General insurance – Machine Learning in Reserving Working Party – members

Application closing date: 7 December

Our starting premise is that while 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.

Find out more about the group’s outputs

Scope

1. Find out where the market is on progressing this

• What are the barriers
• What are the benefits?

2. Bring to together papers/work done to date

3. Undertake research

• Identify any ‘literature gaps’, for example areas as yet unstudied
• Carry out research to fill the gap
• This is likely to include an element of education in data science techniques using examples

4. Look at specific questions around techniques, for example:

• What techniques should be looked at/which work best and why?
• How to incorporate actuarial judgement into process
• How to measure/spot trends
• Can uncertainty be measured?
• IBNER most modelled for these purposes – what to do about IBNYR?
• Paid is often more reliable than incurred – can the information in case estimates be utilised?
• Use of operational time/claims process

5. What research should be commissioned?

6. Trust and ethics

• Analysis of the wider debate in machine learning where relevant to our work

7. What data sources are available?

• For testing methods
• Incorporating wider data sources, pricing, claims, external data.

We are particularly interested in volunteers with relevant reserving experience. However, the working party is open to everyone with enthusiasm for the subject and time to commit. Applications are welcome from both members of the Institute and Faculty of Actuaries (IFoA) and non-members.

Time commitment

It is estimated that volunteers will be asked to devote at least one or two days per month to the research, developing models and/or writing up findings.

Next steps

If you are interested in this role but would like an informal conversation before applying, please email us at engagement.team@actuaries.org.uk.

If you have read all the above and would like to apply, please send us:

• brief details of your relevant experience
• your reasons for wishing to get involved
• your ARN (if you are a member)
• a brief copy of your CV and full contact details (if you are a non-member)
• confirmation that you have read, understood, and agree to the information and requirements laid out in our volunteer information pack (please be aware that until we have received this confirmation, we will not be able to appoint you as a volunteer)

Please email all the above to engagement.team@actuaries.org.uk. Please note, we are unable to accept late applications.

We are committed to promoting diversity, equality of opportunity, and inclusion, within all our vacancies and we actively encourage applications from a diverse range of potential candidates. Recognising and embracing the unique and diverse talents of our volunteers is fundamental to the success of our organisation.

What you need to know

Volunteering provides you with a wide range of opportunities. With all rights and opportunities come responsibilities and we ask all our volunteers to comply with the terms of the IFoA’s governance manual and volunteer information pack. Before offering to provide support, please read through: what you need to know.