Primjena metoda dubinske analize u domeni igara na sreću

master's thesis

• Title (english): Applying Data Mining Methods to the Business Field of Games of Chance
• Author: Ante Gojsalić
• Mentor: Damir Pintar (mentor)
• Committee member: Damir Pintar (predsjednik povjerenstva)
• Committee member: Boris Vrdoljak (član povjerenstva)
• Committee member: Mihaela Vranić (član povjerenstva)
• Granter: University of Zagreb; Faculty of Electrical Engineering and Computing; Zagreb
• Defense date and country: 2016-07-08, Croatia
• Scientific / art field, discipline and subdiscipline: TECHNICAL SCIENCES; Computing

Abstract

U ovom radu predstavljamo metode analize i predikcije vezane uz sportsko klađenje. Koristeći različite skupove podataka pokazali smo što sve utječe na izmjene vjerojatnosti osvajanja meča. Koristeći Markovljevu pretpostavku da je vjerojatnost osvajanja poena konstantna tijekom cijelog meča izveli smo vjerojatnosni model za klađenje uživo u odbojci. Usput smo pokazali kako različite strategije klađenja ovise o vremenski razdvojenim podatkovnim skupovima te na koji način se može upotrebljavati izvedeni vjerojatnosni model u praksi. Za kraj smo pomoću metoda nadziranog strojnog učenja pokušali aproksimirati izmjenu koeficijenata te izradom jednostavnih aplikacija pokazali usporedbu svih modela.

Abstract (english)

In this work we present analysis and prediction methods with applications in sports betting. By using different datasets we analysed how winning probbability changes depending on numerous features. With Markovian assumption that rally winning probability is contsant during the match we derived probabilistic model for live volleyball betting. We showed examples of using our probabilistic model against real world live betting algorithms by deriving multiple betting strategies which we validated on timely-separated datasets. Furthermore we observed how supervised machine learning can be used to approximate live coeficient changing.

• Keywords: Dubinska analiza; sportsko klađenje; Markovljev lanac; odbojka
• Keywords (english): Data mining; sport betting; Markov chain; volleyball
• Language: croatian
• URN:NBN: urn:nbn:hr:168:608682
• 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: 2018-02-06 08:56:08