Time Series Analysis On Indian Mackerel Retail Price In Peninsular Malaysia

Abstract

Forecasting fish price has been started for a long time over the world. The main objective of this study is to predict the monthly retail price of Indian Mackerel in Peninsular Malaysia based on the 9 years data (2007-2015) using two methods which are Box-Jenkins method and Holt’s Linear Trend method. After analyzing the data, the Holt’s linear trend model and autoregressive integrated moving average or ARIMA (0, 1, 1) (0, 0, 0)₁₂ model were proposed. The diagnostic checking for the estimated models confirmed the adequacy of the models. The result of the study showed that the Holt’s linear trend method was become the better model since it had lower root mean square error (RMSE) and mean absolute percentage error (MAPE). Finally, this method was used to forecast 3 months upcoming Indian Mackerel price. However, both models have been proven successful in forecasting the monthly fish prices. This study will help the fish farmers and the planners for future planning in Peninsular Malaysia.