Neural network approach to forecasting the cost of ferroalloy products

The article notes the increasing role of ferroalloy sub-sector in the qualitative development of metallurgy. Progress predicts of modern metallurgy are difficult in the context of increasing risks of global economic development. The high volatility of domestic producers’ prices for the main ferroalloys also has a negative impact. It is necessary to develop methodological tools for forecasting changes in market prices for metallurgical products with a high degree of accuracy. One of the important areas of application in metallurgy forecasting tools is construction of a model for forecasting the cost of ferroalloy products. It is the main purpose of the study. On the example of constructing a forecast model for changing the price of ferrosilicon, relevance of the neural network approach to forecasting the cost of ferroalloy products was substantiated. As part of the tasks of industry development, the capabilities of neural networks have been poorly studied to date. Formal description of the time series forecasting model based on neural networks is given. When constructing neural networks, any time series problem is represented as a multidimensional regression problem. The main parameters of predictive networks training are highlighted. The average price of ferrosilicon on the Russian market and the prices in the Russian regions were used as input variables. The networks that meet the qualitative criteria of forecasting models were trained. Selection of the networks was carried out taking into account the results of graphical analysis and cross-checking. A neural network model was constructed to predict the change in ferrosilicon price in the short term with high accuracy. This model can be useful in strategic decisions justifying in the activities of industry research institutes and metallurgical enterprises.

1. Galkin M.P., Brodov A.A. Modern requirements for the production of special steels and alloys. Sbornik trudov XV mezhdunarodnogo kongressa staleplavil’shchikov, 15-19 оktyabrya 2018, Moskva [Proc. of the 15th Int. Congress of Steelmakers, October 15-19, 2018, Moscow]. Moscow: Assotsiatsiya staleplavil’shchikov, 2018, pp. 23–26. (In Russ.).

2. Katunin V.V., Petrakova T.M., Ivanova I.M. Key performance indicators of the Russian steel industry in 2018. Chernaya metallurgiya. Byul. in-ta “Chermetinformatsiya”. 2019, no. 3, pp. 293–314. (In Russ.).

3. Zhuchkov V.I., Leont’ev L.I., Dashevskii V.Ya. State and development of ferroalloys metallurgy in Russia. In: Perspektivy razvitiya metallurgii i mashinostroeniya s ispol’zovaniem zavershennykh fundamental’nykh issledovanii i NIOKR: FERROSPLAVY: Trudy nauchno-prakticheskoi konferentsii s mezhdunarodnym uchastiem, 29 oktyabrya – 2 noyabrya 2018, Ekaterinburg [Prospects for the Development of Metallurgy and Mechanical Engineering using Completed Fundamental Research and R&D: FERROALLOYS: Proc. of Sci. and Pract. Conf. with Int. Participation, 29 October – 2 November, 2018, Ekaterinburg]. Ekaterinburg: Al’fa Print, 2018, pp. 12–20. (In Russ.).

4. Glaz’ev S.Yu. Ryvok v budushchee. Rossiya v novykh tekhnologicheskom i mirokhozyaistvennom ukladakh [Jerk into the future. Russia in new technological and world economic structures]. Moscow: Knizhnyi mir, 2018, 768 p. (In Russ.).

5. Perez K. Technological revolutions and the role of government in unleashing golden ages. Journal of Globalization Studies. 2012, vol. 3, no. 2, pp. 19–25.

6. Romanova O.A., Sirotin D.V. Metallurgical complex of Central Urals in the conditions of development under Industry 4.0: The road map for repositioning the complex. Studies on Russian Economic Development. 2019, vol. 30, no. 2, pp. 136–145.

7. Adno Yu.L. 2018 results: Challenges and contradictions of economic development. Chernye metally. 2019, no. 7, pp. 73–82. (In Russ.).

8. Cubadda G., Guardabascio B. Representation, estimation and forecasting of the multivariate index-augmented autoregressive model. Int. J. Forecast. 2018, vol. 35, no. 1. pp. 67–79.

9. Sirotin D.V. Spatial integration analysis of metal production markets. Izvestiya. Ferrous Metallurgy. 2017, vol. 60, no. 1, pp. 74–79. (In Russ.).

10. Pradhan R.P., Kumar R. Forecasting exchange rate in India: An application of artificial neural network model. Journal of Mathematics Research. 2010, vol. 2, no. 4, pp. 111–117.

11. Yildiz B., Yalama A.,Coskun M. Forecasting the Istanbul Stock Exchange National 100 Index using an artificial neural network. An International Journal of Science, Engineering and Technology. 2008, vol. 46, pp. 36–39.

12. Catalao J. etc. An artificial neural network approach for day-ahead electricity prices forecasting. In: 6th WSEAS Int. Conf. on Neural Networks, USA, Stevens Point. 2005, pp. 80–83.

13. Widrow B., Hoff M.E. Adaptive switching circuits. In: 1960 IRE WESCON. N.Y., 1960, pp. 96–104.

14. Minsky M.L., Papert S.S. Perceptrons: An Introduction to Comtutational Geometry. MIT Press, Cambrige, MA, 1969, 258 p.

15. McCulloch W.S., Pitts W.A. A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 1943, vol. 5, pp. 115–133.

16. Rozenblatt F. Analytical methods for analysis of neural networks. Zarubezhnaya radioelektronika. 1965, no. 5, pp. 40–45. (In Russ.).

17. Hebb D.O. The Organization of Behavior: A Neuropsychological Theory. New-York: John Wiley & Sons, Inc., 1949, 335 p.

18. Hopfield J. Neural networks and physical system with emergent collective computational properties. In: Proc. of the National Academy of Sciences of the USA. 1982, vol. 79, no. 8, pp. 2554–2558.

19. Romanova O.A., Sirotin D.V. Metodologicheskii podkhod k otsenke perepozitsionirovaniya metallurgicheskogo kompleksa regiona [Methodological approach to repositioning assessment of the region metallurgical complex]. Ekaterinburg: Institut ekonomiki UrO RAN, 2017, 91 p. (In Russ.).

20. Golovko V.A. Neironnye seti: obuchenie, organizatsiya i primenenie: kn. 4 [Neural networks: training, organization and application: Book 4]. Moscow: Radiotekhnika, 2001, 256 p. (In Russ.).

21. Graupe D. Principles of Artificial Neural Networks. 3rd Ed. World Scientific, 2013, 363 p.

22. Filatova T.V. Use of neural networks for data approximation. Vestnik Tomskogo gosudarstvennogo universiteta. 2004, no. 284, pp. 121–125. (In Russ.).