Sustav preporučivanja igara zasnovan na suradničkom filtriranju

master's thesis

• Title (english): Games Recommender System Based on Collaborative Filtering
• Author: Vice Ivušić
• Mentor: Klemo Vladimir (mentor)
• Committee member: Klemo Vladimir (predsjednik povjerenstva)
• Committee member: Marin Šilić (član povjerenstva)
• Committee member: Goran Delač (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Sustavi preporučivanja (engl. recommender systems) softverska su rješenja i tehnike čija je svrha preporučiti sadržaj korisniku. Sustavi zasnovani na suradničkom filtriranju (engl. collaborative filtering) odluku o preporuci predmeta korisniku temelje na njegovu prošlom ponašanju kao i ponašanju drugih korisnika. Vrednovanje sustava provodi se s ciljem utvrđivanja koliko dobro radi sustav preporučivanja.

U sklopu rada predstavljena je implementacija web pauka (engl. web spider) za prikupljanje podataka o ocjenama igara s web stranice Metacritic. Implementiran je sustav preporučivanja zasnovan na suradničkom filtriranju i provedeno je njegovo vrednovanje.

Abstract (english)

Recommender systems are software tools and techniques that provide recommendations for content to users. Recommender systems based on collaborative filtering build their recommendations having taken into consideration the past behaviors of both the target user and of users similar to the target user. System validation is used to determine how well the recommender system works.

As part of this thesis, a web spider implementation for web scraping Metacritic’s website is presented. A recommender system based on collaborative filtering is implemented and validated.

• Keywords: sustavi preporučivanja; suradničko filtriranje; matrica korisnosti; mjere sličnosti; predviđanje ocjena; vrednovanje sustava; mjere uspješnosti; hiperparametri; prikupljanje podataka s weba
• Keywords (english): recommender systems; collaborative filtering; utility matrix; measuring similarity; rating prediction; system validation; hyperparameters; web scraping
• Language: croatian
• URN:NBN: urn:nbn:hr:168:795607
• Study programme: Title: Computing; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-01-13 09:09:37