Related Experiment Video
Updated: Aug 4, 2025
06:52
An Inertial Measurement Unit Based Method to Estimate Hip and Knee Joint Kinematics in Team Sport Athletes on the Field
Published on: May 26, 2020
8.0K
Expected goals in football: Improving model performance and demonstrating value
James Mead1, Anthony O'Hare1, Paul McMenemy1
1Computing Science and Mathematics, University of Stirling, Stirling, United Kindom.
Plos One
|April 5, 2023
Summary
This study enhances expected goals (xG) modeling in football using machine learning and new features. The improved xG metric predicts team success better than traditional stats and industry standards.
Area of Science:
- Sports Analytics
- Football Performance Analysis
- Machine Learning in Sports
Background:
- Football analytics increasingly uses novel metrics like expected goals (xG) for performance evaluation and financial decisions.
- Traditional xG models lack crucial features such as player/team ability and psychological effects, limiting their trust and accuracy.
- There is a need for more robust xG models that incorporate advanced features and are widely accepted.
Purpose of the Study:
- To develop an enhanced expected goals (xG) model using machine learning techniques.
- To incorporate previously untested features, including player/team ability and psychological factors, into xG modeling.
- To compare the predictive performance of the new xG metric against traditional football statistics and industry benchmarks.
Main Methods:
- Implementation of machine learning algorithms to model expected goals (xG) values.
- Inclusion of novel features (e.g., player/team ability, psychological effects) not typically found in standard xG models.
- Comparative analysis of predictive accuracy between the enhanced xG model, traditional statistics, and existing industry models.
Main Results:
- The developed xG models demonstrated competitive error values compared to optimal benchmarks in existing literature.
- Several newly incorporated features were found to significantly impact the output of the expected goals models.
- The enhanced expected goals metric proved to be a superior predictor of future football team success compared to traditional statistics.
Conclusions:
- Machine learning can significantly improve the accuracy and scope of expected goals (xG) modeling in football.
- Incorporating advanced features enhances the predictive power of xG, leading to more reliable performance evaluations.
- This study's enhanced xG model outperforms both traditional metrics and current industry-leading approaches in predicting football outcomes.
Related Concept Videos
01:04Social Facilitation
32.0K
Not all intergroup interactions lead to negative outcomes. Sometimes, being in a group situation can improve performance. Social facilitation occurs when an individual performs better when an audience is watching than when the individual performs the behavior alone. This typically occurs when people are performing a task for which they are skilled.
32.0K
01:26Modeling in Therapy
130
Modeling, a key technique in therapy, uses observational learning to help clients acquire and practice new skills by watching therapists demonstrate desired behaviors. This approach, rooted in Albert Bandura's concept of vicarious learning, plays a significant role in therapeutic interventions for various psychological conditions, including social anxiety, ADHD, and depression.
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...
Participant Modeling
Participant modeling involves therapists demonstrating calm and effective behaviors in...
130
01:12Modeling and Similitude
307
Scaled modeling is a fundamental technique in engineering, enabling the study of large and complex systems by creating smaller, manageable replicas that recreate critical characteristics of the original. In hydrology and civil infrastructure, for example, scaled models of dams help analyze water flow, turbulence, and pressure. This method allows for accurate predictions of real-world behavior within a controlled environment, significantly reducing the cost and time involved in full-scale...
307
01:23Motion of a Projectile
963
Projectile motion becomes evident when a player kicks the ball into the air. The launch angle, or the angle at which the ball is kicked, plays a crucial role in determining the trajectory of the projectile. As the ball soars through the air, influenced solely by gravity, its motion can be dissected into two independent velocity components: the horizontal and the vertical.
Horizontal motion, governed by the initial kick, maintains a constant velocity throughout the flight of the soccer ball.
Horizontal motion, governed by the initial kick, maintains a constant velocity throughout the flight of the soccer ball.
963
03:00Self-Evaluation: Self-Enhancement and Self-Verification
5.2K
Social psychologists have documented that feeling good about ourselves and maintaining positive self-esteem is a powerful motivator of human behavior (Tavris & Aronson, 2008). In the United States, members of the predominant culture typically think very highly of themselves and view themselves as good people who are above average on many desirable traits (Ehrlinger, Gilovich, & Ross, 2005). Often, our behavior, attitudes, and beliefs are affected when we experience a threat to our...
5.2K
01:10Standard Deviation
17.0K
The most commonly used measure of variation is the standard deviation. It is a numerical value measuring how far data values are from their mean. The standard deviation value is small when the data are concentrated close to the mean, exhibiting slight variation or spread. The standard deviation value is never negative, it is either positive or zero. The standard deviation is larger when the data values are more spread out from the mean, which means the data values are exhibiting more variation.
17.0K