MASTER’S IN
ARTIFICIAL INTELLIGENCE
APPLIED TO SPORTS

This module provides an in-depth introduction to Artificial Intelligence and Big Data applied to sports, in collaboration with Olocip.

Students will learn how AI transforms decision-making, optimizes performance, and enhances sports management through real-world cases and practical tools. The module addresses challenges in managing sports data by integrating sources such as GPS, eventing, and retail, and explores solutions for analyzing large volumes of data. Taught by Olocip experts, the module combines theory and practice to demonstrate how AI provides competitive advantages in the sports industry.

1. Introduction to Artificial Intelligence
2. Digital transformation and the AI ladder
3. Machine learning
4. AI projects and applications in sports
5. Action value and predictive scouting in football

This module focuses on key techniques and tools for acquiring, processing, and managing sports data, covering the ETL cycle (Extraction, Transformation, and Loading) and access to various sources such as databases and APIs.

Students will learn to work with formats like Excel, XML, JSON, and CSV, and to use data from providers such as Opta, Statsbomb, or Wyscout.

The module explores how to transform raw data into strategic insights using analytical tools to create heatmaps, clusters, or xG models, emphasizing the practical value of real-time sports analysis.

1. Introduction to Data Sources and Providers

2. Use and Management of Databases

3. Data Extraction Techniques (ETL)

4. Data Security and Privacy

5. Data Integration and Quality

This module explores the application of Business Intelligence in sports, focusing on advanced data visualization and storytelling to optimize performance and management.

Students will learn to use tools like Power BI, Tableau, and Python to create interactive and customized visualizations, translating technical data into clear, actionable insights.

The goal is to equip students with the skills to effectively communicate results and support strategic decision-making in technical-medical and sports management environments.

1. Fundamentals of Business Intelligence and Statistics

2. Visualization and BI Tools

3. Effective Communication and Data Storytelling

4. Advanced Sports Analytics

5. Research Methodology

This module introduces Machine Learning applied to sports, from foundational concepts to the implementation of models using Scikit-learn.

Students will learn to explore structured sports data, formulate hypotheses, and develop predictive models.

Key algorithms will be studied to analyze competitions and athletes, transforming data into competitive advantages and enhancing strategic decision-making.

1. 1. Mathematical Foundations of Artificial Intelligence

   2. Scikit-learn Library

   3. Hyperparameter Tuning and Fine-Tuning

   4. Exploration of Advanced Metrics

   5. Machine Learning Model Lifecycle (End-to-End Machine Learning)

   6. A/B Hypothesis Testing and Clustering

   7. Feature Engineering and Linear Models

   8. Predictive Models and Sports Analytics

   9. Kaggle and GitHub Platforms

This module introduces Deep Learning as a key tool for analyzing complex and unstructured data in the sports field, using TensorFlow and Keras.

Students will learn how to build deep neural networks, apply techniques such as transfer learning and image classification, and address challenges like pose estimation and predictive analysis.

The module explores how Deep Learning complements traditional Machine Learning and how its use enhances tactical strategies, pattern recognition in gameplay, and decision-making based on large volumes of sports data.

1. Introduction to Neural Networks

2. Multilayer Perceptron, Backpropagation, and Gradient Descent

3. Convolutional Neural Network (CNN) Architectures and Autoencoders

4. Advanced Techniques for Sparse and Noisy Sports Data

5. Comparison Between Machine Learning and Deep Learning

6. Deep Learning Frameworks and Libraries

7. Use of Collaborative Development Platforms

This module explores the use of Natural Language Processing (NLP) in sports, from sentiment analysis on social media to the automatic generation of sports narratives.

Students will learn to apply advanced models (LLM, RAG) using frameworks like LangChain for tasks such as translation, content generation, and virtual assistants.

Through hands-on projects, students will develop solutions to analyze real-time textual data and enhance fan engagement, bringing strategic and innovative value to the sports environment.

1. Introduction to Natural Language Processing (NLP): Fundamentals and Applications in Sports

2. TensorFlow Text and PyTorch NLP

3. Text Preprocessing: Advanced Text Manipulation Techniques

4. Advanced NLP Models and Text Generation: Use of Large Language Models

5. Sentiment Analysis and Chatbot Implementation: Techniques for Fan Engagement

6. Sports Narrative and Report Automation: Automated Sports Content via NLP

7. NLP Technologies and Software: Tools and Libraries for NLP Development

8. Training and Fine-Tuning NLP Models: Customization and Deployment of Pretrained Models

This module introduces computer vision as a key tool in sports analysis, enabling automatic detection of players, objects, and tactics through advanced metrics extracted from video.

Through practical cases and tools like OpenCV, TensorFlow, and PyTorch, students will learn to build models that interpret complex aspects of the game, such as off-ball movements and automatic tactical analysis.

The approach combines technical skills with innovative applications to transform how sports are trained, played, and analyzed.

1. Introduction to Computer Vision in Sports: Fundamentals and Historical Evolution of Computer Vision

2. Computer Vision Technologies and Tools

3. Practical Applications in Detection and Segmentation of Relevant Objects in Sports Events, Enhancing Understanding and Analysis of Gameplay and Athlete Performance

4. Implementation of Advanced Models – ResNet and YOLO: Details and Practical Applications

5. Video Analysis and Action Recognition: Techniques for Sports Video Analysis

6. Player Tracking and Motion Capture: Tracking Technologies and Motion Analysis

7. Innovation and Technology in Audiovisual Content: Computer Vision in Sports Broadcasting

This module explores how generative artificial intelligence is transforming sports through technologies such as GANs, Transformers, and autoregressive models, applied to synthetic content creation and game strategy simulation.

Students will learn to implement these tools with Python and libraries like TensorFlow, developing systems such as chatbots, simulators, and recognition algorithms.

It also covers vectorization techniques to model complex sports environments with multiple agents, along with the ethical and legal aspects of their application.

The module provides a solid technical foundation to apply generative AI in performance, tactical analysis, and personalization of experiences in sports.

1. Introduction to Generative Artificial Intelligence
2. Python and Machine Learning in Sports
3. Concepts of Generative AI
4. Relevant Technologies and Tools
5. MLOps and Practical Applications of Generative AI
6. Expanded Definition of Generative AI to Include Augmented Reality (AR) and Virtual Reality (VR)
7. Ethics and Legality in Sports AI

This module promotes an entrepreneurial spirit and encourages the creation of creative solutions with real impact on the sports industry. Additionally, it integrates key concepts such as innovation, digital transformation, financial analysis, and evaluation of return on investment (ROI) in sports, providing a practical and strategic experience that prepares students to face real challenges with a transformative vision.

1. Introduction to Carrying Out AI Projects in Sports
2. Essential Guidelines for Project Organization
3. Innovation and Digital Transformation
4. Design Thinking and AI Innovation
5. Financial Modeling and ROI Analysis with AI in Sports
6. Execution of the Master’s Final Project
7. Online Presentation