Sustav preporuke filmova zasnovan na suradničkom filtriranju

undergraduate thesis

• Title (english): Movie Recommender System Based On Collaborative Filtering
• Author: Maria Fain
• Mentor: Goran Delač (mentor)
• Committee member: Goran Delač (predsjednik povjerenstva)
• Committee member: Zoran Medić (član povjerenstva)
• Committee member: Marin Vlaić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2022-07-01, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Sustavi preporuke stvoreni su u svrhu unaprijeđivanja pretraživanja i korištenja sadržaja korisnicima u virtualnom svijetu. Jedna vrsta sustava za preporuku su sustavi preporuke zasnovani na suradničkom filtriranju čiji način rada je opširnije opisan u ovome radu. Ponuđen je opis metrika koje se koriste u algoritmima preporuke i opis izdvojenih algoritama preporuke zasnovanih na suradničkom filtriranju. Napravljeno je jednostavno programsko ostvarenje sustava preporuke filmova zasnovanog na suradničkom filtriranju koristeći bazu podataka MovieLens. Nakon programskog ostvarenja, provedeno je vrednovanje uspješnosti i preciznosti korištenih algoritama preporuke.

Abstract (english)

Recommendation systems were built with the purpose of upgrading the search and use of content for users in the virtual world. This paper explains the functionality of a certain kind of recommendation systems called recommendation systems based on collaborative filtering. A description of similarity metrics that are used in recommendation algorithms is given along with a description of chosen recommendation algorithms based on collaborative filtering. A simple film recommendation system based on collaborative filtering is implemented using the MovieLens database. Following the implementation, a calculation using accuracy metrics has been made for each of the used algorithms.

• Keywords: sustav preporuke zasnovan na suradničkom filtriranju; fenomen dugog repa; matrica korisnosti; Jaccardova udaljenost; kosinusna udaljenost; Pearsonov koeficijent; algoritam SVD; algoritam KNNWithMeans; algoritam SlopeOne; algoritam CoClustering; srednje apsolutno odstupanje; korijen srednjeg kvadratnog odstupanja; preciznost
• Keywords (english): recommendation system based on collaborative filtering; long tail phenomenon; utility matrix; Jaccard distance; cosine distance; Pearson's coefficient; SVD algorithm; KNNWithMeans algorithm; SlopeOne algorithm; CoClustering algorithm; MAE; RMSE; precision
• Language: croatian
• URN:NBN: urn:nbn:hr:168:235643
• 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: 2023-01-15 10:06:32