Football data analytics: the science of talent: machine learning predictions for player scouting

Albertini, Domenico (A.A. 2023/2024) Football data analytics: the science of talent: machine learning predictions for player scouting. Tesi di Laurea in Data science in action, Luiss Guido Carli, relatore Alessio Martino, pp. 157. [Master's Degree Thesis]

[img]
Preview
PDF (Full text)
Download (11MB) | Preview

Abstract/Index

Modern football scouting scenario: the need for a data-driven approach. Literature review. The role of machine learning and data analytics in sports. The growing role of data science in football. Machine learning in scouting and recruitment: a literature review. Bridging the gaps in football scouting: towards a more effective player identification. Data collection methodology and dataset structure. Data collection tool: the API. Dataset creation. Data preparation: cleaning, sorting and generation of derived variables. Data cleaning. Generation of additional variables. Feature engineering: construction of performance indices. Development of performance indices. In-depth performance indices. Performance indices validation. Introduction to validation. Classification models: implementation and results. Benchmarking against raw features: testing models without indices. Designing a practical and efficient scouting model. Evaluating model options for player scouting. From input to output: from user query to actionable model results. Final in-depth player comparison visualization. Real-world use cases in football scouting: testing the model and player analysis. Testing the model on attackers. Testing the model on midfielfers. Testing the model on defenders.

References

Bibliografia: pp. 137-140.

Thesis Type: Master's Degree Thesis
Institution: Luiss Guido Carli
Degree Program: Master's Degree Programs > Master's Degree Program in Data Science e Management (LM-91)
Chair: Data science in action
Thesis Supervisor: Martino, Alessio
Thesis Co-Supervisor: Spagnoletti, Paolo
Academic Year: 2023/2024
Session: Extraordinary
Deposited by: Alessandro Perfetti
Date Deposited: 10 Jul 2025 10:55
Last Modified: 10 Jul 2025 10:55
URI: https://tesi.luiss.it/id/eprint/42873

Downloads

Downloads per month over past year

Repository Staff Only

View Item View Item