Selection procedures in sports: Improving predictions of athletes' future performance

Predicting special forces dropout via explainable machine learning

Selecting the right individuals for a sports team, organization, or military unit has a large influence on the achievements of the organization. However, the approaches commonly used for selection are either not reporting predictive performance or not explainable (i.e., black box models). In the present study, we introduce a novel approach to selection research, using various machine learning models. We examined 274 special forces recruits, of whom 196 dropped out, who performed a set of physical and psychological tests. On this data, we compared four machine learning models on their predictive performance, explainability, and stability. We found that a stable rule-based (SIRUS) model was most suitable for classifying dropouts from the special forces selection program. With an averaged area under the curve score of 0.70, this model had good predictive performance, while remaining explainable and stable. Furthermore, we found that both physical and psychological variables were related to dropout. More specifically, a higher score on the 2800 m time, need for connectedness, and skin folds was most strongly associated with dropping out. We discuss how researchers and practitioners can benefit from these insights in sport and performance contexts.

A uniform approach for advancing athlete assessment: A tutorial on the Lens Model

In athlete assessment, coaches or scouts typically judge athletes by observing and combining information about their attributes. However, how accurate is the expert's eye in combining this information, and can its accuracy be improved? To address these questions, this paper introduces the Lens Model, a framework for studying human judgment that has been widely successful in other performance domains. Since the framework offers both theoretical and practical benefits and is new to sports scientists and practitioners, our paper is presented in the form of a tutorial. First, we discuss the need for the Lens Model in sports; second, we demonstrate its proven value outside of sports. Third, we provide a conceptual explanation of the Lens Model, detailing, among other aspects, how experts' judgmental policies can be modeled and how judgmental accuracy can be determined and evaluated. This is followed by an empirical example: a study on the judgments of soccer scouts, along with suggestions to improve their accuracy. To inspire further Lens Model research across sports, we conclude with prospective research directions.

Advancing athlete development: How Percentile Comparison Methods (PCMs) can identify youth developmental profiles

OBJECTIVES

Inter-individual developmental differences confound the capability to accurately evaluate youth athletic performance, highlighting the need for considerate methodology and analytical approaches. The present study demonstrated how Percentile Comparison Methods (PCMs) were developed, tested, and applied to identify athlete developmental profiles in Australian youth swimming.

DESIGN

Cross-sectional.

METHODS

Participants were N = 866 female 100-metre (m) Front-Crawl swimmers, aged 9-15 years, competing at 36 Australian regional-national level long course events. At respective events, swim performance time was collated alongside, age, date of birth, and anthropometric measures to identify age group, relative age, and maturity status. Quadratic relative age and maturity status with 100-m performance regression trendlines were generated. Then, individual swim performances at a given relative age or maturity status were converted into percentile rank distributions and compared with raw (unadjusted) annual age-group performance percentile ranks.

RESULTS

At a cohort level, initial testing confirmed relative age and maturity-adjusted percentile rankings were associated with general rank improvements for relatively younger and later maturing swimmers compared to raw ranks (and vice versa). When assessing individual swimmer plots, where three percentile rank scores were compared and rank change threshold criteria applied, five Percentile Comparison Method profile types were identified, namely: 'Early Developing' (19 %); 'Later Developing' (18 %); 'Consistent' (15 %); 'Mixed' (38 %) and 'Counteracting' (10 %). Percentile Comparison Method plots helped identify developmentally (dis-)advantaged swimmers; specific factors leading to (dis-)advantage, and likely onward development trajectories.

CONCLUSIONS

Overall and with practical considerations, Percentile Comparison Methods can improve the validity of youth athletic performance evaluation as well as inform athlete development programming.

Research on prediction and evaluation algorithm of sports athletes performance based on neural network

BACKGROUND

The Ultimate Fighting Championship (UFC) stands as a prominent global platform for professional mixed martial arts, captivating audiences worldwide. With its continuous growth and globalization efforts, UFC events have garnered significant attention and achieved commendable results. However, as the scale of development expands, the operational demands on UFC events intensify. At its core, UFC thrives on the exceptional performances of its athletes, which serve as the primary allure for audiences.

