A football player rating system

Abstract

Association football (soccer) is the most popular sport in the world, resulting in a large economic interest from investors, team managers, and betting agencies. For this reason, a vast number of rating systems exists to assess the strength of football teams or individual players. Nevertheless, most of the existing approaches incorporate deficiencies, e. g., that they depend on subjective ratings from experts. The objective of this work was the development of a new rating system for determining the playing strength of football players. The Elo algorithm, which has established itself as an objective and adaptive rating system in numerous individual sports, has been expanded in accordance with the requirements of team sports. Matches from 16 different European domestic leagues, the UEFA Champions and Europa Leagues have been recorded, with more than 17 000 matches played in recent years, and 12 400 different players. The developed rating system produced promising results, when evaluating the matches based on its predictions. A high relevance of the created system results from the fact that only the associated match report is needed and thus—in relation to existing valuation models—significantly more football players can be assessed.

Implementasi Algoritma Elo-rating untuk memprediksi perilaku E-Commerce Item (Studi Kasus pada Olahan Desa Giri Kecamatan Kebomas Kabupaten Gresik)

“…ELO Rating System merupakan suatu metode untuk menghitung tingkat ketrampilan relatif seorang pemain dibandingkan dengan pemain lainnya (Sutanto, Yulianton, & Diartono, 2012). Sistem Elo tidak hanya digunakan pada permainan catur akan tetapi pada permainan lainnya juga (Wolf, Stephan;. Sistem peringkat Elo menjadi salah satu sistem peringkat paling penting pada permainan olahraga, ekonomi, (Bertram, 2021).…”

“…Sistem peringkat Elo menjadi salah satu sistem peringkat paling penting pada permainan olahraga, ekonomi, (Bertram, 2021). Pengembangan sistem peringkat ini telah menjanjikan sebuah hasil berupa evaluasi tentang kecocokan berdasarkan pada prediksinya (Wolf, Stephan;. Berdasarkan pada asumsi pada kinerja yang dimiliki oleh variabel acak (Veisdal, 2019).…”

An alternative ranking system for biathlon pursuit races

“…An alternative pursuit ranking which minors the influence of the sprint results would therefore be of high interest for biathletes and organizers of international biathlon events. Different rankings than official ones have been recently developed in numerous sports, for example for football teams (Gásquez & Rovuela, 2016), for football players (Wolf et al, 2020), for tennis (Kovalchik, 2020), for basketball (Barrow et al, 2013) . .…”

Comparing bottom-up and top-down ratings for individual soccer players

“…Regularized multiple linear regression models have been used frequently for PM ratings, with examples provided by Saebø & Hvattum (2019), Kharrat et al (2020), Pantuso &Hvattum (2020), andHvattum (2020). Wolf et al (2020) proposed a different top-down rating, based on Elo ratings, where player ratings are updated after each match based on the difference between expected scores and actual scores. While no direct comparison has been made between player ratings based on Elo and PM ratings, by being able to exploit information about starting line-ups, both ratings appear to be better than an Elo team rating at predicting the outcomes of matches, as shown by Wolf et al (2020) and Arntzen & Hvattum (2020), respectively.…”

“…Wolf et al (2020) proposed a different top-down rating, based on Elo ratings, where player ratings are updated after each match based on the difference between expected scores and actual scores. While no direct comparison has been made between player ratings based on Elo and PM ratings, by being able to exploit information about starting line-ups, both ratings appear to be better than an Elo team rating at predicting the outcomes of matches, as shown by Wolf et al (2020) and Arntzen & Hvattum (2020), respectively. Pappalardo et al (2019a) discussed a system where the performance of a player is modelled by a feature vector describing the behavior of the player in a match based on observed events.…”