Research on World Agricultural Economy

Empirical Comparison of Facebook Prophet and Traditional Models for Tomato Price Forecasting in Greece

Eirini Kostaridou

Department of Agricultural Development, School of Agricultural Science and Forestry, Democritus University of Thrace, 68200 Orestiada, Greece

Nikolaos Siatis

Independent Researcher, 16344 Ilioupoli, Greece

George Lampiris

Independent Researcher, 16344 Ilioupoli, Greece

Eleni Zafeiriou

Department of Agricultural Development, School of Agricultural Science and Forestry, Democritus University of Thrace, 68200 Orestiada, Greece

DOI: https://doi.org/10.36956/rwae.v5i4.1295

Received: 30 July 2024 | Revised: 26 August 2024 | Accepted: 30 August 2024 | Published Online: 9 December 2024

---

Abstract

Agricultural product prices are crucial to the income and livelihoods of millions worldwide, making accurate forecasting essential for market participants. The European Union regularly reports agricultural product prices through an online databank, ensuring up-to-date price information is widely available. This study evaluates the effectiveness of Facebook Prophet, a modern forecasting tool, in predicting tomato prices in Greece from 2013 to 2024.The results show that Facebook Prophet outperforms traditional forecasting models, providing more accurate predictions with lower Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) values. Notably, the model exhibited superior performance in forecasting tomato prices over a six-month horizon compared to conventional seasonally adjusted models. This demonstrates Facebook Prophet’s potential to significantly improve decision-making in agricultural markets, offering reliable price forecasts to stakeholders such as farmers, traders, and policymakers. Furthermore, the study incorporated feedback from market participants, which provided valuable insights into market practices and conditions. This integration of practical knowledge with advanced forecasting techniques enhanced the interpretation of the results, making them more applicable to real-world scenarios. Overall, the findings suggest that Facebook Prophet holds considerable promise for future agricultural price forecasting, with potential applications across various commodities. These insights pave the way for more precise agricultural forecasts, benefiting all market participants by supporting more informed and timely decision-making.

Keywords: Tomato Price; Greece; Prophet; Market; Time Series; Forecast Models; SARIMA

---

References

[1] Alamanos, E., Bourlakis, M., Tzimitra-Kalogianni, I., 2013. Segmenting Greek tomato consumers: Policy and marketing insights towards a healthy diet. British Food Journal. 115(4), 488–507. DOI: https://doi.org/10.1108/00070701311317801

[2] Michalis, E., Giatra, C.E., Skordos, D., et al., 2023. Assessing the Different Economic Feasibility Scenarios of a Hydroponic Tomato Greenhouse Farm: A Case Study from Western Greece. Sustainability. 15(19), 14233. DOI: https://doi.org/10.3390/su151914233

[3] Dimokas, G., Tchamitchian, M., Kittas, C., 2009. Calibration and validation of a biological model to simulate the development and production of tomatoes in Mediterranean greenhouses during winter period. Biosystems Engineering. 103(2), 217–227. DOI: https://doi.org/10.1016/j.biosystemseng.2009.01.004

[4] Rezitis, A.N., Pachis, D.N., 2016. Investigating the Price Transmission Mechanisms of Greek Fresh Potatoes, Tomatoes and Cucumbers Markets. Journal of Agricultural and Food Industrial Organization. 14(1), 91–108. DOI: https://doi.org/10.1515/jafio-2015-0004

[5] Sun, F., Meng, X., Zhang, Y., et al., 2023. Agricultural Product Price Forecasting Methods: A Review. Agriculture. 13(9), 1671. DOI: https://doi.org/10.3390/agriculture13091671

[6] Girapunthong, N., Vansickle, J.J., Renwick, A., 2023. Price Asymmetry in the United States Fresh Tomato Market. Journal of Food Distribution Research. 34(3), 51–59.

[7] Anastasiadis, F., Apostolidou, I., Michailidis, A., 2020. Mapping Sustainable Tomato Supply Chain in Greece: A Framework for Research. Foods. 9(5), 539. DOI: https://doi.org/10.3390/foods9050539

[8] Puria, P., Singh, K.M., Parihar, L., 2023. Decomposition and forecasting of tomato price in Bhopal district, Madhya Pradesh. Agricultural Economics Research Review. 36, 111–122. DOI: https://doi.org/10.5958/0974-0279.2023.00020.4

[9] Epperson, J.E., Fletcher, S.M., Collins, M.F., 1987. Price forecasting and trigger price probability estimation. International Journal of Forecasting. 3(2), 281–287.

