Forecasting Malaysia bulk latex prices using autoregressive integrated moving average (ARIMA) and exponential smoothing

Abstract

Natural rubber is a crucial component of many developed countries' socioeconomic structures since it is often used to manufacture essential consumer goods such as tires and latex gloves. The natural rubber industry is heavily affected by the volatility and unpredictability of the natural bulk latex markets. Therefore, forecasting natural rubber prices is critical for the rubber industry in procurement decisions and marketing strategies. This study aims to model monthly bulk latex prices in Malaysia using Autoregressive Integrated Moving Averages (ARIMA) and Exponential Smoothing. The models' performance is measured using the Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The Malaysian Rubber Board has 132 historical prices for latex in Malaysia from January 2010 to December 2020. They are used for training and testing in determining forecasting accuracy. The findings show that ARIMA (1,1,0) provides the most accurate prediction. The model is considered as the best and highly accurate, with a lower MAPE of 8.59 percent and RMSE of 69.78 sen per kilogram.