Basketball Data Analysis Using Spark Framework and K-Means Algorithm

With the rapid development, different information relating to sports may now be recorded forms of useful big data through wearable and sensing technology. Big data technology has become a pressing challenge to tackle in the present basketball training, which improves the effect of baseball analysis. In this study, we propose the Spark framework based on in-memory computing for big data processing. First, we use a new swarm intelligence optimization cuckoo search algorithm because the algorithm has fewer parameters, powerful global search ability, and support of fast convergence. Second, we apply the traditional K-clustering algorithm to improve the final output using clustering means in Spark distributed environment. Last, we examine the aspects that could lead to high-pressure game circumstances to study professional athletes' defensive performance. Both recruiters and trainers may use our technique to better understand essential player's qualities and eventually, to assess and improve a team's performance. The experimental findings reveal that the suggested approach outperforms previous methods in terms of clustering performance and practical utility. It has the greatest influence on the shooting training impact when moving, yielding complimentary outcomes in the training effect.