Profiliranje igrača na temelju in-play podataka teniskih mečeva

undergraduate thesis

• Title (english): Player Profiling Based on In-play Data of Tennis Matches
• Author: Dominik Ćurić
• Mentor: Damir Pintar (mentor)
• Committee member: Damir Pintar (predsjednik povjerenstva)
• Committee member: Luka Humski (član povjerenstva)
• Committee member: Ana Šarčević (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2021-07-06, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

Ovaj rad na temelju povijesno dostupnih podataka vezanih uz teniske mečeve modelira profile igrača s karakteristikama koje se mogu koristiti prilikom prediktivnog modeliranja.Prvi dio rada predstavlja osnovna pravila tenisa, podzadinu prediktivnog modeliranja te statističku analizu podataka koja se koristi prilikom prikaza rezultata.U drugom dijelu rada prikazani su i analizirani rezultati karakteristika dobivenih prilikom izgradnje profila te predloženi modeli za prediktivno modeliranje. Modeli u obzir uzimaju vjerojatnosti osvajanja poena na vlastitom i protivničkom servisu, vjerojatnost osvajanja gamea, vjerojatnost osvajanja seta te vjerojatnost osvajanja meča. U zadnjem dijelu obrađena je tema zamaha koji je modeliran kao uvjetna vjerojatnost. Na temelju tako modeliranog zamaha te deskriptivne analize predloženi su dodatni parametri koji bi se uzimali u obzir prilikom predikcije teniskih mečeva.

Abstract (english)

This paper forms profiles of the players with characteristics that could be used for predictive modeling based on the data available throughout the history of the tennis matches. First part of the paper presents basic tennis rules, the background of the predictive modeling, data analysis process description and statistical analysis of the data used in result presenting. The second part shows results that were created by profile forming; and suggested models for predictive modeling. Models take in consideration the probabilities of winning the point in the opponent's or in own serve, the probability of winning the game, the probability of winning set and the probability of winning match. Topic of momentum is described in the last section. It's modeled as conditioned probability. Based on descriptive analysis of momentum modeled in that way, additional parameters that would be considered whilst predicting tennis matches are given.

• Keywords: Tenis; Prediktivno modeliranje; Markovljev lanac; Statistička analiza podataka Profiliranje
• Keywords (english): Tennis; Predictive modeling; Markov chain; Statistical data analysis; Profiling
• Language: croatian
• URN:NBN: urn:nbn:hr:168:025140
• 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: 2023-01-15 09:57:26