Match Analysis, Data Analytics and Artificial Intelligence in Sport
A.Y. 2026/2027
Learning objectives
The course aims to:
1) provide students with scientific, theoretical, and technical-practical skills concerning the relevance and validity of methods, procedures, and data analysis for monitoring training and competition, as well as the evaluation of the various components of sports performance, including through the use of video tools;
2) train professionals capable of collecting, processing, and interpreting sports data to support the decision-making processes of coaching and management staff. The course will explore the evolution of Video and Match Analysis, from notational analysis to complex models based on large databases (Big Data). Furthermore, it will provide an in-depth look at video analysis applications aimed at coaching, scouting, and talent development, while providing the foundations for the use of and interaction with artificial intelligence agents.
1) provide students with scientific, theoretical, and technical-practical skills concerning the relevance and validity of methods, procedures, and data analysis for monitoring training and competition, as well as the evaluation of the various components of sports performance, including through the use of video tools;
2) train professionals capable of collecting, processing, and interpreting sports data to support the decision-making processes of coaching and management staff. The course will explore the evolution of Video and Match Analysis, from notational analysis to complex models based on large databases (Big Data). Furthermore, it will provide an in-depth look at video analysis applications aimed at coaching, scouting, and talent development, while providing the foundations for the use of and interaction with artificial intelligence agents.
Expected learning outcomes
By the end of the course, students will have acquired data collection, analysis, and management skills, the ability to use basic video editing tools, and the capability to use artificial intelligence models for creating reports and dashboards. Furthermore, they will have developed competencies aimed at organizing and managing evaluation aspects in both educational contexts and those related to sports performance.
Lesson period: First semester
Assessment methods: Esame
Assessment result: voto verbalizzato in trentesimi
Single course
This course cannot be attended as a single course. Please check our list of single courses to find the ones available for enrolment.
Course syllabus and organization
Single session
Responsible
Lesson period
First semester
Course syllabus
Data Analysis Module (Prof. Caumo)
1. Structure of a scientific paper and the role of data analysis
2. Descriptive statistics: tables, graphs, measures of central tendency and variability (mean, variance, standard deviation, median, percentiles, quartiles)
3. Gaussian distribution
4. Basics of inferential statistics:
* population and sample
* estimation of mean and variance
* central limit theorem
* sampling distributions and standard error
* Student's t distribution
* confidence intervals
5. Hypothesis testing and statistical significance; type I and type II errors
6. One-sample tests
7. Paired sample t-test
8. Independent sample t-test
9. Analysis of variance (ANOVA) and Fisher's F distribution; introduction to repeated measures ANOVA
10. Non-parametric alternatives (rank-based tests)
11. Correlation and regression
12. Categorical data analysis: chi-square test for independence
Match Analysis and Artificial Intelligence Module (Prof. Zago)
1. Foundations of video and data analysis
* evolution of match analysis: from notational analysis to modern multi-level analysis
* theoretical vs practical performance analysis
* technologies: functioning, advantages, and limitations of tracking systems
* types of sports data: event, tracking, wearable, video, contextual
* professional roles in elite sport
2. Video and tactical match analysis
* tactical behaviour and game pattern analysis
* qualitative game analysis and tactical deconstruction
* video editing lab: segmentation of key clips and playlist creation
* video-based training: communicating analysis to players
3. AI, prompt engineering and data visualisation
* data organisation and coding of game actions
* introduction to AI in sport: supervised/unsupervised learning, generative AI, LLMs
* prompt engineering: interacting with LLMs for data querying, report generation, and tactical synthesis; limitations and risks
* data visualisation lab: creating dashboards and infographics for decision-making
4. Trend analysis in sport
* evolution of match analysis in research and practice
* dynamical systems theory applied to team sports
* interdisciplinary comparison across team sports and transferability of performance metrics
1. Structure of a scientific paper and the role of data analysis
2. Descriptive statistics: tables, graphs, measures of central tendency and variability (mean, variance, standard deviation, median, percentiles, quartiles)
3. Gaussian distribution
4. Basics of inferential statistics:
* population and sample
* estimation of mean and variance
* central limit theorem
* sampling distributions and standard error
* Student's t distribution
* confidence intervals
5. Hypothesis testing and statistical significance; type I and type II errors
6. One-sample tests
7. Paired sample t-test
8. Independent sample t-test
9. Analysis of variance (ANOVA) and Fisher's F distribution; introduction to repeated measures ANOVA
10. Non-parametric alternatives (rank-based tests)
11. Correlation and regression
12. Categorical data analysis: chi-square test for independence
Match Analysis and Artificial Intelligence Module (Prof. Zago)
1. Foundations of video and data analysis
* evolution of match analysis: from notational analysis to modern multi-level analysis
* theoretical vs practical performance analysis
* technologies: functioning, advantages, and limitations of tracking systems
* types of sports data: event, tracking, wearable, video, contextual
* professional roles in elite sport
2. Video and tactical match analysis
* tactical behaviour and game pattern analysis
* qualitative game analysis and tactical deconstruction
* video editing lab: segmentation of key clips and playlist creation
* video-based training: communicating analysis to players
3. AI, prompt engineering and data visualisation
* data organisation and coding of game actions
* introduction to AI in sport: supervised/unsupervised learning, generative AI, LLMs
* prompt engineering: interacting with LLMs for data querying, report generation, and tactical synthesis; limitations and risks
* data visualisation lab: creating dashboards and infographics for decision-making
4. Trend analysis in sport
* evolution of match analysis in research and practice
* dynamical systems theory applied to team sports
* interdisciplinary comparison across team sports and transferability of performance metrics
Prerequisites for admission
· Basic knowledge of Training Theory and Methodology.
