search query: @keyword Kalman filter / total: 20
reference: 6 / 20
« previous | next »
Author:Purhonen, Juha
Title:Koripallo-otteluiden lopputulosten ennustaminen ottelutilastojen perusteella
Predicting outcomes of basketball games based on box score statistics
Publication type:Master's thesis
Publication year:2010
Pages:[10] + 62      Language:   fin
Department/School:Informaatio- ja luonnontieteiden tiedekunta
Main subject:Laskennallinen tekniikka   (S-114)
Supervisor:Lampinen, Jouko
Instructor:Lampinen, Jouko
OEVS:
Electronic archive copy is available via Aalto Thesis Database.
Instructions

Reading digital theses in the closed network of the Aalto University Harald Herlin Learning Centre

In the closed network of Learning Centre you can read digital and digitized theses not available in the open network.

The Learning Centre contact details and opening hours: https://learningcentre.aalto.fi/en/harald-herlin-learning-centre/

You can read theses on the Learning Centre customer computers, which are available on all floors.

Logging on to the customer computers

  • Aalto University staff members log on to the customer computer using the Aalto username and password.
  • Other customers log on using a shared username and password.

Opening a thesis

  • On the desktop of the customer computers, you will find an icon titled:

    Aalto Thesis Database

  • Click on the icon to search for and open the thesis you are looking for from Aaltodoc database. You can find the thesis file by clicking the link on the OEV or OEVS field.

Reading the thesis

  • You can either print the thesis or read it on the customer computer screen.
  • You cannot save the thesis file on a flash drive or email it.
  • You cannot copy text or images from the file.
  • You cannot edit the file.

Printing the thesis

  • You can print the thesis for your personal study or research use.
  • Aalto University students and staff members may print black-and-white prints on the PrintingPoint devices when using the computer with personal Aalto username and password. Color printing is possible using the printer u90203-psc3, which is located near the customer service. Color printing is subject to a charge to Aalto University students and staff members.
  • Other customers can use the printer u90203-psc3. All printing is subject to a charge to non-University members.
Location:P1 Ark Aalto     | Archive
Keywords:basketball
Bayesian inference
Kalman filter
multiple model approach
prediction
state space model
bayesiläinen päättely
ennustaminen
Kalman-suodin
koripallo
tila-avaruusmalli
usean mallin lähestymistapa
Abstract (eng): This thesis is about predicting the outcomes of basketball games.
In earlier studies, several methods have been proposed for predicting the outcomes based on the outcomes of the previously played games.
However, the outcomes of the games are heavily affected by chance.
Therefore, it is possible that in addition to the points scored by the teams, other statistics listed in the so called box score provide additional information about the relative strengths of the teams.
The goal of this thesis is to determine whether the other statistics should be taken into consideration in the predictions.

The study consists of two phases.
In the first phase, the relative strengths of the teams for different aspects of the game at each time step are measured by estimating the so called power ratings.
The relationship between the power ratings and the box score statistics is modelled using a linear Gaussian state space model, which enabies the estimation of the power ratings using methods based on the Kalman filter.
In the second phase of the thesis, the relationship between the power rating estimates and the outcomes is studied using linear regression analysis.

The method is applied for the games played during the NBA regular seasons 2004- 2009.
The results of the study suggest that, in addition to the outcomes of the previously played games, the number of assists and missed field goal attempts should be also taken into account in the predictions.
However, inclusion of these two statistics has a very moderate effect on the predictions given by the model.
Abstract (fin): Tämä diplomityö käsittelee koripallo-otteluiden lopputulosten ennustamista.
Aiemmissa aihetta käsittelevissä tutkimuksissa on esitelty erilaisia menetelmiä lopputulosten ennustamiseen aiemmin sarjassa pelattujen otteluiden lopputulosten perusteella.
Sattuma vaikuttaa kuitenkin merkittävästi otteluiden lopputuloksiin, joten on mahdollista, että muut ottelutilastot antavat lisäinformaatiota joukkueiden välisistä tasoeroista.
Tämän työn tavoitteena on selvittää, kannattaako lopputulosten ennustamisessa huomioida aiempien lopputulosten lisäksi myös muuta ottelukohtaisessa tilastokokoelmassa listattua informaatiota.

Työ koostuu kahdesta vaiheesta.
Työn ensimmäisessä vaiheessa sarjan joukkueiden tasoa eri ajanhetkinä ja pelin eri osa-alueilla mitataan estimoimalla niin kutsuttuja voimalukuja.
Voimalukujen ja ottelutilastojen välistä yhteyttä kuvataan lineaaris-gaussisen tila-avaruusmallin avulla, mikä mahdollistaa voimalukujen estimoinnin Kalman-suotimeen perustuvilla menetelmillä.
Työn toisessa vaiheessa tutkitaan eri ottelutilastojen perusteella laskettujen voimalukuestimaattien yhteyttä otteluiden lopputuloksiin lineaarisen regressioanalyysin avulla.

Menetelmää sovelletaan NBA-sarjassa kausien 2004-2009 aikana pelattuihin runkosarjaotteluihin.
Työn tulokset viittaavat siihen, että koripallotulosten ennustamisessa kannattaisi huomioida aiempien otteluiden pisteiden lisäksi myös koriin johtaneiden syöttöjen ja epäonnistuneiden pelitilanneheittojen lukumäärät.
Kyseisten ottelutilastojen huomiointi vaikuttaa kuitenkin vain melko vähän mallin tuottamiin ennusteisiin.
ED:2010-08-31
INSSI record number: 40341
+ add basket
« previous | next »
INSSI