'Setting the Benchmark' Part 4: Contextualising the Match Demands of Teams at the FIFA Women's World Cup Australia and New Zealand 2023

Comparative Analysis of U17, U20, and Senior Football Team Performances in the FIFA World Cup: From Youth to Senior Level

PURPOSE

This study aimed to investigate differences in match physical and technical/tactical performance of teams across different competitive levels in international soccer: FIFA Men's World Cup Qatar 2022 (MWC), FIFA U20 World Cup Argentina 2023 (U20WC), and FIFA U17 World Cup Indonesia 2023 (U17WC).

METHODS

From a total of 168 games, 138 games were analyzed (N = 276 game observations) using an optical tracking system.

RESULTS

On average, the U17WC teams exhibited reduced total running (3% less), high-intensity running (14%-16% less), and sprinting (18%-26% less) distance than the MWC and U20WC teams (P ≤ .0023; effect size [ES]: 0.8-1.5). The MWC teams displayed 4% to 5% higher accuracy in passing and executing line breaks (P ≤ .0188; ES: 0.6-0.7), along with increased offers to receive the ball (53%-118% more) and movements to receive the ball (44%-101% more), and received the ball (61%-137%) more often than the U20WC and U17WC teams (P < .001; ES: 1.1-2.1). Moreover, notable decreases in defensive pressure (-18% to -32%) and forced turnovers (-26% to -32%) were observed in the U17WC than other competitions (P ≤ .0001; ES: 0.8-2.2). Greater variability was observed among the U17WC teams in several metrics, including high-intensity/sprinting distances, attempts at goal, and receptions in the final third.

CONCLUSIONS

These findings demonstrate that as the competitive level increases, so do the physical demands, advanced technical skills, and tactical fluidity/adaptability. However, caution should be exercised when interpreting match performance of younger age groups, as higher variability was evident in both physical and technical/tactical performance in matches.

Goal and shot prediction in ball possessions in FIFA Women's World Cup 2023: a machine learning approach

Introduction

Research in women's football and the use of new game analysis tools have developed significantly in recent years. The objectives of this study were to create two predictive classification models to forecast the occurrence of a shot or a goal in the FIFA Women's World Cup 2023 and to identify the associated technical-tactical indicators to these outcomes.

Methods

A total of 2,346 ball possessions were analyzed using an observational design, mapping two different target variables (Success = Goal and Success2 = Goal or Shot) with a relative frequency of 1.28 and 8.35%, respectively. The predictive capacity was tested using Random Forest and XGBoost and finally and SHAP values were calculated and visualized to understand the influence of the predictors.

Results

Random Forest technique showed greater efficacy, with recall and sensitivity above 93% in the resampled dataset. However, recall on the original test sample was 13% (Success = Shot or Goal) and 0% (Success = Goal), demonstrating the models' inability to predict rare events in football, such as goals. The indicators with the greatest influence on the outcome of these possessions were related to the possession zone, attack duration, number of passes, and starting zone, among others.

Conclusion

The results highlight the need to incorporate a greater number of predictive variables in the models and underline the difficulty of predicting events such as goals and shots in women's football.