Feature Extraction and Aggregation for Predicting the Euro 2016

Research output: Journal contributionsConference article in journalResearchpeer-review


This paper is addressing the challenge of predicting Euro 2016 outcomes. A set of processed features alongside with a new proposed feature are used to train a linear model to compute scores of 24 participating countries. The obtained scores form fwin, lose, drawg probabilities for all possible fixtures. The empirical evaluation until the semi-finals shows that the conceptually simple approach proves accurate for countries with historical data.

Original languageEnglish
JournalCEUR Workshop Proceedings
Issue number1842
Number of pages7
Publication statusPublished - 09.2016
EventMachine Learning and Data Mining for Sports Analytics - MLSA 2016 : ECML/PKDD 2016 workshop - Riva del Garda, Italy
Duration: 19.09.2016 → …
Conference number: 3

Bibliographical note

Session 1. urn:nbn:de:0074-1842-7