· Basic mathematics at upper secondary school level
· Familiarity with the use of computer tools and spreadsheets.
· Basic mathematics at upper secondary school level
· Familiarity with the use of computer tools and spreadsheets.
Teaching methods
· Lectures: To provide the theoretical framework of the subject.
· Computer Labs and Practical Sessions: Use of video analysis software (tagging) and data analysis platforms to simulate the work of a match analyst in detecting and coding game actions using real cases from professional sports.
· Group Work and Peer Briefing/Debriefing: Collective interpretation of video clips and positional data, simulating the interaction between the Match Analyst and the coaching staff.
· Computer Labs and Practical Sessions: Use of video analysis software (tagging) and data analysis platforms to simulate the work of a match analyst in detecting and coding game actions using real cases from professional sports.
· Group Work and Peer Briefing/Debriefing: Collective interpretation of video clips and positional data, simulating the interaction between the Match Analyst and the coaching staff.
Teaching Resources
The Data Analysis module does not require a mandatory textbook, as materials uploaded on myAriel are sufficient. Recommended texts include:
· Marc Triola & Mario Triola - Biostatistics for the Biological and Health Sciences (Pearson)
· S. A. Glantz - Primer of Biostatistics (McGraw-Hill)
· David S. Moore - Basic Practice of Statistics (Apogeo / international editions)
For the Match Analysis and Artificial Intelligence module, besides provided presentations and papers, the following books are suggested:
· Performance Analysis in Team Sports (2018), Calzetti & Mariucci
· Match Analysis: How to Use Data in Professional Sport (2021), Taylor & Francis
· Essentials of Performance Analysis in Sport (3rd ed., 2019), Taylor & Francis
· Marc Triola & Mario Triola - Biostatistics for the Biological and Health Sciences (Pearson)
· S. A. Glantz - Primer of Biostatistics (McGraw-Hill)
· David S. Moore - Basic Practice of Statistics (Apogeo / international editions)
For the Match Analysis and Artificial Intelligence module, besides provided presentations and papers, the following books are suggested:
· Performance Analysis in Team Sports (2018), Calzetti & Mariucci
· Match Analysis: How to Use Data in Professional Sport (2021), Taylor & Francis
· Essentials of Performance Analysis in Sport (3rd ed., 2019), Taylor & Francis
Assessment methods and Criteria
Data Analysis module: written exam with 31 multiple-choice questions (60 minutes). Grading scheme: 31 correct answers: 30/30 with honours, 30 correct answers: 30/30, 29 correct answers: 29/30, and so on.
Match Analysis and Artificial Intelligence module: practical assignment including video analysis of a match and data presentation. Students must produce a video summary, a report, and a visual dashboard including performance indicators and practical outcomes.
Match Analysis and Artificial Intelligence module: practical assignment including video analysis of a match and data presentation. Students must produce a video summary, a report, and a visual dashboard including performance indicators and practical outcomes.
IBIO-01/A - Bioengineering - University credits: 3
MEDF-01/B - Sport Sciences and Methodology - University credits: 3
MEDF-01/B - Sport Sciences and Methodology - University credits: 3
Exercises: 48 hours
Lessons: 12 hours
Lessons: 12 hours
Professors:
Caumo Andrea, Zago Matteo
Professor(s)
Reception:
To be arranged via e-mail
Via Colombo 71, 20133 Milano