Predviđanje ishoda odbojkaških utakmica korištenjem metoda strojnog učenja

undergraduate thesis

• Title (english): Predicting the outcome of volleyball matches using machine learning methods
• Author: Domagoj Matošević
• Mentor: Alan Jović (mentor)
• Committee member: Alan Jović (predsjednik povjerenstva)
• Committee member: Nikolina Frid (član povjerenstva)
• Committee member: Igor Stančin (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-09-11, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U radu je objašnjen postupak analize i obrade podataka utakmica muških hrvatskih odbojkaških natjecanja. Motivacija za izradu ovog rada bila je potreba za nekakvi predvidanjem ishoda budućih utakmica. Napisane su stranice gdje se nalaze podaci i načini pomoću kojih su podaci dohvaćeni s tih stranica. Dohvat podataka je napravljen pomoću plugina za Chrome alat naziva Web Scraper. Dohvaćeni podaci o utakmicama su očišćeni koristeći programe napisane u Pythonu. Dodatni podaci su također izračunati korištenjem podataka dobivenih s internet stranica. Pripremljeni podaci su potom korišteni za algoritme strojnog učenja. Algoritam naivnog Bayesovog klasifikatora daje predikciju s točnošću od 71.8%. Algoritam KNN daje predikciju s točnošću od 78.8%

Abstract (english)

In this paper, the procedure of analysing and processing the data of matches of men’s Croatian volleyball competitions is explained. Motivation for the creation of this paper was the need for some kind of prediction for the outcome of future matches. In this paper there are mentioned web pages where the data was found and the ways that data was collected from this pages. Data collection was done by using a Chrome plugin called Web Scraper. The collected data was then cleaned using programs written
in Python. The additional data was also calculated using the data that was collected from the web pages. The prepared data was the used for machine learning algorithms. Naive Bayes classifier algorithm gives prediction with an accuracy of 71.8%. KNN algorithm gives prediction with accuracy of 78.8%.

• Keywords: Odbojka; strojno ucenje; obrada podatka; predikcija ishoda utakmica; ˇ analize podataka
• Keywords (english): Volleyball; machine learning; data processing; match outcome prediction; data analysis
• Language: croatian
• URN:NBN: urn:nbn:hr:168:250100
• Study programme: Title: Computing; Study programme type: university; Study level: undergraduate; Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka računarstva)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Closed access
• Created on: 2023-10-11 09:46:31