Supervised Learning Algorithms for Non-Life SCR Ratio Forecasting
Supervised Learning Algorithms for Non-Life SCR Ratio Forecasting
Author(s): Marius Cristian Acatrinei, Adriana Ana Maria Davidescu, Laurentiu Paul Baranga, Razvan Gabriel HAPAU, George CALINSubject(s): Economy, Business Economy / Management, Financial Markets
Published by: EDITURA ASE
Keywords: general insurance; machine learning; risk prediction; solvability capital requirement ratio;
Summary/Abstract: The solvency is measured by the Solvency Capital Requirement (SCR). This study seeks to determine the best financial ratios to forecast SCR because it is significant. There is seasonality, data jumps, and shifts in insurance indicators, which make prediction of SCR difficult. Different machine learning algorithms are applied to the insurance market in this research to see how well they can describe and predict the SCR ratio. Gaussian process regression, ensemble methods, regression decision trees, stepwise regression, and neural networks were used as supervised learning techniques to find the most suitable method to predict SCR. According to our analysis of nonlife insurance data from Romania between 2016-2020, debt ratio, reserve adequacy, receivables, and liquidity are among the key indicators that should be considered when forecasting SCR. These findings can be useful for policymakers, regulators, actuaries, and professionals involved in risk management or the insurance industry.
Journal: Proceedings of the ... international conference on economics and social sciences.
- Issue Year: 6/2024
- Issue No: 1
- Page Range: 631-647
- Page Count: 17
- Language: English