+7 925 966 4690, 9am6pm (GMT+3), Monday – Friday
ИД «Финансы и кредит»

JOURNALS

  

FOR AUTHORS

  

SUBSCRIBE

    
Financial Analytics: Science and Experience
 

The neural network analysis of trends in innovative activity of the regions of the Russian Federation

Vol. 8, Iss. 29, AUGUST 2015

PDF  Article PDF Version

Received: 1 June 2015

Accepted: 16 June 2015

Available online: 27 August 2015

Subject Heading: INNOVATION AND INVESTMENT

JEL Classification: 

Pages: 56-68

Perova V.I. Lobachevsky State University of Nizhny Novgorod, Nizhny Novgorod, Russian Federation
perova_vi@mail.ru

Goncharova D.G. Lobachevsky State University of Nizhny Novgorod, Nizhny Novgorod, Russian Federation
mmes@mm.unn.ru

Importance The Russian economy undergoes the transition from its export and raw materials focus to innovation. Scientific and technological achievements should contribute to a higher standard of living of population and competitiveness of the country and its regions.
     Objectives The article aims at analyzing trends in innovative activity of the Russian regions. For this, we examined data of the Federal State Statistics Service on economic and social development of the Russian regions.
     Methods We examined the trends in innovative activities of the regions within the period of 2009 to 2013 using the neural network modeling and such innovation indicators as headcount of staff who deal with developments (technologies), the number of patent applications concerning inventions, useful models; the number of patents issued for inventions, useful models; current internal costs for fundamental, applied research and development. The research uses the Kohonen self-organizing maps via MATLAB, i.e. self-trained neural networks.
     Results The research allows identifying the specifics of trends in innovative activities in the Russian regions and determining innovative development centers. The regions get split into five groups (clusters) in terms of their innovative activity. During the period, each cluster formed a nucleus with the constant content. The highest figures are seen in the nucleus of the cluster, which includes the regions with significantly lower indicators of innovative activity as compared with the average indicators throughout Russia.
     Conclusions and Relevance The results of the research indicate the uneven nature of innovative activity in the Russian regions. To modernize the Russian economy successfully, it is necessary to undertake a set of measures stimulating innovative activity in every region, rather than in the most developed ones.

Keywords: innovative, region, neural network analysis, self-organizing map, Kohonen, MATLAB

References:

  1. Khaikin S. Neironnye seti: polnyi kurs [Neural networks: a complete course]. Moscow, Vil'yams Publ., 2006, 1104 p.
  2. Wong T.C., Wong S.Y., Chin K.S. A Neural Network-Based Approach of Quantifying Relative Importance Among Various Determinants Toward Organizational Innovation. Expert Systems with Applications, 2011, vol. 38, no. 10, pp. 13064–13072. Available at: Link.
  3. Harish Naira, Anand Kumar, Osman Ahmed. Neural Network Modelling, Simulation and Prediction of Innovation Growth in United Arab Emirates (UAE). Procedia Computer Science, 2014, vol. 36, pp. 269–275. Available at: Link.
  4. Wang Tai-Yue, Shih-Chien Chien. Forecasting Innovation Performance via Neural Networks – a Case of Taiwanese Manufacturing Industry. Technovation, 2006, vol. 26, iss. 5-6, pp. 635–643. Available at: Link.
  5. Giacomo di Tollo, Stoyan Tanev, De March Davide, Zheng Ma. Neural Networks to Model the Innovativeness Perception of Co-Creative Firms. Expert Systems with Applications, 2012, vol. 39, iss. 16, pp. 12719–12726. Available at: Link.
  6. Giacomo di Tollo, Stoyan Tanev, Kassis Mohamed Slim, Davide De March. Determining the Relationship between Co-Creation and Innovation by Neural Networks. Complexity in Economics: Cutting Edge Research, 2014, pp. 49–62. Available at: Link.
  7. Regional Innovation Scoreboard 2014. European Commission, 2014, 79 p. Available at: Link.
  8. Hajeka P., Henriquesb R., Hajkovac V. Visualising Components of Regional Innovation Systems Using Self-Organizing Maps – Evidence from European Regions. Technological Forecasting and Social Change, 2014, vol. 84, pp. 197–214. Available at: Link.
  9. Perova V.I. Neironnye seti. Chast’ 2 [Neural networks. Part 2]. Nizhny Novgorod, State University of Nizhny Novgorod Publ., 2012, 111 р.
  10. Perova V.I. Neironnye seti v ekonomicheskikh prilozheniyakh. V kn.: Ch. 2. Neironnye seti, obuchaemye bez uchitelya [Neural networks in economic applications. In: Part 2. Self-trained neural networks]. Nizhny Novgorod, State University of Nizhny Novgorod Publ., 2012, 135 p.
  11. Kuznetsov Yu.A., Perova V.I. Ispol'zovanie neirosetevogo modelirovaniya v analize deyatel'nosti krupneishikh kompanii Rossiiskoi Federatsii [Using a neural network model in analyzing the activity of the largest companies of the Russian Federation]. Ekonomicheskii analiz: teoriya i praktika = Economic Analysis: Theory and Practice, 2010, no. 31, pp. 32–34.
  12. Kuznetsov Yu.A., Perova V.I., Vorob'eva E.V. Neirosetevoe modelirovanie finansovo-ekonomicheskoi deyatel'nosti krupneishikh kompanii Povolzh'ya [Neural network modeling of financial and economic activity of the largest companies of the Volga region]. Ekonomicheskii analiz: teoriya i praktika = Economic Analysis: Theory and Practice, 2011, no. 35, pp. 25–36.
  13. Kuznetsov Yu.A., Perova V.I., Eivazova E.N. Neirosetevoe modelirovanie dinamiki innovatsionnogo razvitiya regionov Rossiiskoi Federatsii [Neural network modeling of innovative development dynamics in the regions of the Russian Federation]. Regional'naya ekonomika: teoriya i praktika = Regional Economics: Theory and Practice, 2014, no. 4, pp. 18–28.
  14. Ballabio D., Vasighi M. A MATLAB Toolbox for Self Organizing Maps and Supervised Neural Network Learning Strategies. Chemometrics and Intelligent Laboratory Systems, 2012, vol. 118, pp. 24–32. Available at: Link.
  15. Ghaseminezhad M.H., Karami A. A Novel Self-Organizing Map (SOM) Neural Network for Discrete Groups of Data Clustering. Applied Soft Computing, 2011, vol. 11, no. 4, pp. 3771–3778. Available at: Link.
  16. Chislennost' personala, zanyatogo nauchnymi issledovaniyami i razrabotkami (po sub"ektam Rossiiskoi Federatsii) [The number of personnel charged with scientific researches and development (per region of the Russian Federation)]. Available at: Link. (In Russ.)
  17. Postuplenie patentnykh zayavok i vydacha okhrannykh dokumentov v Rossii (po sub"ektam Rossiiskoi Federatsii) [Receipt of patent applications and issue of protection documents in Russia (per region of the Russian Federation)]. Available at: Link. (In Russ.)
  18. Vnutrennie tekushchie zatraty na nauchnye issledovaniya i razrabotki po vidam rabot (po sub"ektam Rossiiskoi Federatsii) [Internal current costs for scientific researches and development by type of work (per region of the Russian Federation)]. Available at: Link. (In Russ.)

View all articles of issue

 

ISSN 2311-8768 (Online)
ISSN 2073-4484 (Print)

Journal current issue

Vol. 17, Iss. 1
March 2024

Archive