What is Expected Goal (xG)?

The expected goal (xG) metric is defined as the probability that a shot will result in a goal. This metric is particularly relevant for a more accurate analysis of a team's performance, as it considers the quality of the scoring opportunities that each team generates, rather than merely analyzing the result. The widespread use of this metric in examining the performance of football and soccer teams has led to the development of various models for calculating xG, each with a unique approach.

What is this tool?

This is an interactive soccer kick simulation tool that returns different Expected Goals (xG) values from different models found in the literature. This tool enables users to create or import real shots and visualize the discrepancies in xG outcomes between the implemented models.

References

  1. Rathke, Alex. "An Examination of Expected Goals and Shot Efficiency in Soccer." Journal of Human Sport and Exercise, vol. 12, no. 2, 2017, pp. 514–529. Available here.
  2. Anzer, Gabriel; Bauer, Pascal. "A Goal Scoring Probability Model for Shots Based on Synchronized Positional and Event Data in Football (Soccer)." Frontiers in Sports and Active Living, Lausanne, vol. 3, pp. 1–15, 2021. Available here.
  3. Karim, Hassani; Marwane, Lotfi. "The Kos Angle, an optimizing parameter for football expected goals (xG) models." International Journal of Computer Science in Sport, [s.l.], vol. 22, no. 2, pp. 49–61, 2023. Available here.
  4. NARAYANAN, Sachin; PIFER, N. David. "An xG of Their Own: Using Expected Goals to Explore the Analytical Shortcomings of Misapplied Gender Schemas in Football." Journal of Sport Management, Champaign, vol. 38, no. 2, pp. 92–109, 2024. Available here.
  5. Matteotti, Matteo; Sotudeh, Hadi. "The Power of Pixels: Exploring the Potential of CNNs for Expected Goals (xG) in Football." [S.n.]. No prelo. Available here.
  6. Hewitt, James H.; Karakuş, Oktay. "A machine learning approach for player and position adjusted expected goals in football (soccer)." Franklin Open, Filadélfia, vol. 4, pp. 1–16, 2023. Available here.