Development a methodology for a comprehensive assessment and forecasting of the region's innovative development using a self-organizing neural network

The purpose of this article is to study the opportunities that arise from the use of neural network data processing technologies for a comprehensive assessment and forecasting of the innovative development of regions. The article substantiates the advantages of modeling using a neural network approach, which implies the use of neural networks that can learn and generalize accumulated knowledge to solve problems of classification, identification and forecasting. This ultimately allows you to combine the mechanisms of regulation and self-organization in the management of regional innovation systems. The author proposed the use of self-organizing (evolving) neural networks. Using the principles of self-organization allows us to synthesize multilayer neural networks on an incomplete, non-representative training set. As a result of the study, the general concept of the neural network was implemented to solve prognostic tasks in the regional innovation system, which is the basis for the development of systems for managing the economic growth of the constituent entities of the Russian Federation due to the innovative factors

Keywords: innovation, control algorithm, assessment methodology, neural network approach, machine learning

References

  1. Yu. A. Alekseeva. Ocenka finansovogo sostoyaniya i prognozirovanie bankrotstva predpriyatiya. Avtoreferat diss. M., 2011
  2. T. K. Bogdanova, A. V. Baklakova., Instrumental'nye sredstva prognozirovaniya veroyatnosti bankrotstva aviapredpriyatij//Biznes-informatika. 2008. № 1. S. 45-61.
  3. L. A. Gamidullaeva. Teoretiko-metodologicheskie osnovy upravleniya i prognozirovaniya razvitiya innovacionnoj sistemy regiona: dis. … d-ra ekon. nauk. SPb.: SPbGU, 2019.
  4. L. A. Gamidullaeva. Vozmozhnosti neoinstitucional'nogo sistemno-sinergeticheskogo podhoda k issledovaniyu innovacionnyh sistem//Zhurnal ekonomicheskoj teorii. 2015. № 4. S. 142-154.
  5. L. A. Gamidullaeva. Ot shumpeterianskoj teorii sozidatel'nogo razrusheniya k sinergeticheskoj paradigme innovacij//Zhurnal ekonomicheskoj teorii. 2019. T. 16. № 3. S. 498-512.
  6. L. A. Gamidullaeva. Instituty v razvitii innovacionnyh sistem//Journal of Economic Regulation (Voprosy regulirovaniya ekonomiki). 2016. T. 7. № 1. S. 93-103.
  7. N. A. Nikiforova, E. V. Doncov. Primenenie nejrosetevogo modelirovaniya dlya prognozirovaniya finansovogo sostoyaniya predpriyatiya//Upravlencheskij uchet. 2011. № 4. S. 36-46.
  8. E. M. Korostyshevskaya, V. A. Plotnikov, A. V. Prolubnikov, M. V. Rukinov. Social'naya komponenta gosudarstvennoj regional'noj politiki i ee rol' v obespechenii ustojchivogo razvitiya i ekonomicheskoj bezopasnosti//Izvestiya Sankt-Peterburgskogo gosudarstvennogo ekonomicheskogo universiteta. 2018. № 6 (114). S. 120-126.
  9. S. Osovskij. Nejronnye seti dlya obrabotki informacii. M.: Goryachaya liniya Telekom, 2016. 448 s.
  10. P. N. Panfilov. Vvedenie v nejronnye seti//Sovremennyj trejding. 2001. № 2. S. 12-17.
  11. Plas Dzh. Vander. Python dlya slozhnyh zadach: nauka o dannyh i mashinnoe obuchenie. SPb.: Piter, 2018. 576 s.
  12. G. Z. Rahimkulova. Analiticheskie i nejrokomp'yuternye modeli ocenki kreditosposobnosti predpriyatiya//Audit i finansovyj analiz. 2007. № 3. S. 196-198.
  13. S. Rashka. Python i mashinnoe obuchenie. M.: DMK Press, 2017. 418 s.
  14. A. V. Romanovskij. O primenenii iskusstvennyh nejronnyh setej dlya prognozirovaniya finansovyh pokazatelej predpriyatiya//Audit i finansovyj analiz. 2013. № 2. S. 363-370.
  15. I. S. Svetun'kov. Kratkosrochnoe prognozirovanie social'no-ekonomicheskih processov s ispol'zovaniem modeli s korrekciej//Bіznes Іnform. 2011. T. 1. № 5. S. 109-112.
  16. P. Flah. Mashinnoe obuchenie. Nauka i iskusstvo postroeniya algoritmov, kotorye izvlekayut znaniya iz dannyh. M.: DMK Press, 2015. 400 s.
  17. E. V. Balatskii, N. A. Ekimova, M. A. Yurevich. Short-Term Inflation Projection Based on Marker Models//Stud. Russ. Econ. Dev. 30, 498-506, 2019.
  18. J. Carpenter, M. Kenward. Multiple Imputation and its Application. Wiley, 2013. 364 p.
  19. E. A. Fedorova, E. V. Gilenko, S. E. Dovzhenko. Models for bankruptcy forecasting: Case study of Russian enterprises//Stud. Russ. Econ. Dev. 24, 159-164, 2013.
  20. V. I. Gorbachenko, O. Yu. Kuznetsova, D. S. Silnov. Investigation of Neural and Fuzzy Neural Networks for Diagnosis of Endogenous Intoxication Syndrome in Patients with Chronic Renal Failure//International Journal of Applied Engineering Research, 2016, Vol. 11. № 7. P. 5156-5162.
  21. J. C. Neves, A. Vieira. Improving bankruptcy prediction with hidden layer learning vector quantization//European Accounting Review. 2006. Vol. 15. № 2. P. 253-271.
  22. K. Schirmer, M. Kuehn. Fact Extraction from Financial News. In Proceedings of the Second International Conference on Artificial Intelligence Applications on Wall Street. New York, NY, April, 1993. Gaithersburg, MD: Software Engineering Press.
  23. M. Tkáč, R. Verner. Artificial neural networks in business: Two decades of research//Applied Soft Computing. Vol. 38. 2016. P. 788-804.

Authors