Яшил иқтисодиёт ва тараққиёт 4-jild 3-son (2026)
FORECASTING THE EFFICIENCY OF SOLID WASTE RECYCLING IN INDUSTRIAL ENTERPRISES
Axmedov, Sheramat
Annotatsiya
This article provides a comprehensive analysis of modern machine learning methods utilized in industrialsectors, specifically focusing on the application of the XGBoost algorithm to enhance production productivity. The studyexamines the integration of these technologies within solid waste recycling processes at industrial enterprises, whilehighlighting the exceptional accuracy levels achieved by the model. Furthermore, the research demonstrates significantresource optimization capabilities for sustainable manufacturing and effective management.A particular focus is placed on maintaining performance amidst the noise and insignificant data inherent in complexindustrial datasets. Additionally, the article addresses how the algorithm effectively handles incomplete indicators toensure reliable and consistent output. The findings illustrate the practical significance of implementing forecasting modelswithin the framework of the digital economy. Finally, the conclusions define the key role of machine learning technologiesin improving overall industrial efficiency.
XGBoost algorithm, industrial efficiency, machine learning, recycling processes, solid waste, forecasting models, digital economy, resource optimization
Metadata manbasi: jurnal OAI-PMH arxivi · Sindex toʻliq matnni saqlamaydi, manbaga havola beradi.