From Data to Insights: Predictive and Descriptive Analysis of Gas and Metal Consumption in Metallurgy

This study aims to highlight the growing importance of data as a tool for both diagnosis and forecasting. In an era where data-driven decision-making plays a crucial role across industries, the ability to collect, process, and analyze vast amounts of information has become a key factor in staying competitive. The study explores key topics and methodologies related to data valuation. It begins with a review of the state-of-the-art, introducing fundamental concepts of business intelligence, data warehousing and machine learning, and then applies these principles to a real-world case study involving a metallurgical company. The work follows a well defined workflow: first, data is collected and stored in a dimensional model to support subsequent analyses. Then, machine learning models, such as Random Forest and ARIMA, are trained to perform time series forecasting, enabling the prediction of key features in resource consumption. Finally, the insights gained from the previous steps are visualized into an interactive Power BI dashboard. The ultimate goal is to create a tool that enhances data utilization, making insights accessible even to non-experts and supporting the company in data-driven business decision-making.