| EVALUATION OF A VARIABLE ANNUITY PORTFOLIO WITH DEATH BENEFIT USING MACHINE LEARNING METHODS |
| کد مقاله : 1063-FEMATH6 |
| نویسندگان |
|
سید محمد حسین آقابزرگ افجه *1، محمد جلوداری ممقانی2، مرتضی اعلاباف صباغی3 1دانشکده بیمه اکو 2دانشکده آمار، ریاضی و رایانه دانشگاه علامه طباطبایی 3دانشکده بیمه اکو - دانشگاه علامه طباطبایی |
| چکیده مقاله |
| Variable annuities (VA), also known as equity-linked insurance, are modern life insurance contracts that allow the insureds to choose from a selection of investments. Although these contracts are not fully introduced in the insurance market of Iran, according to their significant popularity among developed countries, it is expected that these contracts may have a considerable market share in the future. Due to the nature of these contracts, the area of research on VAs is an interdisciplinary area of actuarial science and mathematical finance, while the most important objective is to evaluate options included in VAs. In this research, our main purpose is to study and elaborate various applications of data clustering and machine learning on the estimation of the risk charge of a large portfolio of VAs with guaranteed minimum death benefits. The results of this research indicate that by applying machine learning algorithms, we reach the estimated risk charge of the portfolio in considerably shorter time while the difference between estimated value and calculated value by Monte Carlo simulation is not significant. This will enable us to modify its application for the Iranian Insurance industry. |
| کلیدواژه ها |
| Variable Annuities, Equity-linked Insurance, Machine Learning, Monte Carlo Simulation. |
| وضعیت: پذیرفته شده برای ارائه شفاهی |