Tel: +998977838464
Search

No. 3 (2026)
Marketing

Articles

FARMATSEVTIKA BOZORIDA TALAB VA TAKLIFNIPROGNOZLASHDA SUNʼIY INTELLEKT ALGORITMLARIDANFOYDALANISH

Published 2026-04-03

Authors
Xomidov Soxibmalik Olimovich
pdf (Uzbek) Google Scholar Google Scholar

Abstract

Ushbu ilmiy maqolada farmatsevtika bozorida talab va taklifni prognozlashda
sunʼiy intellekt (SI) algoritmlaridan foydalanish masalalari tadqiq etilgan. Maqsad:
farmatsevtika sohasida SI asosidagi prognozlash modellarini qiyosiy tahlil qilish va
Oʻzbekiston farmatsevtika bozori uchun eng samarali algoritmni aniqlash.
Metodologiya: mashinali oʻqitish (ML) algoritmlari – LSTM, Random Forest,
XGBoost, Prophet – 2018–2024 yillar uchun Oʻzbekiston farmatsevtika bozori
maʼlumotlari asosida sinab koʻrildi. RMSE, MAE va MAPE koʻrsatkichlari asosida
algoritmlar qiyosiy baholandi. Natijalar: LSTM neyron tarmogʻi eng yuqori aniqlikni
koʻrsatdi (MAPE=4.2%), XGBoost esa tezligi va talqin qilish qulayligi bilan ajralib
turdi. Xulosa: Gibrid SI-modellari (LSTM+XGBoost) Oʻzbekiston farmatsevtika
bozorida talab-taklifni real vaqtda prognozlash uchun optimal yechim hisoblanadi.

Keywords

sunʼiy intellekt, farmatsevtika bozori, talab prognozi, taklif prognozi, mashinali oʻqitish, LSTM, XGBoost, Random Forest, Prophet, Oʻzbekiston.

References

  1. 1. Aamer, A., Eka Putri, L., Eka Pratama, I., & Antara, I.N.Y. (2023). Data
  2. analytics for supply chain demand forecasting: A pharmaceutical case study.
  3. International Journal of Supply Chain Management, 12(1), 48-64.
  4. 2. Babich, V., & Kouvelis, P. (2018). Introduction to the special issue on research
  5. at the interface of finance, operations, and risk management. Manufacturing & Service Operations Management, 20(1), 1-10.
  6. 3. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system.
  7. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge
  8. Discovery and Data Mining, 785-794.
  9. 4. Huang, T., Fildes, R., & Soopramanien, D. (2021). Forecasting demand for
  10. online grocery retail: Insights from both statistical and machine learning approaches. European Journal of Operational Research, 294(2), 615-631.
  11. 5. Ke, G., Meng, Q., Finley, T., Wang, T., Chen, W., Ma, W., ... & Liu, T.Y.
  12. (2017). LightGBM: A highly efficient gradient boosting decision tree. Advances in Neural Information Processing Systems, 30.
  13. 6. Kumar, A., & Bhatia, R. (2022). AI-based demand forecasting in
  14. pharmaceutical supply chains: An empirical study. Journal of Business Logistics,
  15. 43(4), 512-538.
  16. 7. Syntetos, A.A., Boylan, J.E., & Croston, J.D. (2005). On the categorization of
  17. demand patterns. Journal of the Operational Research Society, 56(5), 495-503.
  18. 8. Taylor, S.J., & Letham, B. (2018). Forecasting at scale. The American
  19. Statistician, 72(1), 37-45. https://doi.org/10.1080/00031305.2017.1380080
  20. 9. Williams, B.D., & Kolassa, S. (2020). Supply chain forecasting: a
  21. pharmaceutical case study. International Journal of Forecasting, 36(3), 1030-1049.
  22. 10. Zhang, Q., Li, H., Li, Z., & Wang, J. (2023). Deep learning for pharmaceutical
  23. demand forecasting in China. Health Informatics Journal, 29(1), 1-18.
  24. https://doi.org/10.1177/14604582231157439
  25. 11. Oʻzbekiston Respublikasi Sogʻliqni saqlash vazirligi (2024). Oʻzbekiston
  26. farmatsevtika bozori 2024-yil hisoboti. Toshkent: SSV nashriyoti.
  27. 12. Oʻzfarmsanoat Uyushmasi (2024). Oʻzbekiston farmatsevtika sanoatining
  28. 2018–2024 yillardagi rivojlanish koʻrsatkichlari. Toshkent.
  29. 13. Oʻzbekiston Respublikasi Prezidentining 2025-yil 28-yanvar PF-13-son
  30. “Farmatsevtika tarmogʻini jadal rivojlantirishga oid qoʻshimcha chora-tadbirlar
  31. toʻgʻrisida”gi Farmoni https://lex.uz/uz/docs/-7345588
  32. 14. Statista (2024). Global pharmaceutical market size from 2001 to 2030.
  33. Retrieved from https://www.statista.com/statistics/263102/pharmaceutical-marketworldwide-revenue-since-2001
  34. 15. World Health Organization (2024). Global pharmaceutical market data and
  35. pricing. WHO Geneva.

Downloads

Download data is not yet available.