Forecasting Turkey's Hazelnut Export Quantities with Facebook's Prophet Algorithm and Box-Cox Transformation

Abstract

Time series forecasting methods are used by an evolving field of data analytics for the prediction of market trends, sales, and demands. Turkey is the major producer of hazelnut in the world. If Turkey wants to continue its domination of hazelnut and protect the price-setting role, time series forecasting methods could be key factors accordingly. There are a few studies that focused on time series forecasting of hazelnut export quantities of Turkey, and this study uses a recently developed algorithm and implements a power transformation to increase the forecast accuracy. The presented research aims to forecast Turkey’s hazelnut export quantities for the coming 36-months starting from June 2020. The forecasting process was conducted with the help of Facebook’s Prophet algorithm. To improve the forecast accuracy, a Box-Cox power transformation was also implemented to process. To find out the stationarity and periodicity of the data set, the Augmented Dickey-Fuller test and autocorrelation function was applied to the time-series data. The Prophet algorithm, with Box-Cox transformation, projected the hazelnut export quantity could be over five hundred thousand tons from 07/2020 to 06/2023. The export quantities were in an increment trend, and the slope of the trend has increased since June 2008 by 0.66 % per month. The Prophet algorithm also revealed the seasonality of the data set, and the export amounts indicate monthly oscillations. The monthly export volumes start to increase and reach their peak value in October because August is the time for the harvest of hazelnuts in Turkey.

Developing a three stage coordinated approach to enhance efficiency and reliability of virtual power plants

“…Time series forecasting is an approach based on past values of data to predict future values with the least predictable error. The Prophet application programming is better interpretable machine learning method in which non-linear trends are fit with yearly, weekly, and daily seasonality effects to fit the forecasting functions 37 . The choice of this tool lies in its adaptability for datasets that exhibit trends, seasonality, and holiday effects.…”

“…Economic Risk Mitigation using the Prophet Model in VPPs involves employing advanced forecasting techniques to predict and manage potential price volatility in the energy market. The Prophet Model, known for its robustness in time series forecasting, offers a valuable tool for the VPP operator to mitigate economic risks 37 . The integration of the Prophet Model for economic risk mitigation in the VPP is a significant step towards enhancing the economic viability and sustainability of the system.…”

The role of Turkey in the world hazelnut production and exporting

“…Exporting to these countries have constituted about 75% of the total hazelnut exports of Turkey in 2019. Aytac (2021) projected the hazelnut export quantity will be over Hazelnut export forecasts of the other leading countries in the period 1962-2025 (tonnes). Note: ARIMA (0,1,1) was used for Georgia, Azerbaijan, and Spain.…”

Box-Cox Transformation for Exponential Smoothing With Application

“…The Prophet algorithm, aided by BCT, revealed the data set's seasonality, showing monthly oscillations in export volumes. Given that Turkey's hazelnut harvest occurs in August, monthly export figures started climbing, peaking in October (Aytaç, 2021). The focal point of this paper revolves around leveraging power transformations to enhance the predictive capacity of time series models.…”