This course covers the use of the R platform for statistical computing and data visualization for advanced analytics within the Insurance industry, with examples focusing on non-life insurance pricing.
Non-life insurance pricing is a well-known and well-established process and yet still a critical business issue. The standard for tariff analysis is generalised linear models. We first work through how to develop such a model in R, including model selection and validation. We touch upon how to deploy the model (both scoring using the model and updating the model itself) while ensuring the results remain validated and reproducible.
This part of the course covers substantially all the material of Non-Life Insurance Pricing with Generalized Linear Models by Ohlsson and Johansson (Amazon UK | US), the standard textbook for the European Actuary Academy.
Next we show how easy it is to extend the model to more complex techniques, and the advantages and challenges of doing so. We cover the usual extensions of GLM to GAM and GLMM, and also dive into modern techniques and ensemble models.
From a business perspective we are in no way advocating wholesale abandonment of classical approaches for modern techniques, “black-box” or otherwise. Rather, we propose that you make use of both: continuity and understanding tempered with the results from the latest up-to-date methods. In the final part we cover some of these business issues to show how other insurers resolved them and what commercial benefits resulted. Examples include using the advanced models to restrict the validity domain of the classical approach (“risk we do not understand and will not insure”) and using them to create derived variables, such as interaction variables, to extend the domain of the GLM (“understanding complex risk”).
- Introduction to pricing: the business problem and the data sets we will be using.
- GLM - Generalized Linear Models: Independent claims with categorical rating factors.
- The basics: assumptions and a brief introduction to generalized linear models.
- Model details: tests, confidence, and model selection.
- Multi-level factors and credibility theory.
- GAM - Generalized Additive Models: continuous rating factors.
- GLMM - Generalized Linear Mixed Models: longitudinal claims.
- Ensemble models: maximum predictive power.
- Summary and recommendations.
Note that part 1–3 of the course covers substantially all the practical material of Non-Life Insurance Pricing with Generalized Linear Models by Ohlsson and Johansson, the standard textbook for the European Actuary Academy. The book is recommended (but not required) for its deeper theoretical coverage. You can read more about this book on Amazon UK | US.
Detailed course syllabus
Download the Insurance training detailed schedule. This is subject to change and customization; the latest version will be provided at the course.
Instructor-led training over the course of five half-day sessions with in-class exercises as well as homework. We give the the course in both physical and online (virtual) classrooms.
About the instructor
This course is provided by CYBAEA who are experts in the analysis of commercial data to gain knowledge and genuine understanding of your markets and customers.
As the “more than analytics company” we understand how to exploit those insights and execute on that knowledge within the business to deliver profits and sustainable advantage.
The teacher is usually Allan Engelhardt who is an expert with over 22 years experience in big data analysis and more than 11 years experience with R.
Dates and more information
Contact us to register your interest and receive more information on this course, and we will let you know the next time we run a public class or we can set up one for you and your colleagues.