OBJECTIVE

This study aims to enhance the allure of UFC matches and cultivate exceptional athletes by predicting athlete performance on the field. To achieve this, a recurrent neural network prediction model based on Bidirectional Long Short-Term Memory (BiLSTM) is proposed. The model seeks to leverage athlete portraits and characteristics for performance prediction.

METHODS

The proposed methodology involves constructing athlete portraits and analyzing athlete characteristics to develop the prediction model. The BiLSTM-based recurrent neural network is utilized for its ability to capture temporal dependencies in sequential data. The model's performance is assessed through experimental analysis.

RESULTS

Experimental results demonstrate that the athlete performance prediction model achieved an overall accuracy of 0.7524. Comparative analysis reveals that the proposed BiLSTM model outperforms traditional methods such as Linear Regression and Multilayer Perceptron (MLP), showcasing superior prediction accuracy.

CONCLUSION

This study introduces a novel approach to predicting athlete performance in UFC matches using a BiLSTM-based recurrent neural network. By leveraging athlete portraits and characteristics, the proposed model offers improved accuracy compared to classical methods. Enhancing the predictive capabilities in UFC not only enriches the viewing experience but also contributes to the development of exceptional athletes in the sport.

Differences and relationships between talent detection, identification, development and selection in sport: A systematic review

Although there are numerous studies on talent, especially talent identification, development, and selection, both on influencing factors and model construction or talent prediction, they have relatively independently explored some of its stages. Undeniably, talent development is continuous and phased, with specific tasks to be completed at each step, and these steps have certain differences and relationships. The aim of this review is to provide a clear distinction between the entire talent cultivation process, with the purpose of having better methods and measures for each stage to minimize the turnover rate and ensure the integrity of the talent development process. Through searching the Web of Science ™ database, this review was performed according to Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Selected were original articles in English containing data or models related to talent detection/identification/development/selection in sports. A total of 16 articles were included in the study by reviewing the literature. This overview presents the differences and relationships between the four stages of talent cultivation, where these different aspects are aim, purpose, approach, and emphasis. The relationship is characterized by continuity, progressive, complementary, and mutually. This finding shows that each stage is not developed independently, but is an integral part of the talent training process. Additionally, better differentiation and strengthening of the links between the various talent cultivation stages are considered to contribute to elite athlete development. This review highlights the differences and relationships that exist at each stage of talent cultivation. Meanwhile, some measures are also proposed to strengthen the connection of these phases and how to reduce the turnover rate of talent, which can provide theoretical references for coaches or stakeholders. Based on the results of the review, it is also recommended that future research on talent cultivation could take into account the intrinsic linkages between the various stages and develop talent training programs in a multidimensional way.

Heuristics in sport: A scoping review

Judgement and decision-making under uncertainty often rely on simplistic" rules of thumb", known as "heuristics". The purpose of this scoping review is to explore the extant literature focussed on heuristics and sport. This study employed a five-stage scoping review methodology. The databases searched were Scopus, Web of Science, SPORTDiscus, and PsycInfo. The search terms were sport*, heuristic* (and its synonyms: cognitive shortcut, shortcut, rule of thumb, mental rule, cognitive rule) plus cognitive bias. The search identified 2019 studies, of which 38 were included in the analysis. Studies based in USA and Germany were most common. The use of heuristics by players were most common, while football (soccer) and basketball were the most frequently researched sport contexts. Both males and females were commonly included in most studies, but there were no studies with an explicit focus on females. The research was contextualized within several academic disciplines (e.g., psychology, forecasting, JDM, organization behavior, sports marketing and sponsorship, coaching science, risk analysis and sociology). Approximately 80 % of the studies were quantitative. Sixteen studies examined the fast and frugal heuristics approach (i.e., take-the-first heuristic (n = 8), recognition heuristic (n = 7), or gut instinct (n = 1), whereas eleven articles embraced the heuristics and biases approach. Future research should pursue a greater variety of heuristics, investigate the use of heuristics by selectors and boards of directors, and how best to design, implement, and evaluate heuristic education programs.

