Show simple item record

dc.contributor.authorGeving, Brian
dc.date.accessioned2021-12-23T22:08:25Z
dc.date.available2021-12-23T22:08:25Z
dc.date.issued2021-12
dc.identifier.urihttp://hdl.handle.net/20.500.11803/1649
dc.description.abstractWhile the field of Music Information Retrieval (MIR) is steadily progressing, the majority of music recommendation systems still operate using collaborative filtering. Collaborative filtering operates by finding patterns between music represented in collected playlists. While this method works well for music that has a large amount of representation, it is a very poor method for recommending music that has very little availability. By utilizing machine learning classification algorithms and low-level audio feature extraction, there exists a method to classify music with specific parameters. Instead of using modern music genres as a way to relate music, using labels provided by collaborative filtering can provide a high accuracy way to recommend similar music with low representation.en_US
dc.language.isoenen_US
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 United States
dc.rightsopenAccess
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/
dc.subjectSVMen_US
dc.subjectClassificationen_US
dc.subjectMusicen_US
dc.subjectLibrosaen_US
dc.subjectMIRen_US
dc.subjectMachine learningen_US
dc.subjectCollaborative filteringen_US
dc.titleMeaningful Classification for Music Recommendation Systemsen_US
dc.typeCapstoneen_US
thesis.degree.disciplineComputer Scienceen_US
thesis.degree.grantorCity University of Seattleen_US
thesis.degree.levelMastersen_US
thesis.degree.nameMaster of Scienceen_US
cityu.schoolSchool of Technology and Computingen_US
cityu.siteSeattleen_US
cityu.site.countryUnited Statesen_US


Files in this item

PDF

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-NoDerivs 3.0 United States