Application of Machine learning Techniques to the Calculation of Solvency Capital Requirements

Blake, Gareth

Application of Machine learning Techniques to the Calculation of Solvency Capital Requirements

Thesis / Dissertation

2026

Publisher

University of Cape Town

Department

School of Management Studies

Faculty

Faculty of Commerce

Abstract

The application of machine learning in actuarial science is a rapidly expanding field that bridges traditional actuarial methods with emerging data-driven techniques. This paper examines how machine learning can be used to calculate an insurance company's Solvency Capital Requirement (SCR). Various machine learning models were trained and tested to assess their predictive accuracy for the SCR across different risk scenarios. The findings indicate that machine learning approaches can reliably forecast the SCR, although interpretability challenges must be addressed due to the complex nature of these models. This work contributes to the existing literature on the intersection of traditional actuarial practices and modern machine learning methodologies.

Keywords

machine learning

solvency capital requirement

Reference:

Collections

Masters

Full item page