Why take part?
The IFoA is piloting the use of hackathons as an opportunity for teams, no matter their experience, to provide insightful and different perspectives on current issues in this fast-paced challenge. In this first hackathon run by the IFoA, your output could help shape pandemic modelling going forward.
Setting up teams
Who can take part?
Anyone who is interested in this type of modelling can take part (subject to the hackathon rules). You team may need a combination of skills to complete this task in the required time. There must be at least one member of the team who is an IFoA (or affiliate) member to act as a team lead and point of contact.
There will be a limit of 20 teams able to take part in this activity.
How large can teams be?
Teams can consist of up to 8 individuals. We would recommend a team size of 4-6 for this activity.
What if I can’t find a team?
If you can’t find a team but are still interested in taking part, please contact Katy Stephenson. Whilst we can't guarantee to be able to create a team for you, we may be able to connect you with other like-minded individuals.
Preparing for the activity
What should teams do to prepare for the activity?
Teams are encouraged to:
- read the hackathon overview, and ARG bulletin to understand the background which the question will be based on, in particular the definition of R and how it is calculated
- consider the current ONS data available (along with any other data sets you might consider using) and
- consider ways they can best collaborate during the hackathon and allocate activities where necessary.
As the actual question will not be released until 29 April 2021, we do not anticipate any teams being able to start building models before the event begins.
How long will the activity take?
The question will be released at 9am (BST/ UTC+1) Thursday 29 April. Teams will have until the submission deadline 11:59pm (BST/ UTC+1) Tuesday 4 May to submit their output. These timescales will not be amended for any reason so teams should ensure they are in a position to submit their entry by the closing time.
How should teams collaborate?
Teams can collaborate however they choose, whether that’s on GitHub, Microsoft Teams or any other platforms they have available. We recommend that your teams agree this prior to Thursday 29 April. Team leads will need to submit the teams outputs on a shared file on Egress.
What data sets can teams use?
Teams will need to use the latest ONS data for the activity but are able to use other data sets should they wish to (subject to the hackathon rules and professional practices). If other data sets are being used, teams should ensure that they have authority to use the data and provide links to this within their submission.
When will teams receive the question?
The question will be released at 9am (BST/ UTC+1) Thursday 29 April and emailed to all team leads registered for the hackathon. If you don't receive the question at this time, please contact Katy Stephenson immediately as extensions of time will not be given for any reason.
How will teams submit their outputs?
Team leads will be given access to a shared folder to submit their team’s outputs:
- Links to your data set with instructions and any analysis code
- A summary paper describing data analysis and conclusions (3-4 pages)
What if the team doesn't complete all outputs in time?
We do expect that as this is a fast-paced challenge, time will be a key constraint in forming your outputs and the analysis your team will be able to do in this time and this should be considered in your preparation. Teams are expected to do what they can in the time provided.
Selecting a winner
How will a winning team be selected?
A panel of ICAT coordinators, ARG and IFoA members will select the winning team. Selection will be made considering the following however insight and innovation will also be key considerations:
- Analysis of relevant data
- Performance analysis: building appropriate models and develop analytical tools
- Drawing insightful conclusions
- Ability to clearly communicate conclusions to non-actuarial audiences
When we a winner be selected?
Outputs will be reviewed from Wednesday 5 May and we aim to announce a winner w/c 10 May. Should any delays occur, team leads will be kept informed.
How will the winner be announced?
The winning team will be informed directly and it will be announced on the IFoA website.
Have any further questions?
If you have any further questions, please contact Katy Stephenson.
Filter or search events
This practical course is aimed at actuaries at any stage of their career who want to develop their own growth mindset and apply it to their work setting and personal or professional lifelong learning. The content of the course builds on the lecture given by Dr Helen Wright on Growth Mindset as part of the President’s 2021 Lecture series, and will be delivered over a period of 2 months, from mid-October to early December.
The role of actuaries within the health sector varies considerably from one country to another, due to differences in the local evolution of health systems and the funding models for health services.
This paper outlines key frameworks for reserving validation and techniques employed. Many companies lack an embedded reserve validation framework and validation is viewed as piecemeal and unstructured. The paper outlines a case study demonstrating how successful machine learning techniques will become and then goes on to discuss implications. The paper explores common validation approaches and their role in enhancing governance and confidence.
Content will be aimed at all actuaries looking to understand the issues surrounding mental health in insurance and in particular those looking to ensure products and processes widen access for, and are most useful to, those experiencing periods of poor mental health.
The IFoA Policy Briefing 'Can we help consumers avoid running out of money in retirement' examined the benefits of blending a lifetime annuity with income drawdown. Panellists, including providers and advisers, will look at the market practicalities of taking the actuarial theory through into the core advice propositions used by IFAs and Fund Managers. They will share a number of practical issues such as investment consequences before and after retirement and the level of annuity that is appropriate and answer questions from the audience.
The IFoA is pleased to be hosting the Governor of the Bank of England, Andrew Bailey, to deliver a speech on delivering policyholder protection in insurance regulation.
The speech will be presented to an in-person audience, and simultaneously live-streamed, at 14.00 on Wednesday 1st December.
This webinar looks at the many types of biases, both conscious and unconscious and the impacts they can have in the workplace. Raising our own awareness and understanding of the issues can help us avoid the pitfalls of unconscious bias in particular. We’ve all heard the phrase ‘office banter’ but are we sure that’s how those on the receiving end perceive it and is it ok to go along with it?
Actuaries need to take action now - but how? With a focus on climate change, this session will provide informed insight to enable you to improve your knowledge and understanding of the issues involved, demonstrate how it will impact advice to your clients, and highlight prospective opportunities for actuaries within pensions and wider fields.
Pension scams have become more prevalent as a result of the pandemic, and Trustees have increased responsibilities to protect members, which means that actuaries need to be in a position to provide advice in this area. Our specialist panel will include a professional trustee, an IFA and head administrator, two of whom are members of PASA.
The covid-19 pandemic creates a challenge for actuaries analysing experience data that includes mortality shocks. To address this we present a methodology for modelling portfolio mortality data that offers local flexibility in the time dimension. The approach permits the identification of seasonal variation, mortality shocks and late-reported deaths. The methodology also allows actuaries to measure portfolio-specific mortality improvements. Results are given for a mature annuity portfolio in the UK
In this webinar, the authors of the 2021 Brian Hey prize winning paper present a new deep learning model called the LocalGLMnet. While deep learning models lead to very competitive regression models, often outperforming classical statistical models such as generalized linear models, the disadvantage is that deep learning solutions are difficult to interpret and explain, and variable selection is not easily possible.
The dominant underwriting approach is a mix between rule-based engines and traditional underwriting. Applications are first assessed by automated rule-based engines which typically are capable of processing only simple applications. The remaining applications are reviewed by underwriters or referred to the reinsurers. This research aims to construct predictive machine learning models for complicated applications that cannot be processed by rule-based engines.
With the Pension Schemes Act 2021 requiring a long term strategy from Trustees and sponsors, choosing a pensions endgame strategy has become even more critical. However, it is important that the endgame options available are adequately assessed before choosing one. With an ever-increasing array of creative and innovative options available, this decision may not be straightforward.