Advanced Methods of Non-Life Pricing in R (R6)

Discover how to use advanced techniques for non-life pricing such as regression models and calibrating machine learning models in R through interactive Jupyter Notebooks.

Introduction

If you’re looking to learn how to utilise advanced applications to pricing in R, this course is ideal for you. An individual subscription gives you 3 months’ online access to:

  • Course materials
  • A personal coding environment through Jupyter Notebooks
  • Discussion forums to engage and collaborate with like-minded individuals
  • Instructional videos
  • Option to ask tutors questions through forums and Q&A sessions
  • Hands-on practical examples linked to actuarial work
  • On demand access

As Well As

Our Data Science Resource Library which features Actuartech and Industry specific curated additional content to assist you on your data science journey.

You can also request to access to coding challenges to practice the skills you learn in this course.

A IT engineer working on a project.
Someone working on an online course at their desk.

Pick from any of our introductory or advanced courses with bespoke insurance and actuarial specific case studies.

Our platform is easy to use and embeds the coding environment and learning material in one place to enable you to apply data science hands-on.

We provide case studies and projects relevant to actuarial work, and based on relevant datasets provided. You have the option to interact and network with your peers.

Overview

The course starts with an explanation of the methodology and implementation for generalised additive models (GAMs) in R. We use an introductory example of moving from statistical models to machine learning models, followed by modeling continuous variables using GAMs and penalised regression techniques (e.g. lasso, ridge, elastic net, etc). 

We then, in interactive e-learning sessions, discuss the difference between artificial intelligence (AI) and machine learning (ML) as well as classical approaches vs machine learning. We explain the objectives, families and general process/methodology of ML, and offer examples of ML in insurance. The first interactive e-learning session includes examples of ML in insurance. Thereafter, we focus on error measures, regression trees, bagging, and random forest. Lastly, we do a deep dive into gradient boosted models, neural networks, and support vector machines. Each interactive e-learning session ends with a short quiz for the student to check their understanding of the session before continuing.  

The course ends with the live lesson which deals with calibrating a machine learning model. There is a reference to three practical experiences, the example and two hands-on case studies. The example showcases the application of a regression tree on the claim frequency, and the case studies are hands-on experiences of predicting the number of claims with a Gradient Boosting Machine (GBM) and prediction of random forest on average claim amount. The Notebooks, along with their respective memos, are available for completion on the platform.

This course is presented mainly through a combination of videos with slides, interactive e-learning slides and Jupyter Notebooks. After each video there is a short quiz for the student to gauge their understanding of the section before continuing.

Get started

Advanced Methods of Non-Life Pricing in R

Sign up for a free preview of this advanced course in R

Free Preview

Preview

£300 once-off (3-month access)

Enroll Today

Course Structure

Chapter 1 introduces modelling continuous explanatory variables with generalised additive models and penalised regression techniques.

Chapter 2 introduces machine learning and discusses supervised machine learning techniques.

Chapter 2 offers practical examples of the models as a Jupyter Notebook.

Chapter 3 offers an example of the prediction of the number of claims with a regression tree and includes a hands-on case study on predicting the number of claims with a GBM and using random forest to predict average claim amount.

Chapter 4 discusses how to calibrate a ML model in practice through cross-validation and parameter tuning.

The Appendix contains further resources to assist the student in their data science journey.

A person showing different sections of an online course

Who's this course suitable for?

  • Individuals with experience in R and knowledge of basic machine learning techniques in R.
  • Individuals interested in learning how ML can assist with pricing and how it can offer advanced insights into data.
  • Individuals wanting to learn how to build advanced models in R.
  • Individuals working in pricing and reserving.

Why is this topic important?

  • Advanced models can offer improved accuracy over basic GLMs.
  • Modern machine learning techniques can capture the importance and interaction of rating factors, assisting with risk management and monitoring claim drivers.
  • Limitations of GLMs are addressed, preventing overfitting and maintaining interpretability.

Short note to say really enjoyed today’s webinar. It had a very clear message. […] fully in agreement with the comments that it is imperative we maintain our professional and ethical stance at all times if we want to continue to be trusted and relied on.

Webinars

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.

Heading

Short note to say really enjoyed today’s webinar. It had a very clear message. […] fully in agreement with the comments that it is imperative we maintain our professional and ethical stance at all times if we want to continue to be trusted and relied on.

Webinars

I just wanted to say what an interesting presentation that was. Thank you so much for taking the time to put this on for us, it is very much appreciated by all – especially the flexibility around hosting as a webinar instead of the original [in-person] format. It worked very well indeed!

Webinars

I think I’m [one of the first actuaries in my area] who are pointing towards Data Science, creating the new [role] of Actuarial data Scientist. For this reason i [sic] decided to follow a post graduate master in Business Intelligence and Big data analytics. I'm actively following your company and i [sic] think it is one of the best Actuarial consulting company [sic] who [sic] is pointing towards data Science!

Webinars

I love your videos - being free and accessible really helped me. The Q&A session was fantastic! It always comes down to execution and I feel this should always accompany your presentations - answering the question of how will your participants use what you give them. Keep up the great work!

Round Table

Thank you for having me along. I really found it the most motivating conversation I’ve had in a while, and made me think about what I’m trying to achieve within this area. We all need evenings like that to get some perspective on what we *think* is going on and what actually is. It was a very good evening.

Round Table

It was a really good introduction to Data Science and afterwards I felt that I now have a platform that I could use to further my understanding in this area.

Webinars

I am really happy to have been part of the talk. It was very insightful and please keep doing more of this. I am a data science student currently but I have an actuarial background. I worked in life insurance for about 5 months before resigning to do my masters in Data science so that I blend the actuarial world and Data science together. The talk gave me perspective. Even suggested some potential topics for my Thesis.

Webinars
Get started

Advanced Methods of Non-Life Pricing in R

Sign up for a free preview of this advanced course in R

Free Preview

Preview

£300 once-off (3-month access)

Enroll Today

Interested in Corporate Training?

We have tailored packages available to ensure that corporate teams have the option to attend structured live lessons by our tutors, and the option to request a practical assignment and bespoke feedback. Invoicing option available.