Sustav za preporučivanje zadataka natjecateljskog programiranja

master's thesis

• Title (english): Recommender System for Competitive Programming Assignments
• Author: Tvrtko Petrović
• Mentor: Goran Delač (mentor)
• Committee member: Goran Delač (predsjednik povjerenstva)
• Committee member: Marin Šilić (član povjerenstva)
• Committee member: Klemo Vladimir (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2020-09-09, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U okviru ovog rada odrađena su teoretska razmatranja o izgradnji i svojstvima preporučiteljskih sustava. Napravljen je pregled njihovih najvažnijih vrsta i usporedba njihovih svojstava. Izgrađen je generički preporučiteljski sustav temeljen na suradnji korisnika za područje problema natjecateljskog programiranja. Programski je ostvareno prikupljanje podataka s konkretnih sustava iz domene. Ti podatci primijenjeni su na izgrađeni preporučiteljski sustav. Izgrađena je okolina za samostalan rad preporučiteljskog sustava na Internetu. Za potrebe prikaza njegovih rezultata razvijena je posebna web-aplikacija. Nad preporukom sustava provedeno je vrednovanje. Pomoću rezultata vrednovanja ostvarena je procjena optimalnih vrijednosti parametara rada sustava.

Abstract (english)

This thesis considers the construction process of recommender systems and their most important properties. It contains a review of their most important types and a comparison of their properties. A collaborative recommender system was built in respect to the domain of competitive programming. Automatic data collection was performed on specific existing systems from the target domain. That data was applied to the built recommeder system. Independent environment for the operation of the recommender system was created, along with a web application used for respresenting the results of the recommendation process. Recommendation was tested and the testing results were applied in the estimation of the system parameters.

• Keywords: preporučiteljski sustav; sustav temeljen na suradnji korisnika; natjecateljsko programiranje
• Keywords (english): recommender system; collaborative system; competitive programming
• Language: croatian
• URN:NBN: urn:nbn:hr:168:433390
• 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: 2023-01-15 11:04:06