This study analyzed match profiles from the 2019 Brazilian Football Championship using clustering and classification techniques to identify performance patterns and support tactical decision-making. Employing the K-Means algorithm, matches were segmented into four distinct clusters based on statistical metrics: league position difference, total shots, missed shot rate, starting lineup age difference, goal difference, first-half goals, and total fouls. These variables were analyzed in absolute terms, without differentiating between home and away teams. The identified profiles ranged from matches between teams with significantly different performances to games with high offensive and physical intensity. The Random Forest analysis highlighted league position difference and shot volume as the primary clustering factors. To enrich the analysis, data from 2019 were compared with those from 2018, revealing changes in the relative importance of variables: the missed shot rate surpassed goal difference in relevance, suggesting a growing emphasis on offensive efficiency. Furthermore, in 2019, a cluster emerged that was highly sensitive to multiple factors, indicating increased tactical complexity in the matches. The results demonstrate that clustering can uncover tactical patterns in football, providing strategic insights for match analysis. Future studies may expand this approach by incorporating new variables and exploring more advanced machine learning methods to optimize match segmentation.