Generiranje preporuka koje uzimaju u obzir vremenske i prostorne navike korisnika

master's thesis

• Title (english): Generating Recommendations Taking into Account Users' Temporal and Spatial Habits
• Author: Ivan Cvitanović
• 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: 2020-09-24, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U okviru rada implementiran je preporučiteljski sustav iz domene slobodnog vremena. Preporučiteljski sustav uzima u obzir vremenske i prostorne navike korisnika kako bi ponudio što relevantnije preporuke. Implementiran je sustav za analizu povijesti kretanja korisnika u svrhu stvaranja profila korisnika na temelju kojeg preporučiteljski sustav generira preporuke. Korisniku je kroz korištenje web aplikacije omogućeno ocjenjivanje pojedinih preporuka i definiranje vlastitih interesa, na temelju čega preporučiteljski sustav s vremenom poboljšava profil korisnika i stvara sve relevantnije preporuke. Korisniku je također omogućen uvid u podatke na temelju kojih preporučiteljski sustav donosi odluke o preporukama. Studijom testnog skupa korisnika provedena je evaluacija kvalitete preporučiteljskog sustava.

Abstract (english)

This paper describes the development and implementation of a location-based event recommendation system. User location history is analyzed for the purpose of creating a user profile that the recommender system uses to generate relevant recommendations. Through using the web application, the user can rate individual recommendations as well as define their own interests, which helps to improve the generated user profile and lets the system offer more accurate recommendations. Users can also view the data that the system has collected and see how it's used for generating recommendations. Furthermore, a user study has been conducted in order to evaluate the quality of the recommender system.

• Keywords: preporučiteljski sustav; content-based; povijest lokacija; cold start problem; ASP.NET Core; Web API; Angular; SQL Server
• Keywords (english): recommender system; content-based; location history; cold start problem; ASP.NET Core; Web API; Angular; SQL Server
• Language: croatian
• URN:NBN: urn:nbn:hr:168:317589
• 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 09:05:26