FORECASTING EXCHANGE RATE OF SAR/CNY BY INCORPORATING MEMORY AND STOCHASTIC VOLATILITY INTO GBM MODEL

Since the volume of trading between Saudi Arabia and China is huge, the forecasting of the future price of exchange rates of SAR/CNY is a critical issue for investors. In literature, there are several proposed models to forecast future exchange rates. This research forecasted SAR/CNY by using GBM through three stages: classical GBM without memory and with no stochastic volatility assumption, GFBM with memory only and GFBM perturbed by SV with memory and stochastic volatility assumption. The results show that GFBM perturbed by SV has highest performance, and then GFBM and finally GBM. This result guarantees the positive effect for combining memory properties and stochastic volatility assumption into GBM to forecast exchange rates. This conclusion agreed with several empirical studies in literature. Generally, all models under study exhibited high accuracy according to the small values of MAPE (< 10%). Thus, all models can be utilized to forecast exchange rates in real financial markets.