Hibridni model sustava preporučivanja kozmetičkih proizvoda zasnovan na matričnoj faktorizaciji

master's thesis

• Title (english): Hybrid Skin-care Products Recommendation System Based on Matrix Factorization
• Author: Patrik Marić
• 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: 2020-07-07, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Zbog velike količine podataka, web trgovine za njegu kože moraju filtrirati podatke prema potrebama korisnika. U ovome su radu prikupljeni podaci s jedne popularne web trgovine kozmetičkim proizvodima. Podaci su iskorišteni za implementaciju hibridnog modela sustava preporučivanja koji kombinira SVD, suradnički sustav preporučivanja temeljen na suradnji koji koristi matričnu faktorizaciju, te KNN sustav temeljen na sadržaju. Evaluacija sustava provedena je koristeći nekoliko metrika često korištenih za evaluaciju sustava preporučivanja. Rezultati evaluacije pokazuju da hibridni sustav u pogledu zadatka vračanja K najrelevantnijih produkata kao preporuku uspješno koristi prednosti oba sustava.

Abstract (english)

Due to a large amount of data, online skin-care retail stores need to filter the data according to user needs. In this work, data from one popular online skin-care retail store was scraped, and a hybrid recommender system was implemented. The implemented hybrid system combines SVD, a matrix factorisation collaborative filtering approach, and kNN content-based recommender system. The system was evaluated with several well-known recommendation systems evaluation metrics. The results of the evaluation show that the system successfully utilises the advantages of both systems in regards to the top-K recommendations task.

• Keywords: sustavi preporučivanja; hibridni sustavi preporučivanja; kozmetički proizvodi
• Keywords (english): recommendation systems; hybrid recommendation systems; skincare products
• Language: english
• URN:NBN: urn:nbn:hr:168:647691
• 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 12:59:06