Unleashing potential and optimizing adolescent roller skating performance through a structured exercise program - a randomized controlled trial

BACKGROUND

The intricate nature of an athlete's abilities evolves dynamically with the enhancement of motor skills. Hence the study sought to investigate the impact of a tailored four-week exercise program`encompassing exercises focused on balance, agility, and speed. The primary objective was to determine how this exercise program influences both the roller skating talent and overall physical fitness proficiency in young male roller skaters.

METHODS

Thirty male participants (age 11-14 years) enrolled in the school skating team were recruited. The participants were randomized into either an experimental group [n = 15], performing a short-term exercise program, or a control group [n = 15], involved in the physical education classes for eight sessions over four weeks. The primary outcome measure, the skating performance, was measured by the linear speed test (LST). The secondary outcomes, i.e., balance, agility, and speed, were evaluated using the star excursion balance test (SEBT), agility t-test (ATT), and arrowhead change of direction speed test (ACDT). SEBT was assessed in 8 directions. The study was registered with the Clinical Trials Registry India (TRN: CTRI/2018/09/015713) before the recruitment of the participants on 14/09/2018.

RESULTS

The results showed that LST, ATT, and ACDT improved significantly (p < 0.05) in both groups, however, greater (p < 0.05) improvement was observed in the experimental group (Cohen's d 0.8 to 1.3). Regarding SEBT, improvement was observed in a few directions only in both groups. However, no significant difference was observed between both groups in SEBT measurements.

CONCLUSIONS

A short-term structured exercise program consisting of balance, agility, and speed exercises significantly improved the talent of skating, agility, and speed compared to physical education classes activities in young male roller skaters. The study highlights the potential of targeted training interventions to enhance athletic performance in this population.

Self-report or coach-rating? The predictive validity of different approaches to assess athletes' achievement motivation in team and individual sports

The critical role of psychological features in talent identification research is well established. What remains open is how they should be captured, as self-report as well as coach-rating approaches can be subject to bias when used for talent selection purposes (e.g., social desirability and halo effect). The purpose of this study was to examine which of three different approaches (self-report, coach-rating, and a combination of both) to assess constructs related to achievement motivation offers the highest validity for predicting performance levels of youth athletes in individual and team sports over a two-year period using binary logistic regression models and the DeLong test. Descriptively, the combination model displayed the highest predictive validity, followed by coach-ratings and self-reports. However, only the comparison of the combination and self-report models displayed meaningful differences. The findings do not allow a definitive conclusion, but coach-ratings might be the least biased and most cost and time effective approach.

Disagreement between talent scouts: Implications for improved talent assessment in youth football

Reliable talent identification and selection (TID) processes are prerequisites to accurately select young athletes with the most potential for talent development programmes. Knowledge about the agreement between scouts who play a key role in the initial TID in football is lacking. Therefore, the aim of the present study was to evaluate the agreement within four groups of a total of n = 83 talent scouts during rank assessment of under-11 male youth football players (n = 24, age = 11.0 ± 0.3 years) and to describe scouts' underlying approach to assess talent. Krippendorff's α estimates indicated disagreement of scouts' rankings within all groups of scouts (αA = 0.09, αB = 0.03, αC = 0.05, αD = 0.02). Scouts reported relying mainly on their overall impression when forming their final prediction about a player. Reportings of a consistent, structured approach were less prevalent. Taken together, results indicated that different approaches to TID may be associated with disagreement on selection decisions. In order to overcome disagreement in TID, football organisations are encouraged to establish a more structured process. Future research on the elaboration and benefit of ranking guidelines incorporating decomposed and independently evaluated sub-predictors is recommended to improve the reliability of TID.

The Longitudinal Mediating Influence of Maturation on the Relationship Between Strength and Performance in Male Youth Swimmers

PURPOSE

To examine the longitudinal relationships between shoulder internal and external rotation (IR and ER) strength, maturity status, and swim performance (aim 1). To determine whether maturity status mediated (partially/fully) the relationship between shoulder IR/ER strength and performance in age-group swimmers (aim 2).

