You are here

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.

Workstreams

Foundations

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.

Survey

Lead: Sarah MacDonnell

Find out where the market is on progressing this:

  • what are the barriers?
  • what are the benefits?

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

 

Chair Sarah MacDonnell
Membership 48
Established 2019

Contact Details

If you want more information about this research working party please contact the Communities Team.

professional.communities@actuaries.org.uk

Filter or search events

Start date
E.g., 28/09/2020
End date
E.g., 28/09/2020

Events calendar

  • Autumn Lecture 2020: Professor Elroy Dimson

    Online webinar
    14 October 2020

    Spaces available

    Many individuals and institutions have a long-term focus, and invest funds for the benefit of future generations. Their strategy should reflect their long horizon. University endowments are one of the oldest classes of institutional investor, and I will present the first study of the management of these endowments over the very long term.

  • GIRO Conference 2020 Webinar Series

    Available to watch globally in November.
    02-13 November 2020
    Spaces available

    This year's GIRO has been re-designed as a virtual conference to offer members and non-members the opportunity to get up to date content from leading experts in the general insurance field via online webinars. All sessions will be recorded and made available to purchase and re-watch post-event on the IFoA's GI Online Learning Resource area.

  • Life Conference 2020 Webinar Series

    Online
    16 November 2020 - 27 November 2020

    Spaces available

    This year's Life Conference has been re-designed as a virtual conference to offer members and non-members the opportunity to get up to date content from leading experts in the life insurance field via online webinars. All sessions will be recorded and made available to purchase and re-watch post-event on the IFoA's website.

  • Spaces available

    Cash-flow driven investing is a game-changer for DB pension funds navigating their end-game. Suitable for sponsors who want to reduce risks on their balance sheets. And for trustees, it shifts the focus to providing greater certainty of returns, managing funding level volatility and ensuring they have enough income to pay cash-flow requirements.

  • Spaces available

    The talk will provide an understanding of the priorities and relationships between deficit reduction contributions, in the context of wider scheme funding, and different types of value outflow from the employer based on the working party’s recently published report.