Quantifying Football Shooting Precision: The Expected Shot Impact Timing (xSIT) Approach

Background: Current advanced metrics do not sufficiently isolate and quantify the quality of the shooter’s technical execution under match conditions. Objective: This study aimed to develop an Expected Shot Impact Timing (xSIT) model to evaluate the shooting action by considering the spatial configuration of the shooter, the goalkeeper (GK), and all outfield players, as well as incorporating dynamic variables such as ball velocity and player reaction time. Additionally, this study sought to compare the performance and discriminative capacity of two existing post-shot expected goal metrics (xSIT and xGOT, expected goals on target) in evaluating the probability of scoring for shots on target after the moment of execution. Methods: Formal definitions were established for the following: (i) the ball shot location, (ii) the ball velocity, (iii) the GK location, and (iv) the outfield player’s location. An xSIT model incorporating geometric parameters was designed to optimize performance based on ball position and players’ position. The model was tested using all shots from the 2023 Women’s World Cup and the 2022 Men’s World Cup. A 5-fold cross-validation procedure was applied to evaluate the x SIT model’s performance, and an independent Student’s t-test was performed to statistically compare the performance of the xSIT and xGOT models. Results: The k-fold cross-validation yielded an AUC-ROC score of 0.92 and 84% accuracy, confirming the model’s ability to differentiate successful shooter performance. Statistically and clinically significant differences were observed between the xSIT and xGOT metrics across all analyzed variables, including total shots on target, goal shots, and saved shots (p < 0.001 in all cases). Conclusions: The xSIT metric offers a more nuanced and context-sensitive assessment of shot execution by the shooter, representing a significant advancement over existing post-shot evaluation models. Significant differences were observed between men’s and women’s tournaments.

Authors

Institutions

Publication Details

Journal
Applied Sciences
Published
2025-06-16
DOI
https://doi.org/10.3390/app15126735
Citations
1
Primary Topic
Sports Performance and Training
Type
article
Field-Weighted Citation Impact
1.72
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

Quantifying Football Shooting Precision: The Expected Shot Impact Timing (xSIT) Approach

Blanca De-la-Cruz-Torres, Anselmo Ruiz-de-Alarcón-Quintero, Miguel Navarro-Castro
1 citations
Applied Sciences
Sports Performance and Training
1.72
article

Quantifying Football Shooting Precision: The Expected Shot Impact Timing (xSIT) Approach

Blanca De-la-Cruz-Torres, Anselmo Ruiz-de-Alarcón-Quintero, Miguel Navarro-Castro
article en
1 citations

Abstract

Background: Current advanced metrics do not sufficiently isolate and quantify the quality of the shooter’s technical execution under match conditions. Objective: This study aimed to develop an Expected Shot Impact Timing (xSIT) model to evaluate the shooting action by considering the spatial configuration of the shooter, the goalkeeper (GK), and all outfield players, as well as incorporating dynamic variables such as ball velocity and player reaction time. Additionally, this study sought to compare the performance and discriminative capacity of two existing post-shot expected goal metrics (xSIT and xGOT, expected goals on target) in evaluating the probability of scoring for shots on target after the moment of execution. Methods: Formal definitions were established for the following: (i) the ball shot location, (ii) the ball velocity, (iii) the GK location, and (iv) the outfield player’s location. An xSIT model incorporating geometric parameters was designed to optimize performance based on ball position and players’ position. The model was tested using all shots from the 2023 Women’s World Cup and the 2022 Men’s World Cup. A 5-fold cross-validation procedure was applied to evaluate the x SIT model’s performance, and an independent Student’s t-test was performed to statistically compare the performance of the xSIT and xGOT models. Results: The k-fold cross-validation yielded an AUC-ROC score of 0.92 and 84% accuracy, confirming the model’s ability to differentiate successful shooter performance. Statistically and clinically significant differences were observed between the xSIT and xGOT metrics across all analyzed variables, including total shots on target, goal shots, and saved shots (p < 0.001 in all cases). Conclusions: The xSIT metric offers a more nuanced and context-sensitive assessment of shot execution by the shooter, representing a significant advancement over existing post-shot evaluation models. Significant differences were observed between men’s and women’s tournaments.

Applied SciencesVol. 15(12)
Universidad de Sevilla (ES)
Openalex Percentile: Top 18%
Sports Performance and Training
1.72
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.