METHODS

Using a repeated-measures design, anthropometrics, maturity status, shoulder IR/ER strength, and 200-m front-crawl velocity were assessed over 3 competition seasons in N = 82 Australian male competitive swimmers (10-15 y). For aim 1, linear mixed models examined longitudinal relationships between assessed variables. For aim 2, causal mediation analyses examined proportional (in)direct contributions of maturity status between shoulder IR strength and swim performance.

RESULTS

For aim 1, linear mixed models identified a significant relationship between shoulder IR strength and swim performance over time (F1,341.25 = 16.66, P < .001, marginal R2 = .13, conditional R2 = .91). However, maturity status was influential (ΔAkaike information criterion = -75.8, χ2 = 19.98, P < .001), suggesting removal of the shoulder IR strength-swim velocity relationship (F1,214.1 = 0.02, P = .88). For aim 2, mediation analyses identified maturity status as fully mediating the shoulder IR strength-swim velocity relationship (92.30%, P < .001).

CONCLUSIONS

Shoulder IR and ER strength did not account for variance in longitudinal age-group swim performance independent of maturity status. Interindividual differences in maturity status fully explained the relationship between shoulder IR/ER strength and swim performance. For practitioners, findings promote the need to account for maturation status and question the rationale for upper-limb strength assessment during maturational years.

Flexible Training Planning Coupled with Flexible Assessment: A 12-Week Randomized Feasibility Study in a Youth Female Volleyball Team

According to the Quality Education and Gender Equality ambitions established at the 2030 Agenda for Sustainable Development Goals, we aimed to test the feasibility of a flexible planning and assessment process, using ongoing, bidirectional feedback between planning and assessment. Eighteen players (11.5 ± 0.5 years of age) from a U13 female volleyball team were randomized into an experimental group (in which the plan could be changed daily) or a contrast group (pre-defined planning, adjusted monthly). The pedagogical intervention lasted three months. Besides ongoing daily assessments from the training practices, the Game Performance Assessment Instrument was adopted as a starting point for the weekly assessments in 4 vs. 4 game-forms (i.e., the instrument was modified monthly based on feedback from the training process). Information from daily and weekly formal assessment was used in the planning of the experimental group, and monthly in the contrast group. Data suggested that pre-established and strict planning (even updated monthly) failed to fit current learner needs. Over 12 weeks, the pre-established planning suffered regular modifications in the experimental group, and the assessment tool changed monthly. In conclusion, both planning and assessment should be open and flexible to exchange information mutually, and support the design of tailor-made learning environments.

Methodological Approaches to Talent Identification in Team Sports: A Narrative Review

Talent identification (TID) and talent development (TD) continue to receive significant investment from team sports organisations, highlighting their importance in attempting to identify potential elite athletes. Accompanying this continual pursuit to unearth future talent is an ever-increasing body of research aiming to provide solutions and strategies to optimise TID and TD processes. Therefore, the aim of this review is to provide a summary and critical synthesis of the methodological approaches applied to TID in team sports and present considerations for future TID research. Specifically, this review highlights three key areas for consideration: (1) the timespan of the research design; (2) the use of monodisciplinary or multidisciplinary variables; and (3) the fidelity of the methodological approaches to the assessment of talent. The review highlights the benefits of longitudinal, multidisciplinary, and ecologically valid research designs for TID within team sports.

Physical Fitness and Performance in Talented & Untalented Young Chinese Soccer Players

Sports performance is a complex process that involves many factors, including ethnic and racial differences. China's youth soccer is in a process of constant development, although information about the characteristics of its players and their methodological systems is scarce. The aim of this retrospective study was to characterize the physical fitness and the competitive performance of 722 Chinese players of three sports categories (8.0-9.9, 10.0-11.9 and 12.0-13.9 years), who were classified by their coaches as talented (n = 204) or untalented (n = 518). Players were assessed for anthropometry (body height, body mass, body mass index), lung capacity (Forced Vital Capacity), jumping performance (Squat Jump, Countermovement Jump and Abalakov tests), sprinting performance (10 m and 30 m Sprint tests), agility performance (Repeated Side-Step test) and flexibility (Sit & Reach test). A descriptive, comparative, correlational and multivariate analysis was performed. Competitive ranking was created in order to act as dependent variable in multiple linear regression analysis. Results indicate that Chinese players classified as talented have better motor performance than untalented ones. However, these differences are neither related nor determine the competitive performance of one group or the other.

