<![CDATA[Objective evaluation of athletes’ physical test data can help reduce subjectivity in athlete assessment. This study develops a web-based classification system using the Naïve Bayes algorithm to classify wrestling athletes as Successful or Unsuccessful based on speed, balance, and agility attributes. The study uses a quantitative approach and the Waterfall software development model. The dataset consists of 36 wrestling athlete records, with 30 records used as training data to calculate prior and conditional probabilities and 6 independent records reserved for final testing; the testing records were not used during the training or probability calculation process. Speed is categorized as Slow, Normal, or Fast; balance as Poor, Fair, or Good; and agility as Low, Medium, or High. The target labels, Successful and Unsuccessful, were assigned independently based on recorded athlete performance assessment outcomes and were not derived from the predictor variables. The Naïve Bayes classification process calculates class priors, attribute likelihoods, posterior probabilities, and predicted classes. For the illustrated test case with Slow speed, Poor balance, and Low agility, the normalized probabilities were 4% for Successful and 96% for Unsuccessful. The six-record performance evaluation produced 83.33% accuracy, 75% precision, 100% recall, and an 85.71% F1-score. The system can support structured and more objective athlete assessment; however, the limited dataset size may restrict the generalizability of the results and requires validation using a larger dataset.]]>
