General Insurance Machine Learning in Reserving

About us

The General Insurance Machine Learning in Reserving working party (MLR WP) is a group of over 70 volunteers, bringing together a range of data scientists, actuaries and academics from around the globe.

When we started out in 2019, our premise was to find out why, whilst machine learning techniques are widespread in pricing, they are not being adopted ‘on the ground’ in reserving (certainly in the UK). Since then we have been working to help GI reserving actuaries develop data science skills, and are looking at ways that machine learning can be incorporated into reserving practice.

Workstreams

We have a number of different workstreams:

• Foundations – where do I start/how do I learn machine learning?
• Literature Review – we have reviewed over 60 papers and have highlighted a few of the best.
• Research – we are conducting a variety of research projects. We always aim to share the code so you can try it for yourself.
• Practical considerations – how to interpret ML models/explainability, how to deal with the issues reserving teams come across.
• Data – what data is available to develop ML techniques on?
• Survey – why has the uptake of machine learning in reserving been slow and what are UK and Canadian companies doing in-house (from 2020)?

For the most up-to-date information, our blogs, and more detail on the workstreams, please see our Github site or join the conversation on our LinkedIn page.

Contribute as a volunteer

We are open to new volunteers who have the time and enthusiasm to make a contribution. You don't have to be a member of the IFoA to join. If you would like to help us further the research and would like to collaborate with like-minded people, please see the IFoA volunteer vacancies page for how to apply.

Outputs

• Talks

• Blogs

• No time like the present (The Actuary) – The MLR WP discuss how, and why, general insurance reserving actuaries should get on board with machine learning

_{Last updated October 2022}