This project explores the usage of advanced technologies and machine learning for the development of intelligent systems that predict window status based on data collected from sensors and external meteorological data. By using two different machine learning methods, Random Forest and Gradient Boosting, their performances for the task of predicting window status were analyzed. This project includes the implementation of an API for retrieving external meteorological data and establishing a cloud computing infrastructure for efficient data processing and storage. After data collection, machine learning models were developed and optimized, followed by thorough performance analysis and adjustment of individual models. In the end, a test example demonstrates the final system and its practical application. The results of this project show that machine learning can effectively use real data for accurate predictions. The project also highlights the importance of careful model selection and adjustments according to the available data. In future work, the system could be further improved by expanding functionalities and enhancing model accuracy, adapting to different scenarios and specific user needs. This project confirms the potential of integrating data from various sources and using advanced machine learning algorithms, contributing to the improvement of the quality of life through automated and intelligent decision-making.