Predviđanje rezultata kuglačkih utakmica primjenom metoda nadziranoga učenja

undergraduate thesis

• Title (english): Predicting the 9-pin bowling matches results using supervised learning methods
• Author: Karlo Boroš
• Mentor: Luka Humski (mentor)
• Committee member: Luka Humski (predsjednik povjerenstva)
• Committee member: Ana Šarčević (član povjerenstva)
• Committee member: Frano Škopljanac-Mačina (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2023-07-04, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Tema ovog rada bilo je stvoriti model za predviđanje rezultata kuglačkih utakmica, a pritom naučiti više o analizi zadanog podatkovnog skupa te baratanju istim. Cilj je svakako bio ostvariti predviđanja koja su približna stvarnima i za pojedinačne rezultate i za ekipne. Korišteno je prediktivno modeliranje kao širi skup. Preciznije, do rezultata se došlo pomoću metoda nadziranog učenja. Model je ostvaren u programskom jeziku R. Rezultati su zadovoljavajući. Predviđanje pobjednika utakmice je uspješno u prosječno 3 od 4 utakmice, a pojedinačni rezultati pripadaju prostoru unutar 5 %. Iako prostora za napredak ima, ovaj rad je pokazao kako kuglanje ipak ima konstantu koja se može iskoristiti za predikcije. Budući rad mogao bi se fokusirati na smanjenje pogreške i odstupanja, testiranje drugih metoda i slično, no metoda nadziranog učenja ispostavila se kao dobra metoda za predviđanje kuglačkih rezultata.

Abstract (english)

The aim of this study was to create a model for predicting the outcomes of bowling matches while gaining a deeper understanding of analyzing the given dataset and handling it effectively. The ultimate goal was to achieve predictions that closely resemble the actual results for both individual and team matches. The chosen approach was predictive modeling, specifically utilizing supervised learning methods and the R programming language as the primary tool. The prediction of match winners was successful in approximately 3 out of 4 matches, and individual scores fell within a 5 % margin. Although there is room for improvement, this study demonstrated that predictive methods can be applied to a sport such as bowling. Future research could focus on reducing errors in individual predictions, exploring alternative methods, and so on. Nonetheless, supervised learning has proven to be an effective approach for predicting 9-pin bowling match results.

• Keywords: kuglanje; nadzirano učenje; prediktivno modeliranje; analiza podatkovnih skupova; programski jezik R
• Keywords (english): 9-pin bowling; supervised learning; predictive modeling; data set analysis; R programming language
• Language: croatian
• URN:NBN: urn:nbn:hr:168:324775
• 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: 2023-07-13 09:57:28