Hibridni sustav za preporučivanje glazbe zasnovan na suradničkom filtriranju i sadržajnim značajkama

undergraduate thesis

• Title (english): Hybrid Recommender System for Music Based on Collaborative Filtering and Content Features
• Author: Ana Vuksanović
• Mentor: Marin Šilić (mentor)
• Committee member: Marin Šilić (predsjednik povjerenstva)
• Committee member: Stjepan Požgaj (član povjerenstva)
• Committee member: Dejan Stupar (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-06-27, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu napravljen je osnovni pregled sustava za preporučivanje te su detaljno opisani sustavi zasnovani na suradničkom filtriranju i oni zasnovani na sadržajnim značajkama. Korištenjem skupa podataka The Million Playlist Dataset, koji je objavljen u sklopu istraživačkog izazova Spotify Million Playlist Dataset Challenge, napravljene su implementacije opisanih sustava te je također napravljena implementacija hibridnog sustava za preporučivanje koji se koristi značajkama suradničkog filtriranja i sadržajnim značajkama. Sustavi su evaluirani koristeći mjere r-preciznost i NDCG.

Abstract (english)

This paper provides basic overview of recommender systems and describes recommender systems based on collaborative filtering and recommender systems based on content features in greater detail. The paper outlines the implementation of the described systems made using The Million Playlist Dataset, which was published as part of the Spotify Million Playlist Dataset Challenge. The paper also provides an implementation of a hybrid recommender system for music based on collaborative filtering and content features. The systems were evaluated using r-precision and NDCG.

• Keywords: sustav za preporučivanje; hibridni sustav za preporučivanje glazbe; suradničko filtriranje; sustav za preporučivanje zasnovan na sadržajnim značajkama
• Keywords (english): recommender system; hybrid recommender system for music; collaborative filtering; content-based model
• Language: croatian
• URN:NBN: urn:nbn:hr:168:182002
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2024-10-12 22:29:58