Predicting Seasonal Performance in Professional Sport: A 30-Year Analysis of Sports Illustrated Predictions

In 2017, Sports Illustrated (SI) made headlines when their remarkable prediction from 2014 that the Houston Astros (a team in one of the lowest Major League Baseball divisional rankings) would win the World Series, came true. The less-publicised story was that in 2017, SI predicted the Los Angeles Dodgers to win the Major League Baseball (MLB) title. Assessing the forecasting accuracy of experts is critical as it explores the difficulty and limitations of forecasts and can help illuminate how predictions may shape sociocultural notions of sport in society. To thoroughly investigate SI’s forecasting record, predictions were collected from the four major North American sporting leagues (the National Football League, National Basketball Association, Major League Baseball, and National Hockey League) over the last 30 years (1988–2018). Kruskal–Wallis H Tests and Mann–Whitney U Tests were used to evaluate the absolute and relative accuracy of predictions. Results indicated that SI had the greatest predictive accuracy in the National Basketball Association and was significantly more likely to predict divisional winners compared to conference and league champions. Future work in this area may seek to examine multiple media outlets to gain a more comprehensive perspective on forecasting accuracy in sport.

Storm Clouds on the Horizon: On the Emerging Need to Tighten Selection Policies

Athlete selection is fundamental in elite sport, occurring regularly throughout an athlete's development. Research in this area reveals the accuracy of these decisions is questionable in even the most elite sport environments and athletes are increasingly disputing these decisions as unfair and punitive. As a countermeasure to these dispute and arbitration practices, many elite sport systems have created policies where coaches must outline and stand behind the criteria used for their selection decisions. Selection criteria policies have the potential to help encourage fair selection practices by holding selectors accountable to their selection criteria, but their implementation also has the potential to wrongfully nudge selectors toward developing more defendable, but less-accurate selection practices. The paper concludes with 10 suggestions to help support practitioners when implementing selection criteria.

Theoretical Aspects of the Correlation of Education and Professional Sports in the Development of Information Technology

The rapid development of modern science and technology has had an unprecedented impact on professional sports, resulting in the need to update the methodology of teaching physical education. The purpose of the study is to analyse the correlations between education and professional sports in the context of the active introduction of information technology. The methodology of theoretical research was used in conducting study. It is determined that the new mode of education does not depend entirely on the advantages of media education, but on the reform of physical education regime. It was discovered that the use of media education technology created conditions for the reform of teaching physical education and sports and led to its recessive function due to the new teaching regime. The necessity of comprehensive analysis in evaluating the model of sports education is substantiated. The study established that the informatisation of sports in educational institutions plays an important role in promoting physical education among students. The semantic importance of school sports modernisation is considered, which includes revising views and ideas on physical education, improving the content and methods of teaching, changing the team composition and management of school sports, and updating school sports and sports evaluation system. The study includes statistical data on the student’s attitude to physical activity and their participation in the physical education. The features of the use of media technologies for the purpose of introducing sports among young people have been established, which consist in positive and negative effects on the personality. The practical value of the study lies in the theoretical substantiation of the correlation features of the educational process and professional sports for their further application in practice

Developing a tool to assess technical skills in talented youth table tennis players-a multi-method approach combining professional and scientific literature and coaches' perspectives

Background

The assessment of technical skills as part of a multidimensional approach for talent identification and development in sports seems promising, especially in a technique-based sport like table tennis. However, current instruments mostly focus on a single element of technical skills, mainly use quantitative outcomes, and/or are not developed for talent purposes. Practice would benefit from a new instrument using a more ecologically valid approach. Thus, the purpose of this study was to identify the essential elements of technical skills in young table tennis players and to establish a first tool while using a multi-methods study design including an archive search for professional literature, a systematic search for scientific literature, as well as ten in-depth interviews with expert coaches.

