Penerapan Metode Content Based Filtering Dan K-Nearest Neighbor Dalam Sistem Rekomendasi Musik

Abstract

Current technological developments are able to change the way the younger generation enjoys music, where music can now be packaged in digital form, which is a new innovation in the music industry in Indonesia. Given the large amount of music data available on the internet, a system that provides services for users to search for their favorite music is really needed. The recommendation system will provide relevant information based on the preferences that the user wants to search for. Content Based Filtering recommends that users utilize the information contained in the data to use as parameters. The K-Nearest Neighbor (K-NN) algorithm is a method of classifying objects based on the closest training data to the object under test. In this study, accuracy testing techniques were used to measure the performance of the classification that has been carried out. The classification process that was created succeeded in obtaining the highest accuracy value at 90,49% with a value of k=9 which shows that the classification and recommendation process can run quite well.

Keywords: Accuracy, Content Based Filtering, Classification, Recommendation System, K-Nearest Neighbor, Music