The predictive power of ranking systems in association football

  title={The predictive power of ranking systems in association football},
  author={Janusz Lasek and Zolt{\'a}n Szl{\'a}vik and Sandjai Bhulai},
  journal={Int. J. Appl. Pattern Recognit.},
We provide an overview and comparison of predictive capabilities of several methods for ranking association football teams. The main benchmark used is the official FIFA ranking for national teams. The ranking points of teams are turned into predictions that are next evaluated based on their accuracy. This enables us to determine which ranking method is more accurate. The best performing algorithm is a version of the famous Elo rating system that originates from chess player ratings, but… 

Tables from this paper

How to improve a team's position in the FIFA ranking? A simulation study

The efficacy of the official ranking for international football teams compiled by FIFA, the body governing football competition around the globe, is studied by combining several statistical techniques to derive an objective function in a decision problem of optimal scheduling of future matches.

Mathematical model of ranking accuracy and popularity promotion

Four different ranking methods are discussed, including Elo rating system, Betting Odds, FIFA rating based on Elo style and FIFA ratingbased on Davidson Wang's method, with which 36 round-robin matches of UEFA Euro 2016 are analyzed.

An analytics approach to the FIFA ranking procedure and the World Cup final draw

This paper analyzes the procedure used by FIFA up until 2018 to rank national football teams and define by random draw the groups for the initial phase of the World Cup finals and proposes modifications to that procedure guided by a qualitative and statistical analysis of the FIFA ranking.

Searching for the GOAT of tennis win prediction

Testing the predictive performance of 11 published forecasting models for predicting the outcomes of 2395 singles matches during the 2014 season of the Association of Tennis Professionals Tour found regression models based on player ranking and an Elo approach developed by FiveThirtyEight were the most accurate approaches.

Evaluating the efficiency of the association football transfer market using regression based player ratings

It is shown that the performance of players, as reflected in the player ratings, is an important predictor of transfer prices and several other important factors that determine the size of transfer fees are identified.

A football player rating system

The objective of this work was the development of a new rating system for determining the playing strength of football players using the Elo algorithm, which has established itself as an objective and adaptive rating system in numerous individual sports and has been expanded in accordance with the requirements of team sports.

Predicting match outcomes in association football using team ratings and player ratings

The main goal of this article is to compare the performance of team ratings and individual player ratings when trying to forecast match outcomes in association football. The well-known Elo rating

Quantifying the relation between performance and success in soccer

This study analyzes more than 6,000 games and 10 million events in six European leagues and finds that a team's position in a competition's final ranking is significantly related to its typical performance, as described by a set of technical features extracted from the soccer data.



A network-based ranking system for US college football

American college football faces a conflict created by the desire to stage national championship games between the best teams of a season when there is no conventional play-off system for deciding

A Markov Method for Ranking College Football Conferences

The use of mathematical methods to develop rankings of sports teams is certainly not a new idea, but in Division I college football, where the champion is not determined through a playoff system, they are particularly important.

Random Walker Ranking for NCAA Division I-A Football

An alternative algorithm is presented that is simply explained yet remains effective at ranking the best teams, defined in terms of biased random walkers on the graph formed by the schedule of games played, with two teams connected by an edge if they played each other.

On the Forecast Accuracy of Sports Prediction Markets

It is found that prediction markets for the FIFA World Cup outperform predictions based on the FIFA world ranking as well as the random predictor in terms of forecast accuracy.

How I won the "Chess Ratings - Elo vs the Rest of the World" Competition

The rating system that won the kaggle competition “Chess Ratings: Elo vs the rest of the world” aimed to discover whether novel approaches can predict the outcomes of future games, more accurately than the well-known Elo rating system.

TrueSkillTM: A Bayesian Skill Rating System

We present a new Bayesian skill rating system which can be viewed as a generalisation of the Elo system used in Chess. The new system tracks the uncertainty about player skills, explicitly models

The Perron-Frobenius Theorem and the Ranking of Football Teams

The author describes four different methods to rank teams in uneven paired competition and shows how each of these methods depends in some fundamental way on the Perron–Frobenius theorem.

Home Advantage in Turkish Professional Soccer

Match performance data show that although home teams in Turkey take 26% more shots at goal than away teams, the success rates for shots do not differ and for fouls and disciplinary cards, home and away teams do not differences significantly in Turkey, a finding that differs from games in England.

Parameter Estimation in Large Dynamic Paired Comparison Experiments

Paired comparison data in which the abilities or merits of the objects being compared may be changing over time can be modelled as a non‐linear state space model. When the population of objects being