Results

This approach taken ensured empirical findings to be combined with knowledge and experiences from the practical field and detailed explications by high-level expert coaches. Results for the literature searches yielded 23 professional and 21 scientific articles while data saturation was reached through all ten interviews. The triangulation process resulted in two general (i.e., individuality, interconnection between elements) and five specific (i.e., bat grip, ready position, footwork/body positioning, service, stroke) elements of technical skills in young table tennis players. In addition, criteria for both flawed and excellent executions were identified for each of the five specific elements. Finally, these results were used to create an observation sheet usable for an assessment during competition.

Conclusions

This study revealed the crucial elements of technical skills that should be taken into account when assessing sport-specific technical skills of youth table tennis players (8–12 years). Moreover, it provided concise descriptions of what is considered to be flawed or excellent executions of technical skills. Based on these findings, a first observation sheet, the Oldenburg observation sheet for Table Tennis Technique (O3T), was created to be used for the assessment of the current technical skill level within a competitive context at the early stage of a table tennis player’s career. Future research should focus on its measurement properties and its value within a multidimensional assessment for talent purposes.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40798-021-00327-5.

Troubleshooting a Nonresponder: Guidance for the Strength and Conditioning Coach

Ideally an athlete would continue to improve performance indefinitely over time, however improvement slows as the athlete approaches their genetic limits. Measuring performance is complex—performance may be temporarily depressed following aggressive training for multiple reasons, physiological and psychosocial. This reality may be vexing to the strength and conditioning coach, who, as a service provider, must answer to sport coaches about an athlete’s progress. Recently an evaluation mechanism for strength and conditioning coaches was proposed, in part to help coaches establish their effectiveness within the organization. Without formal guidance and realistic expectations, if an athlete is not bigger, leaner, stronger, etc. as a result of training within a specified timeframe, blame is often placed upon the strength and conditioning coach. The purpose of this article is to explore possible causes of what may be perceived as athlete non-responses to training and to provide guidance for the coach on how to handle those issues within their domain. A process of investigation is recommended, along with resources to assist coaches as they consider a broad range of issues, including enhancing existing testing methods, improving athlete behaviors, and adjusting processes designed to bring about performance improvement.

Nationwide Subjective and Objective Assessments of Potential Talent Predictors in Elite Youth Soccer: An Investigation of Prognostic Validity in a Prospective Study

Recent studies have provided empirical evidence on the prognostic relevance of objective performance diagnostics in the soccer talent identification and development process. However, little is known about the prognostic validity of coaches' subjective evaluations of performance. This study evaluated objective and subjective assessments within a nationwide talent development program and addressed motor, perceptual skill, and personality-related performance factors. Male players (N = 13,869; M_age = 12.59 ± 1.07 years) from the age groups U12 to U15 of the German soccer talent development program participated in this study. Participants completed an objective motor diagnostic (sprint, agility, dribbling, ball control, juggling) and were subjectively rated by their coaches (kicking skills, endurance, individual tactical skills, psychosocial skills). All nine predictors were assessed with sufficient psychometric properties (α ≥ 0.72; except dribbling and ball control: α ≥ 0.53). Players' success three seasons later was operationalized by achieving professional youth academy level or not (success rate, 9%). Independent-samples t-tests analyzed univariate mean group comparisons between future selected and non-selected players. Logistic regression models examined the multivariate prognostic validity of all assessments by predicting success with subjective (model 1), objective (model 2), and both groups of predictors (model 3). Confirming the univariate prognostic validity, future selected outperformed non-selected players regarding all predictors (each p < 0.001, except for agility in U15: p < 0.01). Tactical skills, kicking skills, and sprint were of highest predictive value (d ≥ 0.61 in each age group). Multivariate results provided empirical evidence for the subjective (7% ≤ Nagelkerke's R² ≤ 11%; each p < 0.001) and objective (8% ≤ Nagelkerke's R² ≤ 13%; each p < 0.001) assessments' prognostic validity. However, model 3 revealed the best statistical explanatory power in each age group (0.15 ≤ Nagelkerke's R² ≤ 0.20; p < 0.001). In this combined assessment model, sprint, tactical skills, and dribbling were found to be the most predictive variables. In conclusion, this study reinforces the call for multidimensional diagnostics integrating objective and subjective assessments. Future research is needed to address the demands for longitudinal analyses of subjective ratings, the integration of biological maturation, and empirical evidence for female soccer.

