<p>The continuous advancement of smart home technologies, fueled by the integration of Internet of Things (IoT) and artificial intelligence (AI), has transformed modern residential environments by offering automation, enhanced energy efficiency, and personalized user experiences. Smart home technologies, driven by the Internet of Things (IoT) and artificial intelligence (AI), promise automation, energy efficiency, and personalized experiences. However, their potential is limited by persistent challenges such as inefficient energy use due to static control algorithms, a lack of adaptive control systems that respond to real-time user behavior, and limited interoperability among diverse devices. This study analyzes a four-year smart home dataset to identify device usage patterns, detect inefficiencies, and develop intelligent automation rules aligned with user behaviors. Leveraging machine learning, including decision trees and random forests, and rule-based modeling, the proposed strategies enable real-time optimization of device operations. Simulation results demonstrate potential for an estimated 15-25% reduction in energy consumption and demonstrate that user’s needs are met in the smart home context. The findings underscore the potential of data-driven approaches to improve the scalability, adaptability, and sustainability of smart home systems. This research contributes practical insights for enhancing energy management, automation logic, and user satisfaction in future smart living environments.</p> Graphical Abstract <p></p>