Personalized Cricket Player Analysis by Live Scoring Utilizing Unsupervised Machine Learning

This research delves into the intersection of artificial intelligence and sports analytics, focusing on digitizing data collection in local player tournaments. The shift from traditional paper-based scoring at grassroots levels enables unsupervised machine learning for nuanced pattern recognition in player performance. The advanced data modeling inherent in this methodology distinguishes the research, elevating its contribution to the evolving landscape of sports analytics. The study utilizes K-means clustering for non-overlapping identification of player performance patterns, addressing challenges encountered with the DBSCAN algorithm and offering a novel approach to sports analytics within the realm of local player development.