How soccer scouts identify talented players

Scouts of soccer clubs are often the first to identify talented players. However, there is a lack of research on how these scouts assess and predict overall soccer performance. Therefore, we conducted a large-scaled study to examine the process of talent identification among 125 soccer scouts. Through an online self-report questionnaire, scouts were asked about (1) the players' age at which they can predict players' soccer performance, (2) the attributes they consider relevant, and (3) the extent to which they predict performance in a structured manner. The most important results are as follows. First, scouts who observed 12-year-old and younger players perceived they could predict at older ages (13.6 years old, on average) whether a player has the potential to become a professional soccer player. This suggests that scouts are aware of the idea that early indicators of later performance are often lacking, yet do advise on selection of players at younger ages. Second, when identifying talented players, scouts considered more easily observable attributes, such as technical attributes. However, scouts described these often in a broad sense rather than in terms of specific predictors of future performance. Finally, scouts reported that they assess attributes of players in a structured manner. Yet, they ultimately based their prediction (i.e. final score) on an intuitive integration of different performance attributes, which is a suboptimal strategy according to existing literature. Taken together, these outcomes provide specific clues to improve the reliability and validity of the scouting process. HighlightsBased on a large sample of soccer scouts, we examine three issues that are important in the process of identifying talented soccer players: The age at which good performance predictions can be made, which attributes are relevant predictors, and how performance predictions are formed.Scouts who observe players in young age cohorts believe that the age at which they can predict performance is older than the players they typically scout, suggesting that they are aware that early indicators of performance are often lacking.Technical performance attributes are considered as most important performance predictors by scouts, but these are often described in a broad - rather than specific - sense.Scouts indicate that they predict performance in a structured manner, but form their overall performance prediction on an intuitive integration of different performance attributes, which can be a suboptimal approach.

Assessing Technical Skills in Talented Youth Athletes: A Systematic Review

Background

Talent identification and development (TID) programs aim to identify players with the greatest potential for long-term success. Previous research suggests that the assessment of sport-specific technical skills is valuable for discriminating between more and less skilled individuals and/or for predicting future performance.

Objective

This review aims to provide an overview on both the instruments used to assess sport-specific technical skills and their discriminatory, explanatory and/or predictive findings in the context of TID.

Methods

Electronic searches were conducted in PubMed, Web of Knowledge, SPORTDiscus, SURF and Scopus (January 1990–October 2019). Search terms covered the areas of sport, technical skills assessment, performance, skill level and youth. In the end, 59 relevant studies were identified and evaluated.

Results

The results highlight the widespread and important role of technical skills in TID; almost all studies (93%) reported discriminatory, explanatory and/or predictive benefits for the assessment of sport-specific technical skills. Analyzing and categorizing the number of assessment methods applied in the studies (n = 69) according to their method type (‘technique-related’ or ‘outcome-related’ variables) and method set-up (‘experimental’ or ‘competition’ data acquisition environment) indicated a clear tendency towards ‘outcome-related’ (73%) and ‘experimental’ (75%) assessment methods. We also found a strong overrepresentation of studies assessing cross-sectional data (75%) in soccer (53%) in male samples (74% of studies reporting subjects’ sex) from European countries (64%).

Conclusions

On the one hand, our findings demonstrate the great capability of sport-specific technical skills assessments to discriminate different performance levels and predict future performance in TID activities. On the other hand, this review highlights the focus on ‘outcome-related’ and ‘experimental’ methods in specific populations and, consequently, the limited knowledge in other areas. Here, the application of ‘technique-related’ and ‘competition’ methods appears promising for adding new knowledge, especially in the light of technological advances.

