Αναλυτική αθλητικών δεδομένων : αξιολόγηση αλγορίθμων μηχανικής μάθησης για την πρόβλεψη νικητήριας ομάδας για το αγγλικό πρωτάθλημα ποδοσφαίρου (EPL)
View/
Abstract
Data mining techniques have been successfully applied in many scientific, industrial and business fields. In the field of professional sports it is known that huge amounts of data are collected for every player, practice, team, game and season, but the effective use of this data is still limited. Many sports organizations are beginning to realize that there is a wealth of untapped knowledge contained in their data and there is a growing interest in techniques to use it. The objective of this study is the development of robust models to predict the winning team of the English league with the highest possible precision using and evaluating the performance of problem-specific supervised machine learning algorithms. Statistics for the twenty two seasons of the English Championship were used which were obtained by using web-scraping method from the transfermarkt website. Both the acquisition of the data and the implementation was done entirely in Python programming language and the level of accuracy achieved during the implementation of the predictive model is 90 %.
Postgraduate Studies Programme
Πληροφοριακά Συστήματα και ΥπηρεσίεςDepartment
Σχολή Τεχνολογιών Πληροφορικής και Επικοινωνιών. Τμήμα Ψηφιακών ΣυστημάτωνNumber of pages
61Language
GreekCollections
Except where otherwise noted, this item's license is described as
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα
Αναφορά Δημιουργού-Μη Εμπορική Χρήση-Όχι Παράγωγα Έργα 3.0 Ελλάδα