Sustav preporuke mirkokreditiranja zasnovan na suradničkom filtriranju

master's thesis

• Title (english): Microloan Recommender System Based On Collaborative Filtering
• Author: Denis Kustura
• Mentor: Goran Delač (mentor)
• Committee member: Goran Delač (predsjednik povjerenstva)
• Committee member: Marin Šilić (član povjerenstva)
• Committee member: Siniša Srbljić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-07-09, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Sustavi preporučivanja vrsta su sustava koji predviđaju afinitete i odziv korisnika nekog sustava prema predmetima koji se nude korisnicima tog sustava. Sve je češća uporaba takvih sustava u komercijalne svrhe. U okviru rada, primjenom metode suradničkog filtriranja izgrađen je jedan takav sustav za stvaranje preporuka mikrokredita korisnicima platforme Kiva. Kiva je jedna od najpopularnijih peer-to-peer platformi za mikrokreditiranje. Budući da podatci prikupljeni na Kiva platformi pripadaju vrsti podataka s implicitnom povratnom informacijom, u svrhu izgradnje sustava preporučivanja nad tim podatcima upotrebljen je algoritam alternirajućih najmanjih kvadrata (engl. ALS). Opisana je implementacija navedenog algoritma i prikazani su rezultati njegove evaluacije.

Abstract (english)

Recommender systems are types of systems that seek to predict the preference and response a user would give to items of a given platform. Such systems have become commonly used for commercial purposes. In presented work, a recommender system based on the collaborative filtering method has been implemented to recommend microloans to users of the Kiva platform. Kiva is one of the most popular peer-to-peer platforms used for lending money in the form of microloans. Since the data collected on the Kiva platform has the form of implicit feedback, the alternating least squares (ALS) algorithm was used to construct the recommendation system. The implementation of chosen algorithm is described as well as its evaluation results.

• Keywords: sustav; preporuke; preporučivanje; implicitna; povratna; informacija; Kiva; mikrokreditiranje; mikrofinancije; suradničko; filtriranje; faktorizacija; matrice; ALS; alternirajući; najmanji; kvadrati
• Keywords (english): recommender; system; recommendation; implicit; feedback; Kiva; microloan; microfinance; collaborative; filtering; matrix; factorization; ALS; alternating; least; squares
• Language: croatian
• URN:NBN: urn:nbn:hr:168:745623
• 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: 2020-01-07 19:33:58