Primjena strojnog učenja na analizu podataka iz mješovitih borilačkih vještina

master's thesis

• Title (english): Utilizing machine learning for analyzing data from mixed martial arts
• Author: Iva Maria Ivanković
• Mentor: Dario Bojanjac (mentor)
• Committee member: Dario Bojanjac (predsjednik povjerenstva)
• Committee member: Marko Bosiljevac (član povjerenstva)
• Committee member: Sonja Grgić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2024-07-19, Croatia

Abstract

Mješovite borilačke vještine, ili skraćeno MMA, relativno je mlad sport koji se tijekom zadnjeg desetljeća naglo razvio i stekao veliku popularnost, kako u svijetu, tako i u Hrvatskoj i okolnim zemljama. Ovaj rad sadrži sveobuhvatnu analizu podrijetla MMA, dolaska sporta u Europu, kao i nastanak i razvoj hrvatske MMA promocije Fight Nation Championship (FNC), u suradnji s kojom je rad nastao.

U drugom dijelu rada provedena je temeljita analiza podataka o borcima i borbama u velikim svjetskim MMA organizacijama, s posebnim naglaskom na primjenu modela strojnog učenja za predviđanje pobjednika borbe. Primjenom ovih modela na podatke FNC-a, nastali su konkretni prijedlozi vezano za podatke kojima treba posvetiti pažnju prilikom sastavljanja rostera boraca. Napravljena je i analiza marketinških podataka organizacije, što je rezultiralo poslovnim preporukama za daljnji razvoj organizacije u skladu sa strateškim ciljevima, uz detaljne projekcije za budućnost. Kroz ove analize, rad nudi praktične smjernice za poboljšanje učinkovitosti i popularnosti FNC-a, čime doprinosi unapređenju cjelokupne MMA zajednice u Hrvatskoj.

Abstract (english)

Mixed Martial Arts, or MMA, is a relatively young sport that has developed rapidly over the past decade and gained significant popularity, both globally and in Croatia and its surrounding countries. This thesis provides a comprehensive analysis of the origins of MMA, its introduction to Europe, and the emergence and development of the Croatian MMA promotion Fight Nation Championship (FNC), in collaboration with which this thesis was created.

The second part of the thesis presents a thorough analysis of fighter and fight data from major global MMA organizations, with a special focus on the application of machine learning models to predict fight winners. By applying these models to FNC data, concrete recommendations were made regarding which data should be prioritized when assembling the fighter roster. Additionally, an analysis of the organization's marketing data was conducted, resulting in business recommendations for the further development of the organization in line with its strategic goals, along with detailed future projections. Through these analyses, the thesis offers practical guidelines for improving the efficiency and popularity of FNC, thereby contributing to the enhancement of the overall MMA community in Croatia.

• Keywords: strojno učenje; mješovite borilačke vještine; MMA; znanost o podacima
• Keywords (english): machine learning; mixed martial arts; MMA; data science
• Language: croatian
• URN:NBN: urn:nbn:hr:168:725231
• 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: 2024-10-12 20:51:46