<<<  Back

2017, № 69

UDC: 330.45
GSNTI: 28.17.19

Theory and practice of modeling, analysis and predicting evolutionary socio-economic systems by nonlinear dynamics methods

At the turn of XX and XXI centuries the fundamental concepts has changed in the scientific methods of analysis and forecasting of dynamics of stochastic systems - replacement for linear (continuous) paradigm came the nonlinear (discrete) paradigm, which distinguishes "long-term memory", fractals, chaos, based on the disobedience of many social and economic processes (the dynamics of productivity, in particular) of classical statistics and the normal law. According to the definition of fractal geometry fractal is a structure consisting of such parts that are in some way similar to the whole and to each other (the principle of self-similarity). Synergy deals with the cooperative interaction of many subsystems, demonstrating as the self-organization of the overall economic system. Non-linear paradigm principles implementation in process modeling, analysis and prediction are realiuzable by the researchers through the use of methods of nonlinear dynamics - the fractal analysis, phase analysis, artificial neural networks, fuzzy systems and genetic algorithms. The main idea that is stated in the economic synergy is that fundamentally there is no such evolving economic system, which always would remain stable. It is known that methods that comprise the instrumentation of a classical prediction, fall into three large groups: statistical, causal, and combination. The process of building a prognostic model typically involves the use of refinement methods of prediction in which a predictive model "is learnt" in different methods. Moreover, the synergetic algorithm and the forecast must be internally consistent with the structure of its parts, which is shown by the presented work of the algorithm of the linear cellular automaton. We use models of linear cellular automation - discrete dynamic systems with distributed control as tools for the analysis and forecasting of socio-economic indicators, including productivity of winter crops.
Keywords: Forecast, long-term memory, linear cellular automaton, term set, fuzzy sets, validation
DOI: 10.21515/1999-1703-69-30-35

References:

1. Кумратова, А. М. Предпрогнозный фазовый анализ эволюционного развития элементов финансового рынка / А. М. Кумратова, Е. В. Попова, И. С. Мусатов и др. // Политематический сетевой электронный научный журнал КубГАУ (Научный журнал КубГАУ) [Электронный ресурс]. - Краснодар: КубГАУ, 2017. - № 04 (128). - С. 772-785. - IDA [article ID]: 1281704054. - Режим доступа: http://ej.kub-agro.ru/2017/04/pdf/54.pdf, 0,875 у. п. л.
2. Кумратова, А. М. Оценка и управление рисками: анализ временных рядов методами нелинейной динамики / А. М. Кумратова, Е. В. Попова. - Краснодар: КубГАУ, 2014. - 212 с.
3. Пономарева, Д. Н. Качественные выводы о предпосылках надежного прогнозирования на базе фазовых портретов / Д. Н. Пономарева, А. М. Кумратова, Е. В. Попова // В сб.: Информационное общество: современное состояние и перспективы развития. - Сб. матер. IX студенческого международного форума. - 2017. - С. 213-215.
4. Гилязова, А. М. Предпрогнозный анализ обменного курса валют / А. М. Гилязова, Э. А. Гагай, А. М. Кумратова // В сб.: «Информационное общество: современное состояние и перспективы развития». - Сб. матер. VIII международного форума. 2017. - С. 18-21.

Authors:

1. Kumratova Alphira Menligulovna, PhD in economics, associate professor, Federal State Budgetary Educational Institution of Higher Education “I.T. Trubilin Kuban State Agrarian University”.