1  Introduction

Our opening statement from August 2020

It’s probably fair to say that we are living in the era of big data and machine learning.

This was true in 2020 when Sarah MacDonnell (chair of the MLRWP) launched our website and blog in her first post and in the years since, advances in neural networks, and the recent explosion in large language models have put AI and ML firmly front and centre.

In the actuarial world machine learning (ML) has certainly made inroads into personal lines pricing - tight margins and high competitiveness create a large incentive to extract as much value and insight from data as possible.

However, there has been less use of machine learning in reserving, possibly due to less obvious or immediate competitive advantages. Additionally practical challenges in implementing ML, from actually using the models, to finding the time in a busy reservint team to develop the necessary skills have limited use of ML.

But while reserving may not make extensive use of ML yet, there is recognition of its potential and a lot of interest. Ceratinly, we have observed high engagement with our material at the various conferences we have presented at.

ML techniques applied to richer, more detailed and broader datasets may allow us to gain insights we have not been able to conceive of before; be it as new segmentations, operational improvements, early warning systems, cost efficiencies, or revelations into claim life cycles, settlement patterns or consumer behaviour.

There may also be operational efficiencies to be gained; freeing time for targeted deep dives, allowing more frequent updates, or benefitting those with very large numbers of diverse classes.

Over the last four years we have published material in a number of areas. We gather much of this material together in this book, organised by workstream: