MSc DATA
ANALYTICS IN FOOTBALL

A comprehensive introduction to Big Data and AI concepts, highlighting their transformative impact on sports from optimizing team performance to refining talent-recruitment strategies.

1. History and Evolution of AI in Sports
2. State-of-the-Art AI Applications in Sports
3. Design and Implementation of Big Data and AI Projects
4. Programming Languages and Technical Tools for Sports Analytics
5. Emerging Trends in AI and Sports
6. Physical Performance Data and AI
7. Case Studies of AI in Elite Clubs
8. Simulations and Hands-On Exercises
9. Integrating AI into the Sports Ecosystem
10. Professional Impact and Competencies of AI Specialists in Sports

Football cannot be understood without data, as it is the best complement for decisión making. Data providers such as Wyscout, Opta, and Instat are essential for both scouts and analysts within a football club to begin executing their analyses.

They serve as the starting point, and in this module, the focus is on selecting the appropriate performance indicators based on the set objectives and their export. Additionally, the clear differences between providers will be addressed, along with an overview of their internal structure and all the advanced features they offer.

1. Introduction to Data Providers
2. Opta
3. Scout74
4. Instat
5. Wyscout
6. MediaCoach
7. StatsBomb
8. Statistics Portals

The explosion of Big Data in today’s world reaches and must reach the micro level. The scout must not only be familiar with the data providers in the industry and how they function, but also with their more technical content.

 An analysis or tracking process is meaningless if the performance metrics or indicators to be applied are not fully understood. It is essential to know what each metric measures and the scope of each one when analyzing a player’s performance, both in offensive and defensive phases.

1. The Importance of Data at the Micro Level
2. Offensive Metrics: Concept and Interpretation
3. Defensive Metrics: Concept and Interpretation
4. Development and Focus of Advanced Metrics
5. Goalkeeper Evaluation Metrics
6. Real-life Case Study of a Scout’s Application of Metrics

Data analytics now drives sport. Clubs rely on it daily—for training, opponent scouting, injury prevention and transfer evaluation. Specialised tools model vast datasets and present them clearly for coaching staffs; without sharp visualisation, data remains exposed and under-used.

Representing information is as vital as exporting or contextualising it, and companion platforms both visualise and power deeper análisis and processing.

1. Overview of data-analysis tools
2. Best-practice visualisation
3. Tableau
4. Power BI
5. Other options

The analysis of individual player performance requires both objective and subjective perspectives. Mastery of tools like NacSport or Metrica Sports is essential to visually support their technical-tactical skills.

This module focuses on individual videos that justify game patterns at both macro and micro levels. Additionally, understanding the competitive context and the team’s playing model is crucial for a complete analysis.

1. Introduction to video analysis
2. Methodology to optimize and enhance the tools
3. Matrices and transformation of eventing into useful data
4. Real cases of video analysis
5. Building the support structure for the written report

Player monitoring has become essential in football, with many clubs using GPS to track external load and generate large volumes of data. This course explains how to interpret that data to plan and manage training effectively.

You will learn the basics of GPS use, understand its physiological relevance, and define your team’s game demands to design better training programs. The course also covers internal load tools like Rating of

Perceived Exertion (RPE). By the end, you’ll be able to analyze and apply this data to enhance performance and gain a competitive edge.

1. Introduction

• GPS Technology in Sports

2. Theory

• Anatomy and Energy Systems
• Internal Load vs External Load
• Using Data for the Field
• Training Principles

3. APPLICATION of GPS in Football

• Variables and Performance Determination in the Game

Analysts and scouts must do more than collect and filter data: they must also decide how to present it via written reports or staff briefings. Drawing on varied internal and external sources, they need to compile and deliver insights clearly and succinctly so decisions are supported efficiently.

This module equips students with the fundamentals of structuring concise, effective reports and presentations for different audiences.

1. Introduction (communication types, speaker characteristics)
2. Reports (report types)
3. Presentations (types, objectives, and planning)
4. Big Data (data sources, presentation tools)
5. Technological support tools (preparing presentations/reports, image processing)
6. Practical exercise – preparing a football‑related report or presentation

Adequate support for Big Data processes has traditionally relied on data lakes, which store and provide access to information through either relational databases or non‑relational ones such as NoSQL.

Relational structures underpinning RDBMS query languages have dominated the data industry for years. Now, however, it is increasingly necessary to handle unstructured data via non‑SQL storage that enables useful, high‑velocity data flows.

1. Definition, Manipulation and Control: DDL, DML and DCL
2. The data value chain: Data Lake, Data Warehouse, Data Intelligence and Data Science
3. DBMS query languages: Extract, Transform, Load and queries
4. Introduction to Not Only SQL (NoSQL) databases
5. Guided queries vs. Artificial Intelligence
6. Structure and flow of Not Only SQL (NoSQL) databases

R is a leading language for data analysis in BI, data mining and machine learning. Its statistical functions speed data selection, recoding and retrieval, and its many packages generate high‑quality visualisations. With numerous ML algorithms, R is widely used in sports to process event data and turn it into powerful visual insights.

1. Software installation and key libraries
2. Basic R programming
3. Applying the main libraries
4. Data cleaning
5. Pictograms
6. Solved case studies

The academy is the cornerstone of any project in a football club. The future of the teams depends on having a solid structure and methodology, both in terms of coaches and recruitment scouts. The scout figure is crucial in the lower categories and can even become the cornerstone of the entire future projection at the club level. Detecting not only talent but also players who can build a career at the club and instill a sense of belonging is an essential factor. In this whole process, technology is not as established as in professional football, and therefore, the human eye and knowledge of Smart Data will help minimize errors in tracking players to be incorporated into the academy’s technical secretariat.

1. Introduction to Python with the Anaconda environment (Jupyter Notebook)
2. Opening and closing files
3. Basic Python syntax
4. API management
5. Learning key libraries such as Pandas, Matplotlib and NumPy
6. Control structures (if, for, while) and functions
7. DataFrame operations
8. Integration with databases and visualisation tools
9. Fundamentals of web scraping and data cleaning
10. Practical football‑focused exercises

Google predicts that within ten years every organisation will depend on data for strategic decisions. A Good data analyst is not necessarily the finest mathematician but the one who can trace problems to their source, ask the right questions, and apply the most suitable machine‑learning tools to solve them. In this module students take their first steps in machine learning: they will follow the complete workflow, from defining the initial problem to identifying existing solutions, applying them, and evaluating the results. The aim is to consolidate the knowledge gained in Module 5—Python Programming—and the course is organised into progressive stages that help students absorb each concept.

1. Introduction to Machine Learning: Process and Available Models
2. Data Pre‑processing – Preparing the Information
3. Regression Models: Logistic Regression and Linear Regression
4. Classification Models: K‑Nearest Neighbours (KNN)
5. Clustering Models: K‑Means
6. Result‑Evaluation Metrics

The Master’s Final Project will involve selecting one or more of the topics covered during the course, and students are advised to follow a gradual, progressive approach similar to that of the programme itself.