/ Machine Learning

Insurance Data Science 2018 Conference

Making use of data science in insurance is the reason that Agrippa was established and we were proud to help sponsor and present at the conference.

Introduction

We have just returned from participating and helping to sponsor the the first Insurance Data Science conference at Cass Business School in the centre of the City of London. This was a two day event bringing together practitioners and academics to talk about applications of data science in insurance.  

Cass Business School

Day One

The first day presented talks on topics ranging from risk assessment, customer analytics, pricing, reserving, capital management, catastrophe and econometric modelling.

The keynote speakers were Prof. Dr. Gareth Peters (Heriot Watt University) who talked about recent work in improving the estimation of mortality rates and Eric Novik (CEO, Generable) who gave a general introduction to the application of Bayesian techniques. The balance of the talks were either twenty or ten minutes in length which allowed coverage of a wide range of topics. If you want to find out more here is a complete list of talk

The first day was topped off with drinks and dinner in the spectacular Ironmongers' Hall.

Ironmongers' Hall

Day Two

The second day was a full-day practical workshop covering the application of Bayesian techniques to traditional insurance problems. The talks and workshops were given by Eric Novik and Paul-Christian Bürkner, Jake Morris and our own Mick Cooney and covered the use of STAN in building practical solutions.

My personal highlight was Paul-Christian Bürkner's talk on his R package BRMS. BRMS provides an interface to fit Bayesian generalized multivariate multilevel models using STAN. The formula syntax used by BRMS is very similar to that of existing R packages thus providing a familiar interface for performing regression analyses in a Bayesian setting.

The workshop concluded with a two hour session in which the participants tried their hand at implementing various solutions in STAN and BRMS with the help and guidance of the presenters.

Conclusion

All of us at Agrippa had an excellent time, learning and interacting with all the participants. The organisation was, once again, flawless and the facilities at CASS are outstanding making this one of the best value conference around. If you work in insurance and want to find more about how to use data science in your day to day job this conference is not to be missed - see you next year in Zurich!

The Agrippa team

This post was a collaboration between

Michael Crawford, Mick Cooney, Peter Brennan, Gerard de Vere

  • Michael Crawford

    Michael Crawford

    Michael trained as an actuary but has always worked in IT. He is responsible for providing, project management, data-driven insights, machine learning and AI advice to our financial services clients.

    More posts by Michael Crawford.

    Michael Crawford
  • Mick Cooney

    Mick Cooney

    Mick is a theoretical physicist with a MSc in high performance computing and a PhD in quantitative finance. He runs a couple of data science meetups, is an expert in the use of R and is a Bayesian.

    More posts by Mick Cooney.

    Mick Cooney
  • Peter Brennan

    Peter Brennan

    Peter a chemist by training, has a PhD in photophysics, an MSc in Data Mining, an MSc in Distributed Computing and has developed machine learning / AI anti-fraud solutions for insurance companies.

    More posts by Peter Brennan.

    Peter Brennan
  • Gerard de Vere

    Gerard de Vere

    Gerard has many years’ experience building and managing technology platforms for global re/insurance companies. He combines a passion for technology with a pragmatic approach to getting results.

    More posts by Gerard de Vere.

    Gerard de Vere
Insurance Data Science 2018 Conference

Subscribe to Agrippa Data Consulting