Modeling and forecasting cherry production in Turkey

OpenAlex İngilizce

In this article, the yearly cherry production (in tonnes) data of Turkey for the period of 1961-2019 were used in order to model and forecast cherry production for the period 2020-2025 using Autoregressive Integrated Moving Average (ARIMA) models. Time series data for cherry were found to be non-stationary at the level and hence the first differences of the series were taken to obtain stationary time series before performing the time series modeling. The Box-Jenkins approach was employed and the ARIMA (1,1,1) model was determined to be the most appropriate among the several ARIMA models for the data. The model forecasted the increase in cherry production for 2020-2025 period in Turkey from 66.4076 to 72.6028 tonnes (approximately 1.8% annual growth rate in production). The forecasts for the between 2020 and 2025 will access from 696 351 to 887 609 tonnes in logarithmic transformed new series (ARIMA (0,1,1)). The findings of this study may assist policy makers in developing better strategies for sustainable cherry production. Key Words: Cherry production, ARIMA, Forecasting, Stationary, Turkey