부산대학교 도서관

It is critically important for a college baseball team if the pitch type information is available when the characteristics of a pitch are collected. This information is typically collected by baseball specialists; however, this process can be time-consuming and error-prone due to human nature. To address this issue, multiple machine learning classifiers, including Support Vector Machine (SVM), k-nearest neighbors (kNN), Decision Tree, and Artificial Neural Network (ANN), were examined and compared. Although all tested classifiers achieved at least 0.92 in accuracy, ANN categorized the pitches with the most accuracy (0.96), precision (0.95), and recall (0.95) within a reasonable training time (85.7 seconds). In summary, ANN is the best classifier among the examined models.