Forecasting Iran’s Saffron Export by Comparison of Machine Learning Algorithms
Subject Areas : Decision-making
علیرضا امیرتیموری
1
,
منصور صوفی
2
,
مهدی همایونفر
3
,
مهدی فدایی
4
1 - استاد تمام، گروه ریاضی، واحد رشت، دانشگاه آزاد اسلامی، رشت، ایران.
2 - استادیار، گروه مدیریت صنعتی، واحدرشت، دانشگاه آزاداسلامی، رشت، ایران
3 - استادیار، گروه مدیریت صنعتی، واحدرشت، دانشگاه آزاداسلامی، رشت، ایران
4 - استادیار، گروه مدیریت صنعتی، واحد رشت، دانشگاه آزاد اسلامی، رشت، ایران
Keywords: Neural network, Prediction, deep learning, Saffron Exports, Gradient Boost Tree,
Abstract :
Imports and exports play an integral role in the economic growth of all countries. Therefore, selecting the right products can enhance a country's competitiveness in global trade. Saffron stands out as one of Iran's most vital and unique non-oil products for export. The objective of this study was to predict saffron exports using three data mining algorithms and determine the most suitable algorithm for forecasting. The sample period for the forecasting models encompasses saffron export data from Iran for the years 2012 to 2019, gathered from the Iran Saffron Association. Following the data preparation steps, saffron export was forecasted using three data mining algorithms: artificial neural network, deep learning, and gradient boost tree. The validity of the models plays a crucial role in selecting the best forecasting model. The predictive validity of the three designed models was evaluated using the absolute error (artificial neural network = 0.036, deep learning network = 0.031, and gradient boost tree = 0.047), R-squared (artificial neural network = 0.045, deep learning network = 0.044, and gradient boost tree = 0.073), and correlation coefficients (artificial neural network = 0.95, deep learning network = 0.98, and gradient boost tree = 0.97). Based on the findings, all models demonstrate high accuracy, with very low prediction errors that are closely matched. However, the deep learning network exhibits a slightly lower, albeit statistically insignificant, error. These results can be valuable for enhancing the precision of saffron export planning.
Abasi, S., Mohammadi, H. & Dini, A. (2012). The prediction of the price of oil seeds in Iran, case study of corn and soya. Journal of Economic Research and Policy, 17, 41-53. [In Persian].
Akbari, A., Sharei Hadadzade, M., & Mehrabi Basharabadi, H. (2013). The prediction of Iran's date exports through econometric and artificial intelligence methods. Journal of Agricultural Economics Researches, 5(3), 99-120. [In Persian].
Amirzade Moradabadi, S. (2014). The prediction of wheat price in Iran. National conference on electronic achievements in engineering and basic sciences. Tehran.https://www.civilica.com/Paper-AEBSCONF01-AEBSCONF01_208.htm.l. [In Persian].
Barimnejad, V., & Bakshelu, M. (2017). The prediction of tomato's price, comparison of neural network integrated methods, Self-regression and ARIMA. Agricultural Economics and Development, 83, 89-103. [In Persian].
Breiman, L. (1997). Arcing the Edge. Technical Report 486. Statistics Department, University of California, Berkeley.
Devi, M., Kumar, J., Malik, D.P., & Mishra, P. (2021). Forecasting of wheat production in Haryana using a hybrid time series model. Journal of Agriculture and Food Research, 5, 100175.
Farajzade, Z., & Shahvali O. (2018). The prediction of corps price (Case study: Cotton and rice and saffron). Journal of Agricultural Economics and Development, 17, 43-72. [In Persian].
Fazlollahi, E. & Fatahi, A. (2014). The determination of optimum pattern for prediction of the price of rice in Iran. The country's national rice congress, Sari, instituted of Genetics and Biotechnology and agriculture of Tabarestan. Faculty of Agricultural Sciences and Natural Resources of Sari. [In Persian].
Garcia, R., Telea, A.C., Da Silva, B.C., Torresen, J. & Dihlcomba, J.L. (2018). A task-and-technique centered survey on visual analytics for deep learning model engineering. Computers & Graphics, https://doi.org/10.1016/j.cag.2018.09.018.
Shafieyan, M., Homayounfar, M., & Fadaei, M. (2017). Identification of strategies for sustainable development of rice production in Guilan province using SWOT analysis. International Journal of Agricultural Management and Development., 7, 141-153
Karbasi A., & Akbarzade J. (2008). Estimation of export supply and demand functions for Iran saffron by simultaneous equations system. Agricultural Economics and Development, 16, 33-52. [In Persian].
Kourentzes, N., Barrow, D., & Petropoulos, F. (2019). Another look at forecast selection and combination: Evidence from forecast pooling. International Journal of Production Economics, 209, 226–235.
Kouzegaran, S., Mousavi Baygi, M., Babaeian, I., & Khashei-Siuki, A. (2020). Future projection of the effects of climate change on saffron yield and spatial-temporal distribution of cultivation by incorporating the effect of extreme climate indices. Theoretical and Applied Climatology, 141, 1109–1118.
