Primjena tehnika dubinske analize podataka za predviđanje rezultata sportskih natjecanja

master's thesis

• Title (english): Applying data mining techniques for prediction of sports competition results
• Author: Svibor Dolenec
• Mentor: Marko Banek (mentor)
• Committee member: Marko Banek (predsjednik povjerenstva)
• Committee member: Boris Vrdoljak (član povjerenstva)
• Committee member: Damir Pintar (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2014-07-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Electrical Engineering

Abstract

U ovom radu napravljena je dubinska analiza podataka zadnjih rezultata utakmica deset godina 1. španjolske nogometne lige. Neobrađeni podaci prikupljeni su s weba te ubačeni u bazu podataka gdje su se određenim upitima izvlačile bitne informacije koje su kasnije korištene za analizu. Prediktivni model rađen je u programskom jeziku R pomoću linearne regresije. Zadatak je bio predvidjeti broj bodova momčadi na kraju sezone samo na bazi njihovih rezultata u prvom dijelu sezone.
Nakon unakrsne provjere prediktivnog modela napravljena je analiza te su doneseni zaključci o ponašanju rezultata. Dodatno, sezona 2014. je posebno analizirana zbog svoje uzbudljive završnice te velike medijske praćenosti.

Abstract (english)

In this master thesis a data mining analysis was performed on the match results of the last ten years of the 1st Spain football league. Raw data was found on the Web and was transformed into the database in order to create a suitable data set which could be used for later analysis. The prediction model was made in the programming language R using linear regression. The task was to predict the number of points of the teams in the end of the season by using the match results from the first half of the season only. After the cross validation and analysis of the prediction model, a conclusion of the behaviour of the results was made. Additionally, season 2013-2014. was analyzed in particular because of its thriller ending and a big media coverage.

• Keywords: prediktivni model; unakrsna provjera; dubinska analiza podataka; linearna regresija
• Keywords (english): prediction model; cross validation; data mining; linear regression
• Language: croatian
• URN:NBN: urn:nbn:hr:168:861590
• Study programme: Title: Information and Communication Technology; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije (magistar/magistra inženjer/inženjerka informacijske i komunikacijske tehnologije)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2018-02-06 08:26:29