University of Twente Student Theses

Login

On machine learning approaches to forecast non-life insurers’ loss reserves

Hunsicker, C.F. (2023) On machine learning approaches to forecast non-life insurers’ loss reserves.

[img] PDF
2MB
Abstract:This thesis, titled "On Machine Learning Approaches to Forecast Non-Life Insurers’ Loss Reserves," has been conducted at KPMG Advisory N.V. in the department of Financial Risk Management (FRM). The study delves into the inherent risks faced by insurance companies, distinguishing between life and non-life insurance businesses. The primary focus is on the loss reserves of non-life insurance companies, which are crucial for ensuring the financial stability of these institutions. The loss reserve is divided into premium and loss reserves, with the latter being the main subject of this research. The research emphasizes the importance of accurate estimation of the loss reserve, as it impacts the pricing of insurance policies, compliance with regulations, and the overall financial standing of insurance companies. The study also explores the claim development patterns across different Lines of Business (LoBs) and the associated challenges in determining the appropriate reserve due to the varying nature of claims and their settlement timelines. The research builds upon previous work by exploring the application of machine learning models to predict the loss reserve of non-life insurers, aiming to provide a more accurate and efficient approach to this critical actuarial challenge.
Item Type:Essay (Master)
Clients:
KPMG, Amstelveen, Netherlands
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:30 exact sciences in general
Programme:Industrial Engineering and Management MSc (60029)
Link to this item:https://purl.utwente.nl/essays/97770
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page