This study presents an analytical platform for assessing operational performance in industrial environments through the use of Random Forest classification and K Means clustering. Five key performance indicators—scrap rate, cycle time, quality, attendance, and supervisor-based performance rating—were selected to evaluate a dataset of 293 operators from different production areas. After data cleaning and normalization, the Random Forest model achieved an accuracy of 89%, correctly classifying operators into High, Regular, and Critical categories. In parallel, K Means generated three performance clusters that highlight distinct behavioral patterns among operators. The system was developed with a modular architecture using FastAPI, PostgreSQL, and React.js, and includes interactive dashboards created in Power BI to support decision-making. Practical validation showed benefits such as increased objectivity, transparency, and improved identification of both high and low performers. The results demonstrate that data-driven methods can enhance operational evaluation and provide a foundation for scalable industrial applications.