APPLICATION OF MACHINE LEARNING IN MODELING THE DEMOGRAPHIC PROCESS OF KAZAKHSTAN

Saya Zamanbekovna Sapakova, Madinesh Nurgul

Abstract


This paper considers the demographic process of Kazakhstan over the past 10 years, taking into account the influence of the main factors from the socio-economic spheres. Were investigated and analyzed the numerical characteristics of the investigated statistical indicators of factors affecting population growth in 2009-2020. As a result of analysis and calculation, it was found that with an increase in wages, the standard of living of the population will increase, the more healthcare organizations, the more human capital will develop, and in large industrial areas the population will be more concentrated. The article used modern analytical methods based on machine learning technologies ARIMA (Autoregressive Integrated Moving Average), LSTM (Long-short-term memory) and Prophet, to obtain the country's demographic forecasts for future periods. As a result of comparing the operation of these algorithms, we found the advantage of using the Prophet model.

Keywords


Republic of Kazakhstan; demographic situation; population; migration; factors; fertility; death; marriages; divorces; python; machine learning; neural networks

Full Text:

PDF

References


REFERENCES, IEEE

Silverman Eric, Bijak Jakub, Hilton Jason, Cao Viet Dung and Noble Jason. When Demography Met Social Simulation: A Tale of Two Modelling Approaches // Journal of Artificial Societies and Social Simulation (JASSS), 2013. Vol. 16 (4) , Article 9 / URL: http://jasss.soc. surrey.ac.uk/16/4/9.html

Mevin Hooten, Christopher Wikle, Michael Schwob. Statistical Implementations of Agent‐Based Demographic Models//Wiley Online Library, International Statistical Review, 2020. Vol. 88(2)/URL: https://doi.org/10.1111/insr.12399

Anatolii I. Solovev, Stefan A. Solovev. On approaches to analyzing demographic data using machine learning//Scientific software in education and science, 2018. Vol.14(4)/URL: https://doi.org/10.25559/SITITO.14.201804.947-959.

Morgenstern JD, Buajitti E, O’Neill M, et al. Predicting population health with machine learning: a scoping review. BMJ Open 2020;10:e037860. doi:10.1136/ bmjopen-2020-037860.

M. Swamynathan, Mastering Machine Learning with Python in Six Steps,2017,-374p.

Brink Henrik, Richards Joseph, Feverolf Mark Machine Learning (SPb.: Peter, 2017): 336.

Electronic scientific journal "RESEARCHED IN RUSSIA"1270 http://zhurnal.ape.relarn.ru/articles/2006/136.pdf.

P.E. Gladilin, K.O. Bochenina Machine Learning Technologies (St. Petersburg: ITMO University, 2020): 75

Omarov B., Omarov B., Sarbasova A, Sapakova S. "Face recognition in video surveillance systems as an application of smart cities" , Journal of Theoretical and Applied Information Technology 97 (9)(2019). https://www.scopus.com/authid/detail.uri?authorId=57209294878.Percentile – 37% (https://www.scopus.com/sourceid/19700182903?origin=resultslist).

Saya Sapakova, Anarbek Umit. "Development of information systems for the simulation urbanization processes in Almaty" , Lublin: Polish Information Processing Society (2017): 189-217.

Sapakova S., Anarbek U., Kabylhanova N. "Development of an information system for modeling the urbanization process in Almaty" , "Khabarshi"KazNPU named after Abai 4 (2016): 56




DOI: http://dx.doi.org/10.21533/scjournal.v10i1.203

Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 Saya Zamanbekovna Sapakova

ISSN 2233 -1859

Digital Object Identifier DOI: 10.21533/scjournal

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License