Kajian Metode Simulasi Monte Carlo

Abstract

Forecasting is an important technique for projecting future values based on historical data. The Monte Carlo simulation Method is one of the forecasting methods that uses random numbers, specifically through the use of a Linear Congruential Generator (LCG) and mathematical equations for prediction, forecasting, estimation, and risk analysis. The Monte Carlo simulation Method with one iteration has a high level of accuracy, as evidenced by previous research. The more iterations used, the more accurate the forecasting results. Therefore, the author is interested in examining how well the Monte Carlo simulation method with N iterations performs in forecasting. The study of the Monte Carlo simulation Method with N iterations will be conducted on the forecast of the number of visitors to Fort Rotterdam. The aim of this research is to determine the accuracy of the Monte Carlo simulation method with N iterations for forecasting the number of visitors to Fort Rotterdam. The MAPE values from 2013 to 2018 using the Monte Carlo simulation Method with N iterations sequentially are 16%, 13%, 13%, 12%, 1008%, and 31%. The forecasting ability from 2013 to 2016 falls into the good category, the forecasting for 2017 falls into the poor category, and the forecasting for 2018 falls into the fair category. The accuracy of the Monte Carlo simulation Method with N iterations, where the standard deviation values are higher than the standard deviation of the data containing outliers in this study, is classified below the good category.