MUSIC RECOMMENDATION SYSTEM BASED ON COSINE SIMILARITY AND SUPERVISED GENRE CLASSIFICATION

Categorizing musical styles can be useful in solving various practical problems, such as establishing relationships between songs, similar and finding communities that share an interest a particular genre. Our goal this research is to determine the most effective machine learning technique accurately predict song genres using K-Nearest Neighbors (K-NN) Support Vector Machine (SVM) algorithms. In addition, article offers contrastive examination of when dimensioning considered without Principal Component Analysis (PCA) for dimension reduction. MFCC used collect data from datasets. each track uses feature. The results reveal offer more precise reducing dimensions than PCA results. accuracy method 58% has potential decrease. music genre classification, are proven efficient classifiers. 64,9%, 77%. Not only that, but we also created recommender system cosine similarity provide recommendations songs have relatively same From one sample tested, five were obtained had with average 80%.