Calendrier des événements

On Claims Reserving with Machine Learning Techniques

Présentation de thèse

The Institut des actuaires is pleased to invite you to a presentation by Vilma Guevara Härkönen, winner of the 2024 SCOR Actuarial Prize in Sweden for her thesis On Claims Reserving with Machine Learning Techniques.

This presentation will take place on Thursday April 10th at 6pm.

You can register HERE.

Attending this conference will allow you to add 6 points to your Continuing Professional Development score.

Abstract :

Machine learning has gained popularity due to advances in computing power and access to large datasets, enabling the training of complex models. This thesis explored its potential in insurance reserve setting by comparing Gradient Boosting Machines (GBM) and neural networks with traditional statistical models. The results showed that machine learning often provided more accurate reserve estimates, with GBM performing best in most cases by balancing over- and underestimations. While all models worked well on simulated data, they faced challenges with real-world data. Overall, the findings suggest that machine learning, offers an interesting approach for improving reserve accuracy in non-life insurance.

Voir tous les événements

Jeudi 10 avril 2025
18h00 - 19h00 (GMT +2)

L'événement est organisé en ligne

Intervenants

Vilma Guevara Härkönen

Folksam

Vilma Guevara Härkönen is an actuary specializing in non-life insurance at Folksam in Stockholm. She holds a MSc in actuarial science from Stockholm University, where she graduated in 2021. With a strong interest in innovation, she explores how machine learning can be leveraged to enhance reserving accuracy.

Autres événements

31 Mars

Copil CJA

31 Mars