Vrednotenje napada v košarki na podlagi prostorsko-časovnih podatkov o gibanju igralcev

KRIVEC, JAN (author), Kononenko, Igor (mentor), Vračar, Petar (comentor)

Namen diplomskega dela je analiza in vrednotenje napada glede na razporeditev igralcev na igrišču ob danem trenutku. Tako sestavimo algoritem, ki za dan trenutek napada poda oceno v obliki vrednosti. Diplomsko nalogo lahko razdelimo na dva večja sklopa. V prvem sestavimo algoritem, ki pretvori podatke SportVU v smiseln potek košarkarske igre, ter opišemo rezultate in težave le-tega. V drugem sklopu najprej pripravimo podatke za modeliranje ter opišemo uporabljene atribute, modele in mere za ocenjevanje. Za modeliranje smo uporabili odločitveno drevo, naključni gozd, logistično regresijo, metodo podpornih vektorjev in umetne nevronske mreže. Le-ti poskušajo predvideti, ali bo naslednje dejanje met, podaja ali preobrat. Glede na dobljene rezultate smo za glavni model izbrali naključni gozd. S pomočjo dobljenega modela sestavimo več hevristik, ki podajo oceno trenutka v napadu. Za boljšo oceno sestavimo tudi modela za napovedovanje smeri podaje in verjetnosti zadetka meta. Hevristike evalviramo na primeru napada in primerjamo vsoto vrednosti hevristik za vsako ekipo z dejansko uvrstitvijo le-teh.

• Language: Slovenian
• Keywords: košarka, strojno učenje, napovedovanje, analiza podatkov
• Work type: Bachelor thesis/paper
• Typology: 2.11 - Undergraduate Thesis
• Organization: FRI - Faculty of Computer and Information Science ; FMF - Faculty of Mathematics and Physics
• Year: 2021
• PID: 20.500.12556/RUL-125232
• COBISS.SI-ID: 54723587
• Publication date in RUL: 09.03.2021

KRIVEC, JAN, 2021, Vrednotenje napada v košarki na podlagi prostorsko-časovnih podatkov o gibanju igralcev [online]. Bachelor’s thesis. [Accessed 22 April 2025]. Retrieved from: https://repozitorij.uni-lj.si/IzpisGradiva.php?lang=eng&id=125232

Secondary language

• Language: English
• Title: Evaluation of basketball attacks based on spatio-temporal data of player movement

Abstract

The aim of the thesis is analysis and evaluation of a basketball attack based on position of players on the court at a certain time. We develop an algorithm, that grades an attack with a value. We can split our thesis into two bigger parts. In the first part we develop an algorithm, that converts SportVU data into a reasonable timeline of a basketball game, and evaluate its results and problems. In the second part we first prepare the data for modeling and we describe attributes, models and different metrics for evaluating the models. For modeling we used a decision tree, random forest, logistic regression, support vector machine and artificial neural networks. We use these models to predict, whether the next action is going to be a shot, a pass or a turnover. Based on given results we chose the random forest as our main model. With the help of this model we compute several heuristics for evaluating a moment during an attack. For a better estimate we also build models for predicting direction of a pass and the probability of taking a successful shot. We evaluate these heuristics on an example attack and we compare the sum of all values given by the heuristics for every team and we compare them to the actual team standings.

• Keywords: basketball, machine learning, prediction, data analysis