Forecasting Banana Harvest Area and Production in Turkey Using Time Series Analysis

Abstract

In this study, 1961–2015 period FAOSTAT data of banana harvest area and production in Turkey was modeled with the objective to forecast banana harvest area and production for the 2016–2025 period. Stationarity was provided with taking the first difference of the time series. Several Autoregressive Integrated Moving Average (ARIMA (0,1,1), ARIMA (1,1,0) and ARIMA (1,1,1)) and Exponential Smoothing (Holt, Brown and Damped) models were tested. Brown exponential smoothing model was determined as the most suitable one for forecasting banana harvest area and production. Banana harvest area was forecasted to be 6175 ha in 2016 and increase to 9733 ha in 2025 year. Banana production was predicted to show a substantial increase for the 2016–2025 period, from 291,667 to 482,093 t. Briefly, the results of this study could help policy makers to develop better macro-level policies for food security and sustainability, as well as to establish better banana planting area and production strategies in Turkey for the future.