[10] De Gooijer, J.G., Hyndman, R.J., 2006. 25 years of time series forecasting. International Journal of Forecasting. 22(3), 443–473. DOI: https://doi.org/10.1016/j.ijforecast.2006.01.001

[11] Giri, A., Giri, V.R., 2024. Forecasting cauliflower prices in Nepal: A comparative analysis using seasonal time series and nonlinear models. Cogent Food and Agriculture. 10(1), 2340155. DOI: https://doi.org/10.1080/23311932.2024.2340155

[12] Majhi, S.K., Bano, R., Srichandan, S.K., et al., 2023. Food price index prediction using time series models: A study of cereals, millets, and pulses. pp. 1–26. DOI: https://doi.org/10.21203/rs.3.rs-2999898/v1

[13] Jayapal, S., Muntean, C.H., 2023. Food Demand Prediction using Statistical and Machine Learning Models MSc Research Project Data Analytics. pp. 1–25. Available from: https://norma.ncirl.ie/6594/1/sasikumarjayapal.pdf

[14] European Commission, 2024. Tomato Trade Dashboard. Available from: https://agridata.ec.europa.eu/extensions/DashboardTomato/TomatoTrade.html

[15] Falatouri, T., Darbanian, F., Brandtner, P., et al., 2022. Predictive analytics for demand forecasting – A comparison of SARIMA and LSTM in retail SCM. Procedia Computer Science. 200, 993–1003. DOI: https://doi.org/10.1016/j.procs.2022.01.298

[16] Chatfield, C., 2003. The Analysis of Time Series. Chapman and Hall/CRC: London, UK. DOI: https://doi.org/10.4324/9780203491683.

[17] Damrongkulkamjorn, P., Churueang, P., 2023. Monthly energy forecasting using decomposition method with application of seasonal ARIMA. In Proceedings of the 2005 International Power Engineering Conference; Singapore, 29 November–2 December 2005.

[18] Adanacioglu, H., Yercan, M., 2016. An analysis of tomato prices at wholesale level in Turkey: An application of SARIMA model. Available from: www.custoseagronegocioonline.com.br

[19] Johnston, F.R., Boyland, J.E., Meadows, M., Shale, E., 1999. Some properties of a simple moving average when applied to forecasting a time series. Journal of the Operational Research Society. 50(12), 1267–1271. DOI: https://doi.org/10.1057/palgrave.jors.2600823

[20] Akpinar, M., Yumusak, N., 2016. Year ahead demand forecast of city natural gas using seasonal time series methods. Energies. 9(9), 727. DOI: https://doi.org/10.3390/en9090727

[21] Gómez, V., Maravall, A., 1997. Programs TRAMO and SEATS: instructions for the user. Banco de España.

[22] Theodosiou, M., 2011. Forecasting monthly and quarterly time series using STL decomposition. International Journal of Forecasting. 27(4), 1178–1195. DOI: https://doi.org/10.1016/j.ijforecast.2010.11.002

[23] Ouyang, Z., Ravier, P., Jabloun, M., 2021. STL Decomposition of Time Series Can Benefit Forecasting Done by Statistical Methods but Not by Machine Learning Ones. Engineering Proceedings. 5(1), 42. DOI: https://doi.org/10.3390/engproc2021005042

[24] Cleveland, W.S., 1979. Robust Locally Weighted Regression and Smoothing Scatterplots. Journal of the American Statistical Association. 74(368), 829–836. DOI: https://doi.org/10.1080/01621459.1979.10481038

[25] Hyndman, R.J., Athanasopoulos, G., 2021. Forecasting: Principles & Practice. 3rd ed. Otexts: Melbourne, Australia.

[26] Taylor, S.J., Letham, B., 2023. Forecasting at Scale. DOI: https://doi.org/10.7287/peerj.preprints.3190v2

[27] Blanc, S.M., Setzer, T., 2016. When to choose the simple average in forecast combination. Journal of Business Research. 69(10), 3951–3962. DOI: https://doi.org/10.1016/j.jbusres.2016.05.013

[28] Wichern, D.W., Makridakis, S., Wheelwright, S.C., 1979. Forecasting: Methods and Applications. Journal of the American Statistical Association. 74(367), 733. DOI: https://doi.org/10.2307/2287014