General Insurance Machine Learning in Reserving

Our starting premise is that whilst machine learning techniques are widespread in pricing, they are not being adopted ‘on the ground’ in reserving (certainly in the UK).  The idea of the working party is to help move this forward, by identifying what the barriers are, communicating any benefits, and helping develop the research techniques in pragmatic ways.

At the same time we understand the resource and time pressures that reserving actuaries are under and the aim is not to replace existing reserving methods per se, but to start the journey to understanding if and how machine learning may help us in our day to day work.

This is an international working party bringing together experts in this field from around the globe.

For the most up to date information, our blogs, and more detail on the workstreams, please see our Github site.

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

Join the conversation on our LinkedIn page

Workstreams

Survey

Further details

Lead: Sarah MacDonnell

We have spoken to companies in the UK and Canada to find out whether our presumption was correct that machine learning is not being used ‘on the ground’ in reserving. We found that there is a great deal of interest in the subject and that a number of companies are investing in the research.

• UK findings
• Canadian findings

We have plans to undertake additional surveys in other countries.

Foundations

Further details

Lead: Grainne McGuire

Provide a path to gaining competency in common statistical and machine learning techniques by:

• creating a roadmap of methods to learn
• gather together relevant learning materials and,
• developing notebooks in R and Python with example code.

Literature Review

Lead: Greg Taylor

Bring together and review related papers or work.

Data

Lead: Nigel Carpenter

• Identify publicly available datasets that can be used to illustrate reserving techniques.
• Provide a summary of the features available in each dataset.
• Provide notebook examples of how to generate simulated datasets.

Research

Develop and undertake our own research.

We anticipate adding additional workstreams covering issues such as pragmatic considerations, and trust and ethics, as our research develops.

Outputs

• GIRO – Nov 2020

• CIA Appointed Actuary Virtual Seminar – Sep 2020

• CAS Casualty Loss Reserving Seminar – Sep 2020

• Machine Learning in GI Reserving- Data Science MIG Event, March 2020