Anxiety experienced by an athlete before a match often affects their performance, so it is important for the coach to know the athlete's anxiety level before competing in order to provide appropriate mental training and make decisions that will affect the outcome of the match. However, not all coaches can know the level of anxiety of athletes; therefore, it is necessary to build a web-based system to classify the anxiety level of athletes before competing. The system can be built using one of the data mining methods, namely KNN (K-Nearest Neighbour), where this method can be used to classify the anxiety level of athletes based on a dataset of 364 futsal athlete data participating in the Mechanical Futsal Competition, which will be classified into 3 anxiety categories, namely low, medium, and high, from 17 attributes. From the tests carried out on the dataset using the confusion matrix method using the ratio of testing data: 80:20 training data with K = 5, accuracy, precision, and recall values of 100% were obtained. So we successfully built a website that can be used by a coach to classify athletes based on their anxiety level.