Dobrovolsky Intelligent systems for forecasting demographic changes and their impact on marketing strategies in the IT industry

Authors

  • D.I. Uhryn Vinnytsia National Technical University
  • Yu.O. Ushenko Vinnytsia National Technical University
  • O.M. Yatsko Vinnytsia National Technical University
  • A.Ya. Dovhun Vinnytsia National Technical University
  • Yu.G. Dobrovolsky Vinnytsia National Technical University

DOI:

https://doi.org/10.31649/1681-7893-2024-48-2-13-23

Keywords:

intelligent system, machine learning, neural network, IT industry, forecasting demographic changes, marketing strategies

Abstract

The article is devoted to the development of an intelligent system for forecasting demographic changes, which is an important task in the modern world. Traditional analysis of demographic data faces difficulties such as limited access to up-to-date information and a significant amount of unstructured data. The system automates the processing of demographic indicators (fertility, mortality, migration) and their structuring for further analysis and forecasting. The authors have implemented ARIMA and Exponential Smoothing models that allow forecasting population size based on trends and seasonality. Testing of the models for Ukraine, Brazil, and other countries showed that the accuracy of the forecasts depends on the socioeconomic characteristics of each country. ARIMA has proven to be highly accurate in forecasting for stable regions, while Exponential Smoothing adapts to changes in trends. This system provides analysts and governments with an important tool for making informed strategic decisions in the field of population policy, allowing them to take into account complex interrelationships and dynamic trends.

References

Shahrizal, K., et al. (2022). Comparison of ARIMA and Exponential Smoothing in Population Forecasting. Journal of Data Science, 25(3), p. 15.

Bahuguna, A., et al. (2023). Time Series Forecasting of Population Data using ARIMA and Exponential Smoothing Models. International Journal of Research in Medical Sciences, 11(5), p.8.

Kim, M., & Lee, J. (2023). Demographic Prediction Using Hybrid Time Series Models." IEEE Access, 31(6), p. 10.

Gupta, R. & Singh, V. (2021). Forecasting Demographic Changes with ARIMA and Holt-Winters Methods. Demographic Research Journal, 44(5), p. 12.

Wu, Z., et al. (2022). Accuracy of Forecasting Models in Population Dynamics: A Cross-Country Comparison. Journal of Population Studies, 16(1), p. 18.

Nguyen, T. & Pham, L. (2020). Using Time Series Analysis for Predicting Population Growth. Asian Journal of Statistics, 9(4), p. 6.

Santos, E., et al. (2022). Comparative Analysis of ARIMA and Exponential Smoothing for Demographic Forecasting in Emerging Economies. Global Demographics Review, 33(2), p. 20.

Kumar, S. & Patel, J. (2021). Time Series Methods in Population Forecasting: A Review. Journal of Statistics and Applications, 7(3), p. 7.

Rodriguez, C., & Hernandez, S. (2023). Population Prediction Models: A Case Study Using ARIMA and ETS Models. International Journal of Population Studies, 14(2), p. 9.

Hossain, M., et al. (2023). An Adaptive System for Predicting Migration Trends using ARIMA and Seasonal Exponential Smoothing. Population and Migration Studies, 20(3), p. 10.

Tran, L. & Nguyen, C. (2021). Forecasting Birth and Mortality Rates Using Advanced Time Series Techniques. Journal of Demographic Studies, 5(2), p. 8.

Smith, K., & Larson, R. (2022). Forecasting Economic Impacts on Demographics with Hybrid Models. Demography and Economics, 12(5), p. 11.

Huang, J., & Li, X. (2023). Improving Population Forecast Accuracy in Developing Nations Using ARIMA. Population Studies and Statistics, 19(4), p. 14.

Gomez, M., et al. (2022). Analysis of Seasonal Patterns in Population Dynamics Using ARIMA and ETS Models. Journal of Seasonal Forecasting, 11(6), p. 9.

Hamada, K., et al. (2020). Comparative Study on the Effectiveness of Time Series Models for Demographic Changes. International Journal of Forecasting, 36(2), p. 12.

Vander Plas, J. (2016). The Data Science Guide with Python: Essential Tools for Working with Data. O'Reilly Media, 578 p.

Stepanov A., Kornaga Y., Krylov E., Anikin V.. (2021). Peculiarities of indexing in databases and choosing the optimal implementation. Adaptive automatic control systems, 2(37), p. 110–117.

Lathkar M. (2023). High-Performance Web Apps with FastAPI. California: Apress Berkeley, 2023, 309 p.

Romanyuk O., Pavlov S. (2017). Fast ray casting of function-based surfaces, Przeglad elektroteczny, 5, p. 83-86.

Advancements in CNN Architectures for Computer Vision: A Comprehensive Review. (2023). This paper explores recent developments in CNN architectures and their applications in image classification, object detection, and segmentation. IEEE. https://ieeexplore.ieee.org/document/9654151.

A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects. (2022). - A thorough analysis of CNN advancements, covering foundational concepts and current innovations in architecture, along with applications in healthcare, security, and autonomous vehicles. IEEE Transactions on Neural Networks and Learning Systems, https://ieeexplore.ieee.org/document/9451544.

Uhryn D., etc. (2024). Risk management and marketing in the IT industry for the analysis of the exchange rate and forecasting of commodity money, Opt-el. Inf.-Energy Tech., Vol. 47, issue 1, p. 17–27.

Downloads

Abstract views: 3

Published

2024-11-16

How to Cite

[1]
D. Uhryn, Y. Ushenko, O. Yatsko, A. Dovhun, and Y. Dobrovolsky, “Dobrovolsky Intelligent systems for forecasting demographic changes and their impact on marketing strategies in the IT industry”, Опт-ел. інф-енерг. техн., vol. 48, no. 2, pp. 13–23, Nov. 2024.

Issue

Section

Principal Concepts and Structural Approaches to the Three-Level System of Specialist Training

Metrics

Downloads

Download data is not yet available.

Most read articles by the same author(s)

<< < 1 2 3 > >>