Optimizing Player Management Processes in Sports: Translating Lessons from Healthcare Process Improvements to Sports

Typical player management processes focus on managing an athlete’s physical, physiological, psychological, technical and tactical preparation and performance. Current literature illustrates limited attempts to optimize such processes in sports. Therefore, this study aimed to analyze the application of Business Process Management (BPM) in healthcare (a service industry resembling sports) and formulate a model to optimize data driven player management processes in professional sports. A systematic review, adhering to PRISMA framework was conducted on articles extracted from seven databases, focused on using BPM to digitally optimize patient related healthcare processes. Literature reviews by authors was the main mode of healthcare process identification for BPM interventions. Interviews with process owners followed by process modelling were common modes of process discovery. Stakeholder and value-based analysis highlighted potential optimization areas. In most articles, details on process redesign strategies were not explicitly provided. New digital system developments and implementation of Business Process Management Systems were common. Optimized processes were evaluated using usability assessments and pre-post statistical analysis of key process performance indicators. However, the scientific rigor of most experiments designed for such latter evaluations were suboptimal. From the findings, a stepwise approach to optimize data driven player management processes in professional sports has been proposed.

Offseason Fitness Tests a Collegiate Basketball Strength Coach Should Choose to Predict In-Season Perfomance Based on Sex

Quantification of athletic performance via analysis of scores of off-season fitness tests has become an essential part of the modern strength and conditioning coach (SCC). Player Efficiency Rating (PER) and Efficiency index (EFF) are two of the most used in-season basketball performance metrics in the US. We collected data from male and female basketball players of a National Collegiate Athletic Association (NCAA) program. Based on sex, we examined a) if unadjusted PER (uPER) and EFF reflect different amounts of information and b) which fitness tests predict those two indices more accurately. Our results showed lower means and less variability of the fitness tests scores in women than men. The correlation between uPER and EFF in men was moderate and strong in women. In men, no strong correlation was found between any fitness test and EFF, while full court sprint was strongly correlated with uPER. In women, strong correlations were detected between a) the T-drill and EFF and b) the foul court sprint, the vertical jump, and the T-drill and uPER. The collegiate SCCs should consider that off-season scores of a) the foul court drill may predict uPER more accurately in both men and women and b) the T-drill may predict both EFF and uPER more precisely in women.

A scoping review using social network analysis techniques to summarise the prevalance of methods used to acquire data for athlete survelliance in sport

To aid the implementation of athlete surveillance systems relative to logistical circumstances, easy-to-access information that summarises the extent to which methods of acquiring data are used in practice to monitor athletes is required. In this scoping review, Social Network Analysis and Mining (SNAM) techniques were used to summarise and identify the most prevalent combinations of methods used to monitor athletes in research studying team, individual, field- and court-based sports (357 articles; SPORTDiscus, MEDLINE, CINHAL, and WebOfScience; 2014-2018 inc.) . The most prevalent combination in team and field-based sports were HR and/or sRPE (internal) and GPS, whereas in individual and court-based sports, internal methods (e.g., HR and sRPE) were most prevalent. In court-based sports, where external methods were occasionally collected in combination with internal methods of acquiring data, the use of accelerometers or inertial measuring units (ACC/IMU) were most prevalent. Whilst individual and court-based sports are less researched, this SNAM-based summary reveals that court-based sports may lead the way in using ACC/IMU to monitor athletes. Questionnaires and self-reported methods of acquiring data are common in all categories of sport. This scoping review provides coaches, sport-scientists and researchers with a data-driven visual resource to aid the selection of methods of acquiring data from athletes in all categories of sport relative to logistical circumstances. A guide on how to practically implement a surveillance system based on the visual summaries provided herein, is also presented.

