Adaptivni sustav za generiranje preporuka iz domene putovanja

master's thesis

• Title (english): Adaptive Recommender System for Travel Planning
• Author: Marija Hlobik
• Mentor: Ljiljana Brkić (mentor)
• Committee member: Ljiljana Brkić (predsjednik povjerenstva)
• Committee member: Igor Mekterović (član povjerenstva)
• Committee member: Boris Milašinović (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2019-02-18, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U okviru ovog rada proučeni su modeli preporučiteljskih sustava i njihovi principi rada. Razvijen je vlastiti sustav za generiranje preporuka pri planiranju putovanja. Uz pomoć javno dostupnih aplikacijskih programskih sučelja izgrađen je set podataka o gradovima za planiranje putovanja, smještajnim jedinicama i dostupnim avionskim letovima do pojedinog grada. Proučeni su načini prevladavanja problema nepoznavanja korisnikovih interesa i implementiran je vlastiti način rješavanja problema nepoznavanja korisnikovih interesa. Jedno od rješenja je prikupljanje inicijalnih podataka o korisniku preko aplikacijskog programskog sučelja Facebook društvene mreže te izgradnja korisničkog profila. Izrađena je prikladna web-aplikacija koja demonstrira rad sustava. Dodatno, za evaluaciju kvalitete preporučiteljskih sustava i poboljšanje budućih preporuka za korisnika, implementiran je i modul za ocjenjivanje preporuka pojedinog preporučiteljskog sustava.

Abstract (english)

This paper describes study of the recommender systems and their working principles. A system for generating travel planning recommendations has been developed. With the help of publicly available application programming interfaces, a set of city planning data for travel plans, accommodation units, and available flights to a particular city was built. The ways to overcome the cold start problem were studied and own way of solving that problem was implemented. One of the solutions for cold start problem is to collect initial user data via the Facebook social network application program interface and build user profile. An appropriate web application that demonstrates the operation of the system was developed. Additionally, for evaluating recommender systems and improving the recommendation quality for users, a module for rating recommendation for each of the recommender system was implemented.

• Keywords: preporučiteljski sustav; kolaborativno filtriranje; preporuke zasnovane na sadržaju; preporuke zasnovane na znanju o korisniku; problem nepoznavanja korisnikovih interesa; društvena mreža; ASP.NET MVC; API; RavenDB
• Keywords (english): recommender system; collaborative filtering; content-based; knowledge-based; cold start problem; social network; ASP.NET MVC; API; RavenDB
• Language: croatian
• URN:NBN: urn:nbn:hr:168:984636
• 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: 2019-03-13 20:48:55