Comparative study for Modeling and Forecasting life insurance premiums applying ETS, Holt Winter, NNETAR, and TBATS models | ||
| المجلة العلمية للدراسات والبحوث المالية والتجارية | ||
| Volume 6, Issue 2 - Serial Number 1, July 2025, Pages 55-81 PDF (1.31 M) | ||
| Document Type: المقالة الأصلية | ||
| DOI: 10.21608/cfdj.2025.358453.2171 | ||
| Author | ||
| Dina Talaat Hamdy Neel* | ||
| Faculty of Business Administration, Horus University | ||
| Abstract | ||
| Life insurance provides financial security to individuals, as well as helping to improve the stability of financial markets. It also offers advantages in terms of discipline and continuous savings. To achieve this, life insurance companies need to calculate and forecast premiums. The aim of this research is to model and forecast life insurance premiums by applying alternative forecasting models. The data set is extracted from the insurance statistical annual book data for the period 2009–2023 for Misr Life Insurance quarterly premiums and forecasts up to 2026. Four models were applied to determine what the best forecasting model was for this type of data. To address this, models were applied: Exponential Smoothing models (ETS), Holt Winter models, Neural Network Autoregressive NNETAR, and Trigonometric Seasonality Box-Cox Transformation ARIMA errors Trend Seasonal components TBATS. The primary findings of this research highlight the rise in premiums for Misr Life Insurance, a governmental company sector. In addition, among the applied models in this paper, NNETAR is the best model to forecast life insurance premiums with this type of data. | ||
| Keywords | ||
| life insurance; premiums; Exponential smoothing ETS; Holt Winter | ||
|
Statistics Article View: 75 PDF Download: 66 |
||
