Mathematical modeling and neural network prediction of the structure and dynamics of human capital of the Russian Federation | Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie, vychislitelnaja tehnika i informatika – Tomsk State University Journal of Control and Computer Science. 2020. № 53. DOI: 10.17223/19988605/53/2

Mathematical modeling and neural network prediction of the structure and dynamics of human capital of the Russian Federation

The problem of mathematical modeling and forecasting the values, structure and dynamics of human capital using the neural network algorithm is solved. The paper is used an integrated economic and mathematical model of human capital, which includes quantitative and qualitative characteristics. A quantitative characteristic is the distribution of demographic elements by ages. Qualitative characteristics include such components of human capital as educational capital, health, and cultural capital. The forecast of the dynamics of human capital is based on the two-dimensional transport equation, which takes into account the time and age of demographic elements, as well as the forecast values of the volume of budgetary and private investments in human capital, built on a multilayer neural network model. The calculations were made on the basis of statistical information for the Russian Federation, including data on demographics, volumes of investments in human capital of the economic system of the Russian Federation, as well as indicators of directions of socio-economic development. Volumes of investments in human capital determine budget expenditures and private expenses of citizens. To forecast the dynamics of human capital, the values of the volumes of investments in it are used, the forecast of which, in turn, is built using the neural network model. The period 2000-2018 was chosen as the studied one. The adaptive neural network modeling algorithm used in the work made it possible to construct a forecast of human capital of the Russian Federation until 2025. The neural network model used in this study is a multilayer fully connected perceptron with a sigmoidal logistic activation function. Neural network modeling of investment values has been shown to be effective. The constructed forecasts satisfy the given accuracy. So, the deviation of the model values of investments from the actual in the components of human capital for the period of retrospective forecast 2015-2018. amounted to 1.6%. Calculations of the human capital of the Russian Federation in the interval 2000-2018 showed that it began to increase since 2005 with an annual average rate of 5.5%. Since that moment in time, the average annual investment rate in the components of human capital has increased: health - 3.7%, education - 3.8%, culture - 2.6%. In the future, until 2025, a slowdown in the growth of human capital of the Russian Federation to 1.0% per year is forecasted. The proposed methodology for calculating the magnitude and dynamics of human capital can be used to assess and compare the socio-economic situation of the Russian Federation regions.

Download file
Counter downloads: 166

Keywords

mathematical modeling, forecasting, human capital, neural network algorithm

Authors

NameOrganizationE-mail
Ketova Karolina V.Kalashnikov Izhevsk State Technical Universityketova_k@mail.ru
Rusyak Ivan G.Kalashnikov Izhevsk State Technical Universityprimat@istu.ru
Vavilova Daiana D.Kalashnikov Izhevsk State Technical Universityvavilova_dd@mail.ru
Всего: 3

