Transfering Targeted Maximum Likelihood Estimation for Causal Inference into Sports Science.

Although causal inference has shown great value in estimating effect sizes in, for instance, physics, medical studies, and economics, it is rarely used in sports science. Targeted Maximum Likelihood Estimation (TMLE) is a modern method for performing causal inference. TMLE is forgiving in the misspecification of the causal model and improves the estimation of effect sizes using machine-learning methods. We demonstrate the advantage of TMLE in sports science by comparing the calculated effect size with a Generalized Linear Model (GLM). In this study, we introduce TMLE and provide a roadmap for making causal inference and apply the roadmap along with the methods mentioned above in a simulation study and case study investigating the influence of substitutions on the physical performance of the entire soccer team (i.e., the effect size of substitutions on the total physical performance). We construct a causal model, a misspecified causal model, a simulation dataset, and an observed tracking dataset of individual players from 302 elite soccer matches. The simulation dataset results show that TMLE outperforms GLM in estimating the effect size of the substitutions on the total physical performance. Furthermore, TMLE is most robust against model misspecification in both the simulation and the tracking dataset. However, independent of the method used in the tracking dataset, it was found that substitutes increase the physical performance of the entire soccer team.

Early Prediction of Physical Performance in Elite Soccer Matches-A Machine Learning Approach to Support Substitutions.

Substitution is an essential tool for a coach to influence the match. Factors like the injury of a player, required tactical changes, or underperformance of a player initiates substitutions. This study aims to predict the physical performance of individual players in an early phase of the match to provide additional information to the coach for his decision on substitutions. Tracking data of individual players, except for goalkeepers, from 302 elite soccer matches of the Dutch 'Eredivisie' 2018-2019 season were used to enable the prediction of the individual physical performance. The players' physical performance is expressed in the variables distance covered, distance in speed category, and energy expenditure in power category. The individualized normalized variables were used to build machine learning models that predict whether players will achieve 100%, 95%, or 90% of their average physical performance in a match. The tree-based algorithms Random Forest and Decision Tree were applied to build the models. A simple Naïve Bayes algorithm was used as the baseline model to support the superiority of the tree-based algorithms. The machine learning technique Random Forest combined with the variable energy expenditure in the power category was the most precise. The combination of Random Forest and energy expenditure in the power category resulted in precision in predicting performance and underperformance after 15 min in a match, and the values were 0.91, 0.88, and 0.92 for the thresholds 100%, 95%, and 90%, respectively. To conclude, it is possible to predict the physical performance of individual players in an early phase of the match. These findings offer opportunities to support coaches in making more informed decisions on player substitutions in elite soccer.

Personalized Physical Activity Coaching: A Machine Learning Approach.

Living a sedentary lifestyle is one of the major causes of numerous health problems. To encourage employees to lead a less sedentary life, the Hanze University started a health promotion program. One of the interventions in the program was the use of an activity tracker to record participants' daily step count. The daily step count served as input for a fortnightly coaching session. In this paper, we investigate the possibility of automating part of the coaching procedure on physical activity by providing personalized feedback throughout the day on a participant's progress in achieving a personal step goal. The gathered step count data was used to train eight different machine learning algorithms to make hourly estimations of the probability of achieving a personalized, daily steps threshold. In 80% of the individual cases, the Random Forest algorithm was the best performing algorithm (mean accuracy = 0.93, range = 0.88-0.99, and mean F1-score = 0.90, range = 0.87-0.94). To demonstrate the practical usefulness of these models, we developed a proof-of-concept Web application that provides personalized feedback about whether a participant is expected to reach his or her daily threshold. We argue that the use of machine learning could become an invaluable asset in the process of automated personalized coaching. The individualized algorithms allow for predicting physical activity during the day and provides the possibility to intervene in time.