By creating a data-driven, intelligent decision support system (IDSS), this project focuses on improving energy management for businesses by utilizing forecasting techniques and insights derived from monitoring energy data. Electricity consumption predictions are made by using a variety of inputs including historical consumption data of manufacturing companies. This will reduce the negative effects of uncertainty, resource waste, and potential power outages. This creates a more sustainable environment by preventing excessive energy consumption. Various algorithms are tested using Python, focusing on time series using machine learning (ML) techniques. Then, the results are compared to determine the model that predicts the data best. The future electricity consumption can be estimated using the selected model in IDSS. Later, companies can perform budget and invoice management using this estimated data. For application, by gathering data from Hudop Technology Inc.’s database and performing necessary preprocessing steps, the goal is to select the best model having high accuracy and low error for every scenario and use it in IDSS for electricity consumption forecasts of manufacturing companies.