The rise of big data has transformed soccer analysis, providing rich insights through high-volume, high-velocity, and high-variety information. This data’s potential benefits are immense, offering a deeper understanding of team tactics, player performance, and more. However, challenges in data governance and processing must be addressed. Machine learning has emerged as a potent tool in soccer analytics. It’s used to analyze events, evaluate player performance, predict injuries, and estimate team tactics. Its applications span from predicting match outcomes to measuring individual and collective performance. Open datasets fuel ongoing research in this area. The knowledge discovery pipeline in soccer involves data collection, preprocessing, mining, modelling, and evaluation. This iterative process supports performance measurement, success determinants identification, and outcome prediction. Libraries like Floodlight, Codeball, soccermatics, and optapro aid soccer data analysis. They provide streamlined tools for handling data, creating visualizations, and extracting insights. Big data and machine learning revolutionize soccer analysis, while the knowledge discovery process and dedicated libraries facilitate deeper insights and strategic decision-making.