Master's Theses

Department

Computer Science

Degree Name

Master of Science (MS)

Abstract

The market value of professional football players is a critical factor in decision-making for clubs, agents, and analysts. Accurate player valuation impacts transfers, contract negotiations, and financial planning. In recent years, data-driven approaches have emerged to support traditional scouting with predictive analytics. This thesis presents a comparative study of machine learning models to estimate the market value of football players based on historical performance and personal attributes.

This thesis presents a comparative study of two independently developed machine learning systems designed to predict the market value of football players for the 2020–2021 season. Both systems were trained using real data collected from Kaggle: one dataset covering the seasons 2017–2020, and another containing actual market values for the 2020–2021 season. These datasets combine player statistics and performance indicators sourced from Transfermarkt and FBref.

In Project 1, ensemble algorithms such as Random Forest, XGBoost, and Support Vector Regression (SVR) were trained and compared. In Project 2, alternative models including CatBoost, K-Nearest Neighbors (KNN), and Gradient Boosting were explored. Each system selects its best performing model based on Root Mean Square Error (RMSE) and is deployed through a custom built Streamlit interface that supports interactive prediction and analysis.

Predicted values for 2020–2021 were then compared with actual market values from that season, allowing for quantitative evaluation of each project's accuracy. Finally, the results of both projects were compared and analyzed to determine which approach is more suitable for real-world application in football analytics.

This work demonstrates the feasibility of using machine learning for player valuation and provides a practical framework for evaluating multiple modeling strategies in sports data science.

Keywords

football analytics, sports valuation, player market price prediction, regression models, machine learning

Advisor

Dr. Hong Biao Zeng

Date of Award

Summer 2025

Document Type

Thesis

Rights

© The Author

Comments

For questions contact ScholarsRepository@fhsu.edu

Download


Share

COinS