• Login
    View Item 
    •   Home
    • Brock Theses
    • Masters Theses
    • M.Sc. Mathematics and Statistics
    • View Item
    •   Home
    • Brock Theses
    • Masters Theses
    • M.Sc. Mathematics and Statistics
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of BrockUCommunitiesPublication DateAuthorsTitlesSubjectsThis CollectionPublication DateAuthorsTitlesSubjectsProfilesView

    My Account

    LoginRegister

    Statistics

    Display statistics

    When Moneyball Meets the Beautiful Game: A Predictive Analytics Approach to Exploring Key Drivers for Soccer Player Valuation

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    Brock_Li_Yisheng_2021.pdf
    Size:
    1.686Mb
    Format:
    PDF
    Download
    Author
    Li, Yisheng
    Keyword
    Moneyball, sports analytics, player valuation, predictive modeling, interpretable machine learning
    
    Metadata
    Show full item record
    URI
    http://hdl.handle.net/10464/15088
    Abstract
    To measure the market value of a professional soccer (i.e., association football) player is of great interest to soccer clubs. Several gaps emerge from the existing soccer transfer market research. Economics literature only tests the underlying hypotheses between a player’s market value or wage and a few economic factors. Finance literature provides very theoretical pricing frameworks. Sports science literature uncovers numerous pertinent attributes and skills but gives limited insights into valuation practice. The overarching research question of this work is: what are the key drivers of player valuation in the soccer transfer market? To lay the theoretical foundations of player valuation, this work synthesizes the literature in market efficiency and equilibrium conditions, pricing theories and risk premium, and sports science. Predictive analytics is the primary methodology in conjunction with open-source data and exploratory analysis. Several machine learning algorithms are evaluated based on the trade-offs between predictive accuracy and model interpretability. XGBoost, the best model for player valuation, yields the lowest RMSE and the highest adjusted R2. SHAP values identify the most important features in the best model both at a collective level and at an individual level. This work shows a handful of fundamental economic and risk factors have more substantial effect on player valuation than a large number of sports science factors. Within sports science factors, general physiological and psychological attributes appear to be more important than soccer-specific skills. Theoretically, this work proposes a conceptual framework for soccer player valuation that unifies sports business research and sports science research. Empirically, the predictive analytics methodology deepens our understanding of the value drivers of soccer players. Practically, this work enhances transparency and interpretability in the valuation process and could be extended into a player recommender framework for talent scouting. In summary, this work has demonstrated that the application of analytics can improve decision-making efficiency in player acquisition and profitability of soccer clubs.
    Collections
    M.Sc. Mathematics and Statistics

    entitlement

     
    DSpace software (copyright © 2002 - 2023)  DuraSpace
    Quick Guide | Contact Us
    Open Repository is a service operated by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.