TIME – SERIES MODELLING OF FOOD SECURITY INFLATION IN MALAYSIA USING AN ARIMA MODEL AS A MACHINE LEARNING APPROACH

Abstract

After air and water food, is the most important thing that we as humans need to survive and getting wholesome food is becoming more and more difficult. Food security refers to the accessibility and availability of the food resources. A household is considered food-secure if there is no starvation in every family member. With the burgeoning population in the world nowadays, food security become a significant problem across the globe by every country and international organizations. The objective of this study was to forecast the prices of food by category based on the 7 years data from time-series consumer price index reported by the Department of Statistics Malaysia (DOSM) from 2014 to 2021. The study considered Autoregressive Integrated Moving Average (ARIMA) processes to forecast the future trend of the food prices. The ARIMA model for forecasting food prices showed good agreement and stationery concerning the observed data on food prices based on the Augmented Dickey Fuller (ADF). The results show the ARIMA model to be a suitable method for analyzing statistics. In data-poor food prices situations, this method can support potential evaluations of future food prices for decision making and effective management.