APPLICABILITY OF MACHINE LEARNING MODELS USING A NEURAL NETWORK FOR PREDICTING THE PARAMETERS OF THE DEVELOPMENT OF FOOD MARKETS
Abstract
Forecasting the parameters of the food market is a difficult task due to the volatility of demand, which depends on many factors. In this study, the authors attempted to implement a machine learning model based on multiple data on the food market. A boxed recurrent neural network was chosen as a prediction technique. The information basis was made up of data from 3,200 US cities for 2010-2012, reflecting characteristics that may be directly or indirectly related to the price of dairy products. The following models were used for data preprocessing, anomaly search, dimensionality reduction: AdaBoost, LogisticRegression, SVM. As a result of analytical actions, a neural network architecture has been formed for use in market forecasting: two competitive neural networks. First: 2 layers with Bidirectional GRU+Dropout. Second: 3 layers of LSTM+Dropout + Attention with skip-layers. Its use makes it possible to obtain a prediction model of the desired parameters with qualitative indicators of the validation sample - R^= 0.86. The applicability of the constructed machine learning model is considered on the example of classical agricultural production with the presentation of the stages of deployment of such a model at the enterprise level.
References
Abbasimehr, H., Shabani, M., & Yousefi, M. (2020). An optimized model using LSTM network for demand forecasting. Computers and Industrial Engineering, 143. https://doi.org/10.1016/j.cie.2020.106435.
Bengio, Y. (2009). Learning deep architectures for AI. Foundations and Trends in Machine Learning, 2(1), 1-27. https://doi.org/10.1561/2200000006.
Bensaadi, S., & Louchene, A. (2023). Low-cost convolutional neural network for tomato plant diseases classification. IAES International Journal of Artificial Intelligence, 12(1), 162-170. https://doi.org/10.11591/ijai.v12.i1.pp162-170.
Bernardo, José M., and Adrian F. M. Smith. (2009). Bayesian Theory. Wiley Series in Probability and Statistics. John Wiley and Sons.
Carballo, J., Handley, K., & Limão, N. (2022). Economic and policy uncertainty: Aggregate export dynamics and the value of agreements. Journal of International Economics, 139. https://doi.org/10.1016/j.jinteco.2022.103661.
Castellani, B., and Lasse G. (2021). Map of Complexity Sciences. Available online: https://www.art-sciencefactory.com/complexity-map_feb09.html (25.07.2022).
Cho, K., Merrienboer, B., Gulcehre, C., Bougares, F., Schwenk, H. & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. https://doi.org/10.3115/v1/D14-1179.
Dean, J., Corrado, G. S., Monga, R., Chen, K., Devin, M., Le, Q. V.,… Ng, A. Y. (2012). Large scale distributed deep networks. Advances in Neural Information Processing Systems, 2, 1223-1231.
Demidovskij, A. V., Babkin E. A. (2021). Integrated neurosymbolic decision support systems: problems and opportunities. Business Informatics, 15(3), 7-23. https://doi.org/10.17323/2587-814X.2021.3.7.23.
Dubovitski, A. A., Klimentova, E. A., Rogov, M. A. (2021). Regional features of innovative development and differentiation of directions of innovation policy of Russia. Journal of Process Management and New Technologies, 9(3-4), 121-132. https://doi.org/10.5937/jpmnt9-35068.
ElHihi, S. & Bengio, Y. (1995). Hierarchical recurrent neural networks for long-term dependencies. In Proc. Advances in Neural Information Processing Systems 8. Available online: http://papers.nips.cc/paper/1102-hierarchical-recurrent-neural-networks-for-long-term-dependencies. (20.07.2020)
Filali, A. E., Lahmer, E. H. B., & Filali, S. E. (2022). Machine learning techniques for supply chain management: A systematic literature review. Journal of System and Management Sciences, 12(2), 79-136. https://doi.org/10.33168/JSMS.2022.0205.
Galushkin, A. I. (1970). Multilayer pattern recognition Systems. Moscow Institute of Electronic Engineering, Moscow, Russia.
Haynes, P., & Alemna, D. (2022). A systematic literature review of the impact of complexity theory on applied economics. Economies, 10(8), https://doi.org/10.3390/economies10080192.
Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735.
Hodelin, R. S. (2022). Statistical disclosure and economic growth: What is the nexus? World Development, 160. https://doi.org/10.1016/j.worlddev.2022.106036.
Hoffmann, M. A., Lasch, R., & Meinig, J. (2022). Forecasting irregular demand using single hidden layer neural networks. Logistics Research, 15(1). https://doi.org/10.23773/2022_6.
Huang, G. -., & Chen, L. (2008). Enhanced random search based incremental extreme learning machine. Neurocomputing, 71(16-18), 3460-3468. https://doi.org/10.1016/j.neucom.2007.10.008.
