Publication of code on GitHub for both tutorials.
6th Aug 18: Publication of our second tutorial: Insights from Inside Neural Networks.
5th Aug 18: Publication of the ADS strategy paper..

Spotlights

In the strategy document we describe the evolution of the actuarial profession, with Actuarial Data Science being the actuary of the 5th kind.

The actuary of the 5th kind has its core skills in Mathematics, Statistics and Computer Science.