O‘ZBEKISTONDAGI INFLYATSIYA DARAJASINING SO‘NGGI 10 YILDAGI DINAMIKASI VA UNI NEYRON TARMOQ YORDAMIDA BASHORAT QILISH

Abstract

Annotatsiya.Mazkur maqolada O‘zbekiston iqtisodiyotidagi inflyatsiya darajasining 2015–2024 yillar oralig‘idagi dinamikasi tahlil qilinib, sun’iy neyron tarmoq yordamida 2025-yil uchun prognoz shakllantirilgan. Tadqiqotning asosiy maqsadi – inflyatsiya darajasiga ta’sir etuvchi omillarni aniqlash va sun’iy intellekt yondashuvi yordamida iqtisodiy bashorat aniqligini oshirishdan iborat. Tadqiqotda O‘zbekiston Respublikasi Markaziy banki, Statistika agentligi va Jahon banki ma’lumotlari asosida pul massasi, valyuta kursi, foiz stavkasi, YaIM o‘sish sur’ati kabi asosiy ko‘rsatkichlar o‘rganilgan. Metodologiya sifatida ko‘p qatlamli perseptron (MLP) va uzoq xotirali LSTM (Long Short-Term Memory) neyron tarmoq modellari qo‘llanilgan. Natijalar shuni ko‘rsatdiki, LSTM modeli inflyatsiya prognozida an’anaviy ARIMA modeliga nisbatan 11,4% yuqori aniqlikka ega. Tadqiqot iqtisodiy barqarorlikni ta’minlash va pul-kredit siyosatini samarali rejalashtirishda amaliy ahamiyatga ega.

Abstract.This article analyzes the dynamics of the inflation rate in the economy of Uzbekistan during the period 2015–2024 and develops a forecast for 2025 using artificial neural networks. The main objective of the study is to identify the factors influencing inflation and to improve the accuracy of economic forecasting through an artificial intelligence approach. The research is based on data from the Central Bank of the Republic of Uzbekistan, the Statistics Agency, and the World Bank, examining key indicators such as money supply, exchange rate, interest rate, and GDP growth rate. As a methodological approach, multilayer perceptron (MLP) and Long Short-Term Memory (LSTM) neural network models are employed. The results demonstrate that the LSTM model achieves 11.4% higher forecasting accuracy in predicting inflation compared to the traditional ARIMA model. The study has practical significance for ensuring economic stability and for the effective planning of monetary policy.