<![CDATA[The increasing demand for electrical energy in residential areas has highlighted the need for more intelligent and efficient energy management systems. This research explores the application of Internet of Things (IoT) technology integrated with data science prediction models to enhance the efficiency of household energy consumption. By deploying IoT-based smart sensors in various electrical appliances, real-time energy usage data was collected and transmitted to a centralized cloud-based system. The data was then processed and analyzed using predictive modeling techniques, including Linear Regression, Random Forest, and Long Short-Term Memory (LSTM) networks, to identify usage patterns and forecast future consumption. The research was conducted through a prototype implementation in selected households, where energy usage was monitored over a period of 30 days. The prediction models were trained using historical consumption data and validated with a testing dataset to evaluate their accuracy. Among the models used, the LSTM model demonstrated the highest prediction accuracy with a Mean Absolute Percentage Error (MAPE) of 5.3%, outperforming traditional regression-based methods. Additionally, a user-friendly dashboard was developed to visualize real-time consumption and provide personalized recommendations for energy-saving behavior. The results indicate that the integration of IoT and data science can significantly contribute to more informed decision-making in energy usage at the household level. ]]>