References

Petty W. Political Arithmetick. London, 1690.
Smith A. An Inquiry into the Nature and Causes of the Wealth of Nations. Scotland, 1776.
Ricardo D. On the Principles of Political Economy and Taxation. England, 1817.
Marshall A. Principles of Economics. London, 1860.
Fisher I. Senses of “Capital” // The Journal of Political Economy. 1897. V. 7, No. 26. P. 199-213.
Schultz T.W. Economic value of education. New York : Columbia University Press, 1963. XII, 92 p.
Becker G.S. Human capital: a Theoretical and Empical Analisis with Special Reference to Education. New York : Columbia Uni versity Press, 1975. XVI, 187 p.
Ben-Porath Y. The production of Human Capital and the Life Cycle of Earning // Journal of Political Economy. 1967. No. 4 (75). P. 352-365.
Добрынин А.И., Дятлов С.А., Цыренова Е.Д. Человеческий капитал в транзитивной экономике: формирование, оценка, эффективность использования. СПб. : Наука, 1999. 310 с.
Капелюшников Р.И. Записка об отечественном человеческом капитале. М. : ГУ ВШЭ, 2008. 56 с.
Корицкий А.В. Введение в теорию человеческого капитала. Новосибирск : СибУПК, 2000. 112 с.
Айвазян С.А. Анализ синтетических категорий качества жизни населения субъектов РФ: их измерение, динамика, основные тенденции // Уровень жизни населения регионов России. 2002. № 11. С. 5-40.
Keskin K., Saglam C. Investment on human capital in a dynamic contest model // Studies in nonlinear dynamics and econometrics. 2019. Vol. 23, No. 1. DOI: 10.1515/snde-2017-0095
Макаров В.Л., Айвазян С.А., Афанасьев М.Ю., Бахтизин А.Р., Нанавян А.М. Оценка эффективности регионов РФ с учетом интеллектуального капитала // Экономика региона. 2014. № 4. С. 9-30.
Fedotova M.A., Loseva O.V., Kontorovich O.I. Monetary Valuation of Intellectual Human Capital in Innovative Activity // Equilibrium-quarterly journal of economics and economic policy. 2016. Vol. 11, No. 2. P. 369-385. DOI: 10.12775/ EQUIL.2016.017
Xu Y., Li A. The relationship between innovative human capital and interprovincial economic growth based on panel data model and spatial econometrics // Journal of computational and applied mathematics. 2020. V. 365. DOI :10.1016/j.cam.2019.112381
Кетова К.В. Математические модели экономической динамики. Ижевск : ИжГТУ, 2013. 284 с.
Русяк И.Г., Кетова К.В. Анализ экономических характеристик демографических потерь // Вестник Томского государственного университета. 2008. № 310. С. 153-160.
Кетова К.В., Русяк И.Г. Идентификация и прогнозирование обобщающих показателей развития региональной экономической системы // Прикладная эконометрика. 2009. № 3 (15). С. 56-71.
Cavarretta F., Naldi G. Mathematical study of a nonlinear neuron model with active dendrites // Aims Mathematics. 2019. V. 4, No. 3. P. 831-846. DOI: 10.3934/math.2019.3.831
Nguyen G., Dlugolinsky S., Bobk M. Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: a survey // Artificial Intelligence Review. 2019. No. 52. P. 77-124. DOI: 10.1007/s10462-018-09679-z
Айвазян С.А., Афанасьев М.Ю., Кудров А.В. Индикаторы основных направлений социально-экономического развития и их агрегаты в пространстве характеристик региональной дифференциации // Прикладная эконометрика. 2019. № 2 (54). С. 51-62.
Осовский С. Нейронные сети для обработки информации. М. : Финансы и статистика, 2004. 343 с.
Рутковская Д., Пилиньский М., Рутковский Л. Нейронные сети. генетические алгоритмы и нечеткие системы. М. : Горячая линия - Телеком, 2006. 383 с.
Кетова К.В., Касаткина Е.В., Насридинова Д.Д. Прогнозирование динамики инвестиционных процессов // Вестник Ижевского государственного технического университета. 2013. № 3 (59). С. 150-154.
Вавилова Д.Д. Программа нейросетевого моделирования и прогнозирования инвестиционных процессов. Св-во о регистрации программы для ЭВМ 2019667497. Заявка № 2019666706 от 16.12.2019.
 Mathematical modeling and neural network prediction of the structure and dynamics of human capital of the Russian Federation | Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie, vychislitelnaja tehnika i informatika – Tomsk State University Journal of Control and Computer Science. 2020. № 53. DOI: 10.17223/19988605/53/2

Mathematical modeling and neural network prediction of the structure and dynamics of human capital of the Russian Federation | Vestnik Tomskogo gosudarstvennogo universiteta. Upravlenie, vychislitelnaja tehnika i informatika – Tomsk State University Journal of Control and Computer Science. 2020. № 53. DOI: 10.17223/19988605/53/2

Download full-text version
Counter downloads: 484