Neural network forecasting price dynamics for agricultural products

The agrarian industry occupies a special place in the economy of any country. The specificity of the role of the agrarian industry is due, first of all, to the production of food products, as the basis for the life of people and the reproduction of the labor force, as well as the production of raw materials for many other industries. Therefore, the level of development of agriculture largely determines the level of economic security of the country. In modern conditions, the development of agro-industrial production entirely depends on the acceleration of scientific and technological progress, the use of the achievements of science and technology. However, strengthening the innovation orientation is possible only with the further development and improvement of scientific research and their practical implementation, both in agricultural production and in the processes of its management. The most important function of management is the development of scientifically based forecasts, which in the context of growing market uncertainty becomes a difficult task. Under these conditions, classical forecasting methods become of little use. In conditions of increased uncertainty, it is necessary to use special methods of analysis and forecasting. The use of neural network technologies can be used as an alternative to classical forecasting methods. Mastering these tools is an urgent task of agricultural science and practice. The object of research in the article is the beef meat market in Russia. The subject of the research is the dynamics of prices and the price forecast in the beef markets

Keywords: time series, forecast, neural networks, agricultural production

References

  1. Kallan R. Osnovnie kontseptsii neyronnikh setey: per. s angl./R. Kallan. – M.: Izdat. Dom «Vilyams», 2001 — 287 s.
  2. Lyuger F. Iskusstvenniy intellekt: strategii i metodi resheniya slozhnikh problem, 4-e izdanie.: Per. s angl. – M.: «Vilyams», 2003 — 864 s.
  3. Murray A. Applications of Neural Networks/A. Murray. — Springer, 2014. — 340 p.
  4. Rassel S., Norvig P. Iskusstvenniy intellekt. Sovremenniy podkhod. — M.: Izda-vo «Vilyams», 2006 — 1408 s.
  5. Khaykin S. Neyronnie seti. Polniy kurs. — 2-e izd./Per. S angl. — M.: Izdatelskiy dom Vilyams, 2008, 1103 s.
  6. S. YU. Gorodetskiy, V. A. Grishagin. Nelineynoe programirovanie i mnogoekstremalnaya optimizatsiya. — Nizhniy Novgorod: Izdatelstvo Nizhegorodskovo Universiteta, 2007. —489 s.
  7. Yasnitskiy P.N. Intellektualnie sistemi. M. Laboratoriya znaniy. 2016. 221 s.
  8. https://mcx.gov.ru/ministry/departments/departament-ekonomiki-investitsiy-i‑regulirovaniya-rynkov/industry-information/info-monitoring-rynkov-apk/(data obrashcheniya 23.02.2021)
  9. Rudkovskaya D. Neyronnie seti, genetitcheskie algoritmi I netchetkie sistemi. — M.: Goryatchaya liniya — Telekom, 2004. — 452 s.
  10. Dzhoshi, Pratik. Iskusstvenniy intellect s primerami na Python: per. s angl. — SPb. OOO «Dialektika», — 2019 . — 448 s. — Parap tit angl.
  11. Joshi Prateek. Artificial Intelligence with Python. — Birmingham — Mumbai.: Packt Publishing, 2017. — 521 p.

Authors