Jian, L.; Xiang, H.; Le, G. (2022). LSTM-Based Attentional Embedding for English Machine Translation. Sci. Program, 10, 1-8. https://doi.org/10.1155/2022/3909726
Karminsky, A.M., Grishunin, S., Dyachkova, N. et al. (2020). The comparison of empirical methods for modeling credit ratings of industrial companies from BRICS countries. Eurasian Economic Review, 10, 333–348. https://doi.org/10.1007/s40822-019-00130-4
Karpunina, E. K., Dedov, S. V., Kholod, M. V., Ponomarev, S. V., & Gorlova, E. A. (2020). Artificial intelligence and its impact on economic security: Trends, estimates and forecasts. In Institute of Scientific Communications Conference (pp. 213-225). Springer, Cham. https://doi.org/10.1007/978-3-030-47945-9_23.
Karpunina, E. K., Kosorukova, I. V., Dubovitski, A. A., Galieva, G. F., & Chernenko, E. M. (2021). State policy of transition to society 5.0: Identification and assessment of digitalisation risks. International Journal of Public Law and Policy, 7(4), 334-350. https://doi.org/10.1504/IJPLAP.2021.118895
Khedr, A. M., Arif, I., Pravija Raj, P. V. et al. (2021). Cryptocurrency price prediction using traditional statistical and machine-learning techniques: A survey. Intelligent Systems in Accounting, Finance and Management, 28(1), 3-34. https://doi.org/10.1002/isaf.1488.
Lecun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521(7553), 436-444. https://doi.org/10.1038/nature14539.
Marston, S., Li, Z., Bandyopadhyay, S., Zhang, J., & Ghalsasi, A. (2011). Cloud computing - the business perspective. Decision Support Systems, 51(1), 176-189. https://doi.org/10.1016/j.dss.2010.12.006.
McConnell Campbell R., Brue Stanley L., Flynn Sean M. (2009). Economics: principles, problems, and policies. 18th ed. The McGraw-Hill series in economics.
McCulloch, W.S., Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5, 115–133. https://doi.org/10.1007/BF02478259
Nedeljković, M., Mutavdžić, B., Zoranović, T., & Suzić, R. (2019). Forecasting corn production indicators in the republic of Srpska. Economics of Agriculture, 66(3), 681–690. https://doi.org/10.5937/ekoPolj1903681N
Nikitin, A., Klimentova, E. & Dubovitski, A. (2020). Impact of small business innovation activity on regional economic growth in Russia. Revista Inclusiones, 7(SI), 309-321.
Panigrahi, S., & Behera, H. S. (2017). A hybrid ETS–ANN model for time series forecasting. Engineering Applications of Artificial Intelligence, 66, 49-59. https://doi.org/10.1016/j.engappai.2017.07.007.
Polyakov, V. V. (2005). Long-term forecasting of prices and demand for industrial raw materials on the world market* (questions of methodology). Economic analysis: theory and practice, 4(37), 2-6. (in Rus.).
Rashevsky, N. (1938). Mathematical biophysics. Chicago: Univer. Chicago Press.
Ropelewska, E., & Piecko, J. (2022). Discrimination of tomato seeds belonging to different cultivars using machine learning. European Food Research and Technology, 248(3), 685-705. https://doi.org/10.1007/s00217-021-03920-w.
Rosenblatt, F. (1958). The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review, 65(6), 386-408. https://doi.org/10.1037/h0042519.
Sabouri, H., & Sajadi, S. J. (2022). Image processing and area estimation of chia (salvia hispanica L.), quinoa (chenopodium quinoa willd.), and bitter melon (momordica charantia L.) leaves based on statistical and intelligent methods. Journal of Applied Research on Medicinal and Aromatic Plants, 30. https://doi.org/10.1016/j.jarmap.2022.100382
Sazu, M. H., Jahan, S. A. (2022). Impact of big data analytics on distributed manufacturing: does big data help? Journal of Process Management and New Technologies, 10(1-2), 70-81. doi: https://doi.org/10.5937/jpmnt10-37793
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15, 1929-1958.
Strategic Framework 2022-2031. (2021). Food and Agriculture Organization of the United Nations. Available online: https://www.fao.org/3/cb7099en/cb7099en.pdf (18.11.2022)
The Sustainable Development Goals Report (2020). Available online: https://unstats.un.org/sdgs/report/2020/The-Sustainable-Development-Goals-Report-2020.pdf (26.07.2022).
Turabieh, H., Mafarja, M., & Li, X. (2019). Iterated feature selection algorithms with layered recurrent neural network for software fault prediction. Expert Systems with Applications, 122, 27-42. https://doi.org/10.1016/j.eswa.2018.12.033
Verbos, P. J. (1974). In addition to regression: new tools for forecasting and analysis in behavioral sciences (PhD). Harvard University.
Vong, C. N., Conway, L. S., Feng, A., Zhou, J., Kitchen, N. R., & Sudduth, K. A. (2022). Corn emergence uniformity estimation and mapping using UAV imagery and deep learning. Computers and Electronics in Agriculture, 198. https://doi.org/10.1016/j.compag.2022.107008
Zecevic, M., Pezo, L., Bodroza-Solarov, M., Brlek, T., Krulj, J., Kojić, J., & Marić, B. (2019). A business model in agricultural production in Serbia, developing towards sustainability. Economics of Agriculture, 66(2), 437–456. https://doi.org/10.5937/ekoPolj1902437Z