EVALUATION OF A VARIABLE ANNUITY PORTFOLIO WITH DEATH BENEFIT USING MACHINE LEARNING METHODS

Equity-linked insurance, also known as Variable annuities (VA), are mod ern life insurance contracts geared with investment vehicles. 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.