BI-TIZIMNING CHUQUR O’QITISH ASOSIGA QURILGAN UMUMLASHGAN ARXITEKTURASI
DOI:
https://doi.org/10.47390/ts-v3i8y2025No5Ключевые слова:
Biznes-intellekt (BI), chuqur o‘qitish, ma’lumotlarni tayyorlash, LSTM, chiziqli regressiya (Linear Regression), tayanch vektor regressiyasi (SVR), gibrid model, bashoratlash tizimi, qishloq xo‘jaligi mahsulotlari narxlari, BI-Pred 1.0, intellektual tahlil, ma’lumotlarni vizualizatsiya qilish, strategik qarorlar qabul qilishАннотация
Mazkur maqolada “BI-Pred 1.0” dasturiy jamlanmasining umumiy arxitekturasi va uning asosiy komponentlari tahlil qilinadi. Model qurilishida ma’lumotlarni tayyorlash, dastlabki ishlov berish, mashinali o‘qitish algoritmlari hamda gibrid yondashuv asosida ishlab chiqilgan LSTM, Linear Regression va Support Vector Regression modellarining qo‘llanishi ko‘rib chiqiladi. Ushbu yondashuv asosida qishloq xo‘jaligi mahsulotlari narxlarini, xususan kartoshka narxlarini bashoratlash imkoniyati asoslab beriladi. Tadqiqot natijalari, iqtisodiy jarayonlarda intellektual tahlil usullaridan samarali foydalanish orqali strategik qarorlar qabul qilishni yengillashtirishi bilan ahamiyatlidir
Библиографические ссылки
1. Zhang, Q., Wu, Y., & Li, X. (2024). Short-term forecasting of vegetable prices based on LSTM. PLOS ONE, 19(3), e11239047. https://doi.org/10.1371/journal.pone.11239047
2. Sun, C., Pei, M., Cao, B., Chang, S., & Si, H. (2024). A Study on Agricultural Commodity Price Prediction Model Based on Secondary Decomposition and Long Short-Term Memory Network. Agriculture, 14(1), 60. https://doi.org/10.3390/ agriculture14010060
3. Smola, A. J., & Schölkopf, B. (2004). A tutorial on support vector regression. Statistics and Computing, 14(3), 199–222. https://doi.org/10.1023/B:STCO.0000035301.49549.88
4. Almarashi, R. S., et al. (2023). Support vector regression model with variant tolerance (Aεi-SVR). Journal of Theoretical and Applied Information Technology, 101(4), 1182–1194. https://doi.org/10.1177/00202940231180620
5. Manogna, R. L., Singh, R., & Kumar, D. (2025). Enhancing agricultural commodity price forecasting with deep learning approaches. Scientific Reports, 15(1), 5103. https://doi.org/10.1038/s41598-025-05103-z
6. Yadav, R. & Tiwari, P. (2022). Evolution of Support Vector Machine and Regression Modeling in Price Forecasting Tasks. International Journal of Advanced Computer Science and Applications (IJACSA), 13(12), 45–52. https://doi.org/10.14569/IJACSA.2022.013126.
This work is licensed under a 