Kuchakzade, S., Vahid F., & Kuchakzade, A. (2013). Modeling and prediction of saffron exports, National Congress of Scientific and Research Achievements about Saffron, TorbatHeidarie University. [In Persian].
Kyriazi, F., Thomakos, D.D., & Guerard, J.B. (2019). Adaptive learning forecasting with applications in forecasting agricultural prices. International Journal of Forecasting, 35 (4), 1356-1369.
Li, J., Li, G., Liu, M., Zhu, X., & Wei, L. (2021). A novel text-based framework for forecasting agricultural futures using massive online news headlines. International Journal of Forecasting, (In press)
Luo, J., Klein, T., Ji, Q., & Hou, C. (2019). Forecasting realized volatility of agricultural futures with infinite Hidden Markov HAR models. International Journal of Forecasting, (in press). http://dx.doi.org/10.
1016/j.ijforecast.2019.08.007
Mendes-Moreira, J., Soares, C., Jorge, A.M., & De Sousa, J.F. (2012). Ensemble approaches for regression: A survey. ACM Computing Surveys, 45(1), 10.
Ministry of Agriculture Jihad. (2018). The MAJ database. Available at Web sitehttp://www.maj.ir.(Verified 5 December2018).
Moghadasi, R., Khaligh Khiav, P. & Kavusi Klashami, M. (2011). The prediction of Iran's non-oil exports, regression and artificial neural network patterns. Economic Modeling, 5,13, 67-90.
Mohamadzadeh, S.H., Karbasi, A. & Kashefi, M. (2016). Comparison of logit, probit, and Tobi in the factors affecting the adoption of saffron insurance Case study: Qaen City. Saffron agronomy and technology, 4(3), 239-254. [In Persian].
Nasabian, S., & Ghashghaei, S.A. (2017). The prediction of the global price of wheat and saving currency in Iran, financial economy. Journal of Financial Economics, 41(11), 225-242.
Nazemi, A. (2016). Investigating Factors Affecting the Export of Pistachio, Saffron and Solutions to Improve Exports. Modern Applied Science, 10(12), 229-236. [In Persian].
Nazlioglu, S., & Soytas, U. (2012). Oil price, agricultural com- modify prices, and the dollar: A panel cointegration and causality analysis. Energy Economics, 34(4), 1098–1104
Omidi, M., & Omidi, H. (2016). The investigation and prediction of the exports of saffron, through gray systems and artificial neural network, 2nd National Congress on Agricultural Science and Natural Resources Development [In Persian].
Ramezani, M., Dourandish, A., & Davari Torshizi, M. (2018). Economic Analysis and Investigation of Factors Affecting the Inefficiency of Saffron Fields in Gonabad. Journal of Saffron Research, 6, 191-202. [In Persian].
Riahi Modavar, H., Khashei-Siuki, A., & Seifi, A. (2017). Accuracy and uncertainty analysis of artificial neural network in predicting saffron yield in the south Khorasan province based on meteorological data. Journal of Saffron Agronomy and Technology, 5 (3), 255-271.
Sabu, K.M., & Kumar, T.K.M. (2020). Predictive analytics in Agriculture: Forecasting prices of Arecanuts in Kerala, Procedia Computer Science, 171, 699-708.
Salari, A., Bashiri, M., & Marusi, A. (2017). The prediction of the performance of saffron through data mining methods and determination of effective climate parameters on it in Khorasan Razavi. Journal of Saffron Research, 5(1), 1-17. [In Persian].
Sanainejad, S.H., Farsi, M., Hasheminiya, S.M.H., & Seied, N. (2007). The investigation and performance prediction of saffron in south khorasan, by climatic factors through practical relationships. 5th Festival of Talaye Sorkh, South Khorasan. [In Persian].
Shaygan, M.A., Mohamadi, H., & Musavi, S.N. (2007). The prediction of the imports rate of rice and corn through artificial neural networks. Journal of Economic Research and Policy, 15 (44), 83-100. [In Persian].
Tashakkori, F., & Torkashvand, A.M. (2020). Comparison of Different Methods of Estimating Saffron Yield Based on Soil Properties in Golestan Province. Communications in Soil Science and Plant Analysis, 51(4), 1-13.
Wang, J., Li, Xiang, H., Tao, & Wang, S. (2018). A semi-heterogeneous approach to combining crude oil price forecasts. Information Sciences, 460, 279–292
Wang, J., Wang, Z., Li, X., & Zhou, H. (2019). Artificial bee colony-based combination approach to forecasting agricultural commodity prices. International Journal of Forecasting, DOI: 10.1016/j.ijforecast.2019.08.006
Zarei, G. & Jafari, A.M. (2015). The Role of Import and Export of Major Crop Productions in Virtual Water Trade and Water Footprint in the Agricultural Sector of Iran. Iranian Journal of Irrigation and Drainage, 9 (5), 784-797.
Zhang, Y. (2019). Application of improved BP neural network based on e-commerce supply chain network data in the forecast of aquatic product export volume. Cognitive Systems Research, 57, 228-235.