A Data Mining Approach to Predict Non-Contact Injuries in Young Soccer Players

Predicting and avoiding an injury is a challenging task. By exploiting data mining techniques, this paper aims to identify existing relationships between modifiable and non-modifiable risk factors, with the final goal of predicting non-contact injuries. Twenty-three young soccer players were monitored during an entire season, with a total of fifty-seven non-contact injuries identified. Anthropometric data were collected, and the maturity offset was calculated for each player. To quantify internal training/match load and recovery status of the players, we daily employed the session-RPE method and the total quality recovery (TQR) scale. Cumulative workloads and the acute: chronic workload ratio (ACWR) were calculated. To explore the relationship between the various risk factors and the onset of non-contact injuries, we performed a classification tree analysis. The classification tree model exhibited an acceptable discrimination (AUC=0.76), after receiver operating characteristic curve (ROC) analysis. A low state of recovery, a rapid increase in the training load, cumulative workload, and maturity offset were recognized by the data mining algorithm as the most important injury risk factors.

Validation of Velocity Measuring Devices in Velocity Based Strength Training

To control and monitor strength training with a barbell various systems are on the consumer market. They provide the user with information regarding velocity, acceleration and trajectory of the barbell. Some systems additionally calculate the 1-repetition-maximum (1RM) of exercises and use it to suggest individual intensities for future training. Three systems were tested: GymAware, PUSH Band 2.0 and Vmaxpro. The GymAware system bases on linear position transducers, PUSH Band 2.0 and Vmaxpro base on inertial measurement units. The aim of this paper was to determine the accuracy of the three systems with regard to the determination of the average velocity of each repetition of three barbell strength exercises (squat, barbell rowing, deadlift). The velocity data of the three systems were compared to a Vicon system using linear regression analyses and Bland-Altman-diagrams. In the linear regression analyses the smallest coefficient of determination (R2.) in each exercise can be observed for PUSH Band 2.0. In the Bland-Altman diagrams the mean value of the differences in the average velocities is near zero for all systems and all exercises. PUSH Band 2.0 has the largest differences between the Limits of Agreement. For GymAware and Vmaxpro these differences are comparable.

Sports Information Systems: A systematic review

Many professional sport organizations are currently in the process of finding or already using sports information systems (SIS) to integrate data from different information and measurement systems. The problem is that requirements are very heterogeneous. That is why no consistent definition of SIS and their categories exist, and it is often not clear which fields and functions SIS must cover. This work aims to provide a structured comparison of commercial SIS available on the market to provide an overview of the relevant features and characterize categories. Following PRISMA guidelines, a systematic search for relevant SIS providers was conducted. A catalog of 164 review items was created to define relevant features of SIS and to conduct semi-standardized interviews with product representatives. Overall 36 eligible SIS from 11 countries were identified and 21 of them were interviewed. The analysis of the interviews has shown that there are features that are present in all SIS, whereas others differ or are generally less represented. As a result, different SIS categories have been defined. The study suggests a more differentiated categorization of SIS is necessary and terms need to be defined more precisely. This review should be considered when companies designing SIS or sport organizations select SIS.

Can Elite Australian Football Player’s Game Performance Be Predicted?

In elite Australian football (AF) many studies have investigated individual player performance using a variety of outcomes (e.g. team selection, game running, game rating etc.), however, none have attempted to predict a player’s performance using combinations of pre-game factors. Therefore, our aim was to investigate the ability of commonly reported individual player and team characteristics to predict individual Australian Football League (AFL) player performance, as measured through the official AFL player rating (AFLPR) (Champion Data). A total of 158 variables were derived for players (n = 64) from one AFL team using data collected during the 2014-2019 AFL seasons. Various machine learning models were trained (cross-validation) on the 2014-2018 seasons, with the 2019 season used as an independent test set. Model performance, assessed using root mean square error (RMSE), varied (4.69-5.03 test set RMSE) but was generally poor when compared to a singular variable prediction (AFLPR pre-game rating: 4.72 test set RMSE). Variation in model performance (range RMSE: 0.14 excusing worst model) was low, indicating different approaches produced similar results, however, glmnet models were marginally superior (4.69 RMSE test set). This research highlights the limited utility of currently collected pre-game variables to predict week-to-week game performance more accurately than simple singular variable baseline models.

