ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Properties of sports competitions and relation to market value

Matic Tribušon (2018) Properties of sports competitions and relation to market value. MSc thesis.

[img]
Preview
PDF
Download (4Mb)

    Abstract

    Sports are a very popular type of entertainment around the world. Consequently, they have become very important from a business perspective. In this thesis, we research the influence of sports competition competitive balance on its market value. The aim is to determine the competitive balance of various sports competitions and explore the correlation between competitive balance and market value of sports competitions. We propose a method for assessing competitive balance of an arbitrary team sport competition. The method is based on network analysis and a version of the PageRank algorithm. As an input, it only requires results of played matches in the observed sports competition and the output is an index of competitive balance. We compare the proposed method with Massey's method and evaluate the results. We also propose different metrics that are related to market value of sports competitions and research the correlation between the competitive balance, obtained with the proposed method, and the mentioned metrics. The results of competitive balance analysis confirm the hypothesis that North American sports competitions are more balanced. From the results of correlation analysis it is clear that the chosen time period was too short for per-season correlation analysis. Thus, the confidence intervals of correlation results are too wide. Correlation analysis on per-game basis confirms the hypothesis that competitive balance of sports competitions has a positive effect on their market value.

    Item Type: Thesis (MSc thesis)
    Keywords: network analysis, PageRank, sports competitions, competitive balance, market value
    Number of Pages: 81
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    doc. dr. Lovro ŠubeljMentor
    doc. dr. Erik Štrumbelj5570Comentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537698755)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 4035
    Date Deposited: 10 Jan 2018 11:23
    Last Modified: 25 Jan 2018 13:21
    URI: http://eprints.fri.uni-lj.si/id/eprint/4035

    Actions (login required)

    View Item