POSTGRADUATE IN SPORTS ANALYTICS

Organized by:
Backed by:

The postgraduate in Sports Analytics offers a unique opportunity to unify advanced data analysis and the sports passion. The postgraduate is carried out in collaboration with Fútbol Club Barcelona, leading team in data analysis in sports. This collaboration will allow working with first-rate data, event data and tracking data, and in solving applied problems. In addition, students will be able to obtain a real and privileged view of the application of sports analytics in a leading club in this field. The postgraduate program aims to give a global and transversal vision of a data ecosystem applied to the sports field, deepening in data management and data analytics. The postgraduate provides an overview of all the components and tasks involved in the application of sports analytics today.

Icon 01

START DATE

October 2023

Icon 02

COMPLETION DATE

February 2024

Icon 03

DURATION

4 months

Icon 04

LANGUAGE

Spanish

Icon 06

PLACE

Barcelona

Icon 07

CREDITS

15 ECTS

Icon 08

PRICE

€ 4.500

Icon 09

DEGREE

Postgraduate in Sports Analytics

Icon 05

FORMAT

On Campus

TARGET AUDIENCE

Graduates in computer science or equivalent, statistics, mathematics, physics or engineering. Computer professionals, mainly developers, architects, data analysts and system administrators, interested in data management and analytics applied to the sports sector. Those interested must have technical training in centralized databases, programming and statistics.

SYLLABUS

  • Introduction to sport analytics.
  • Introduction to game analysis.
  • Soccer methodology, DNA Barça.
  • Sports analytics in other sports.
  • Advanced data analysis in soccer.
  • Physical performance data.
  • Artificial intelligence applied to basketball.

  • Introduction: Big data, cloud computing and service engineering (XaaS).
  • Data management on cloud databases (NOSQL).
  • Processing and analysis of distributed data.
  • Most used unstructured or semi-structured data models.
  • Streams management.
  • Geospatial data management and trajectories.
  • Integration and data quality.
  • Visualization.

  • Introduction: Basic statistics.
  • Statistical inference, sampling and method validation.
  • Statistical modeling and model calibration.
  • Knowledge discovery in databases and association rules.
  • Principal component analysis.
  • Clustering methods.
  • Decision trees.
  • Time series.
  • Method classification: discriminant analysis and Support Vector Machine (SVM).
  • Neural networks.
  • Convolutianal neural networks.

The objective of this module is to put into practice the concepts explained in the 3 previous modules, starting from the realization of a use case.