Comparing bottom-up and top-down ratings for individual soccer players

Correctly assessing the contributions of an individual player in a team sport is challenging. However, an ability to better evaluate each player can translate into improved team performance, through better recruitment or team selection decisions. Two main ideas have emerged for using data to evaluate players: Top-down ratings observe the performance of the team as a whole and then distribute credit for this performance onto the players involved. Bottom-up ratings assign a value to each action performed, and then evaluate a player based on the sum of values for actions performed by that player. This paper compares a variant of plus-minus ratings, which is a top-down rating, and a bottom-up rating based on valuing actions by estimating probabilities. The reliability of ratings is measured by whether similar ratings are produced when using different data sets, while the validity of ratings is evaluated through the quality of match outcome forecasts generated when the ratings are used as predictor variables. The results indicate that the plus-minus ratings perform better than the bottom-up ratings with respect to the reliability and validity measures chosen and that plus-minus ratings have certain advantages that may be difficult to replicate in bottom-up ratings.

Strictness vs. flexibility: Simulation-based recognition of strategies and its success in soccer

Introduction: Recognition and optimization of strategies in sport games is difficult in particular in case of team games, where a number of players are acting “independently” of each other. One way to improve the situation is to cluster the teams into a small number of tactical groups and to analyze the interaction of those groups. The aim of the study is the evaluation of the applicability of SOCCER© simulation in professional soccer by analyzing and simulation of the tactical group interaction. Methods: The players’ positions of tactical groups in soccer can be mapped to formation-patterns and then reflect strategic behaviour and interaction. Based on this information, Monte Carlo-Simulation allows for generating strategies, which – at least from the mathematical point of view – are optimal. In practice, behaviour can be orientated in those optimal strategies but normally is changing depending on the opponent team’s activities. Analyzing the game under the aspect of such simulated strategies revealed how strictly resp. flexible a team follows resp. varies strategic patterns. Approach: A Simulation- and Validation-Study on the basis of 40 position data sets of the 2014/15 German Bundesliga has been conducted to analyze and to optimize such strategic team behaviour in professional soccer. Results: The Validation-Study demonstrated the applicability of our tactical model. The results of the Simulation-Study revealed that offensive player groups need less tactical strictness in order to gain successful ball possession whereas defensive player groups need tactical strictness to do so. Conclusion: The strategic behaviour could be recognized and served as basis for optimization analysis: offensive players should play with a more flexible tactical orientation to stay in possession of the ball, whereas defensive players should play with a more planned orientation in order to be successful. The strategic behaviour of tactical groups can be recognized and optimized using Monte Carlo-based analysis, proposing a new and innovative approach to quantify tactical performance in soccer.

Comparison of the Evaluation of Performance Preconditions in Tennis with the Use of Equal and Expertly Judged Criteria Weights

Tennis performance is influenced by various factors, among which physical performance factors play an important role. The aim of the study was an analysis of possibilities of the use of Saaty’s method for assessing the level of performance prerequisites and comparing the results obtained using equal weights and various weights. The research on Czech female players (U12; n = 211) was based on the results of the TENDIAG1 test battery (9 items) and the results were processed by FuzzME software and relevant statistical methods (correlation coefficient r, Student´s t-test, effect size index d). The results of Saaty’s method show that the most important athletic performance criteria for tennis coaches are the leg reaction time and the running speed, while the least important are endurance and strength. The evaluation using various criteria weights offers a finer scale for assessing athletes’ performance prerequisites despite the proven high degree of association between the results obtained with equal and various weights and the insignificant difference of mean values. The results have shown possibilities for the use of a fuzzy approach in sports practice and motivate further research towards broadening the structure or the number of evaluation criteria.