On Friday, 25 June 2021 at 08:30 BST, we were pleased to present a webinar on the applications of machine learning to motor insurance claims.
This webinar shows you how to utilise data science techniques to analyse motor insurance claims.
By fitting advanced data science models we aim to predict the frequency of these claims to assess risk.
This case study is designed to give a broad overview of basic machine learning techniques that can be used to model data in the context of a motor insurance company.
These techniques will be applied to a particular dataset (see below) in conjunction with more traditional actuarial techniques, including a comparison of performance in both instances with the results produced explained. In addition, we will touch on how certain models could potentially be fine-tuned to yield better and more explainable models, in the context of this dataset.
We will be using a dataset of motor contracts from a French insurer.
The file is named ‘freMTPL2freq’ and can be found on kaggle.com: https://www.kaggle.com/karansarpal/fremtpl2-french-motor-tpl-insurance-claims.
During this introductory webinar we will show you:
- Overview of how we utilise data science techniques to analyse motor claims using the dataset above.
- How to fit a machine learning model that aim to predict the frequency of these claims to assess risk.
- We demonstrate how these techniques and other data science techniques are being applied to aim to improve reserving and pricing processes within motor insurance.
This webinar will be presented by:
- Valerie du Preez, Founder and Managing Director at Dupro Advisory
- Patrick Moehrke, Junior Actuarial Consultant at Dupro Advisory
- Julien Crespy, Actuary & Data Scientist
- Xavier Marechal, CEO Reacfin
This webinar discusses coding competitions from various perspectives following the competition hosted by the AI Crowd (with Actuartech as one of the sponsors) where competitors acted as an insurance company by building a pricing model and competing against other players for profit.
This webinar discusses the significant changes in technology, regulation, markets, customer behaviour, the environment and other global trends are influencing the actuarial department.
This presentation aims to show practical steps to embark on a data science journey in Python. The presentation will show examples from each step of the data science pipeline, from importing and cleaning, model building and testing, to visualisation.
This presentation aims to show practical steps to embark on a data science journey in R. The presentation will show examples from each step of the data science pipeline, from importing and cleaning, model building and testing, to visualisation.
This webinar present two non-traditional insurance use cases that are challenging the norm with the use of innovative AI solutions; leveraged from cutting-edge technologies in wider fields.
This webinar addresses the significant challenges actuaries and their organisations are facing in an ever-changing world, especially in the midst of a global pandemic.
This webinar addresses how, as a result of COVID-19, the insurance industry is being affected through the combination of lockdown measures, changing product demand, increased mortality, health & event cancellation claims, and volatile financial markets, among others.
This webinar presents a brief history of Insurtech and how it is likely to develop in the future. It also explores the application of image, video and audio in the financial services industry and in insurance.
A huge increase in data generation, data capture & data storage combined with significantly increased computing power is providing insurers with a unique opportunity to re-evaluate the value their data can provide; & the technologies available to do that.
Actuartech and Montoux collaborated on a content series that digs into the heart of what the modern actuary looks like, the challenges and opportunities facing the profession today, and what the actuaries of tomorrow could look like.
AI has become more and more popular within the financial industry, and many insurers have started out on their AI journey. The webinar discusses some of the worries around delegating decisions to machines, and how to overcome some of these challenges.
The challenges faced at the moment given the global pandemic is causing actuarial teams to change their operating models significantly. This webinar discusses how ready we have been for this change and what issues we have been experiencing.
Explainable Machine Learning Machine learning techniques have become more and more popular within the financial industry mainly because of the potential to capture complex interactions from data the potential for better predictive models than traditional statistical models the ability to capture non-linear interactions within a range of inputs
A huge increase in data generation, data capture and data storage combined with significantly increased computing power is providing insurers with a unique opportunity to re-evaluate the value that their data can provide; and the technologies available to do that.
We explore opportunities created by new Insurtech innovations as well as look at how companies are responding.Insurers have the opportunity to optimise their processes and create new sources of revenue by rethinking their traditional business models with the use of modern day technologies.
IFRS17 has been deferred by another year.... The IASB decided that IFRS 17 will come into force on January 1, 2023. Join our webinar as we look at what this means for insurers. We will look back at recent progress made on IFRS 17 implementation by insurers. We will also look at the opportunities available to insurers to make the most of the extra year.
Methods used in non-life pricing are evolving at a fast pace and more advanced actuarial and statistical techniques are being used in pricing, competition analysis and profitability analysis.
How can life insurers address low persistency? How can data and analytics help? Join our webinar on Friday 12 March 12pm as we discuss how the full cycle of actuarial analysis is evolving
A huge increase in data generation, data capture and data storage combined with significantly increased computing power is providing insurers with a unique opportunity to re-evaluate the value that their data can provide.
Improvements in computational power has given rise to the use of data science and artificial intelligence techniques in a wide variety of areas, including finance, driverless cars, image detection, speech recognition etc. This is directly impacting business practices within the financial services through its application within banking, insurance and asset management.
In the current economic climate, insurers need to improve their processes continually – making them more efficient and cost-effective while maintaining the agility to deal with new requirements. At the same time, technological change is providing new ways of achieving these objectives. In particular, the term ‘robotics’ appears to be used everywhere, and it is important to grasp the impact and potential use of these new technologies.
Listen to Valerie du Preez, founder and Managing Director of Actuartech, on the panel for Legerity's IFRS 17 webinar discussing, "Can IFRS17 help deliver digital transformation?".
In a world of high volume and varied datasets, data science techniques can add valuable tools to an actuary’s toolkit to provide actionable insights from data.
Sophisticated machine learning models have the potential for high predictive accuracy but their complexity may sometimes result in black box models, which, in some cases, may appear to be a trade-off between accuracy and interpretability.
Sign up to our newsletter for the latest in actuarial technology and data science