Game Insight Skills as a Predictor of Talent for Youth Soccer Players

Perceptual–cognitive skills are found to be important factors for soccer players. The aim of this study was, therefore, to find within-group differences for game insight in an elite group of youth soccer players by means of a Game Insight inDicator (GID). In addition, the prospective value of perceptual–cognitive skills was examined by following the trajectory of the participants. The GID consisted of film clips that show game situations. The task of the players was to predict the trajectory and destination of the ball and move toward the correct position to receive the pass of a teammate. The film clips stopped 80 ms before, at, and 80 ms after the football contact of a teammate. We also sought to validate the GID against game performance. Participants were talented soccer players 11–13 years old and playing at the elite level for their age. Based on eight independent elite-coach judgments, two groups were created: highly talented players (HT) and less talented players (LT). The coach ratings were supported by a significant difference between the two groups based on the objective notational analysis of their game performance in 4 vs. 4 and 11 vs. 11 matches. With respect to the GID, a significant interaction effect for the groups (HT vs. LT) by occlusion time (−80, 0, and +80 ms) was found, showing that the HT performs better than the LT in 0 and +80 ms condition. In addition, GID scores were compared with soccer levels at the mean age of 19 years. Longitudinal data did not show significant differences between elite and sub-elite. Overall, the GID was found to be a valid and useful indicator for players anticipating the ball's trajectory and destination at age 11–13 years but failed to predict the players' level at age 19 years. The latter indicates how difficult it is to predict talent development.

An eye for talent: The recruiters' role in the Australian Football talent pathway

Talent identification and recruitment (TIR) in elite sport is a complex process with performance and career longevity implications for athletes, sports organisations, and scouts (hereafter referred to as recruiters). Although there is an established body of published research on TIR the critical roles that recruiters perform has only recently gained attention from researchers. In this study, we report on the practices that 12 full time Australian Football recruiters use to inform their TIR decisions. Inductive qualitative semi-structured interviews were conducted using open-ended questions. Thematic analysis resulted in the identification of four primary themes (the recruiter, processes and practices, assessment and selection). The results and discussion provide insights and an occupational 'road map' into the important role recruiters perform in sporting organisations.

The validity of small-sided games in predicting 11-vs-11 soccer game performance

Predicting performance in soccer games has been a major focus within talent identification and development. Past research has mainly used performance levels, such as elite vs. non-elite players, as the performance to predict (i.e. the criterion). Moreover, these studies have mainly focused on isolated performance attributes as predictors of soccer performance levels. However, there has been an increasing interest in finer grained criterion measures of soccer performance, as well as representative assessments at the level of performance predictors. In this study, we first determined the degree to which 7-vs-7 small-sided games can be considered as representative of 11-vs-11 games. Second, we assessed the validity of individual players’ small-sided game performance in predicting their 11-vs-11 game performance on a continuous scale. Moreover, we explored the predictive validity for 11-vs-11 game performance of several physiological and motor tests in isolation. Sixty-three elite youth players of a professional soccer academy participated in 11 to 17 small-sided games and six 11-vs-11 soccer games. In-game performance indicators were assessed through notational analysis and combined into an overall offensive and defensive performance measure, based on their relationship with game success. Physiological and motor abilities were assessed using a sprint, endurance, and agility test. Results showed that the small-sided games were faster paced, but representative of 11-vs-11 games, with the exception of aerial duels. Furthermore, individual small-sided game performance yielded moderate predictive validities with 11-vs-11 game performance. In contrast, the physiological and motor tests yielded small to trivial relations with game performance. Altogether, this study provides novel insights into the application of representative soccer assessments and the use of continuous criterion measures of soccer performance.

Methodological Issues in Soccer Talent Identification Research

Talent identification research in soccer comprises the prediction of elite soccer performance. While many studies in this field have aimed to empirically relate performance characteristics to subsequent soccer success, a critical evaluation of the methodology of these studies has mostly been absent in the literature. In this position paper, we discuss advantages and limitations of the design, validity, and utility of current soccer talent identification research. Specifically, we draw on principles from selection psychology that can contribute to best practices in the context of making selection decisions across domains. Based on an extensive search of the soccer literature, we identify four methodological issues from this framework that are relevant for talent identification research, i.e. (1) the operationalization of criterion variables (the performance to be predicted) as performance levels; (2) the focus on isolated performance indicators as predictors of soccer performance; (3) the effects of range restriction on the predictive validity of predictors used in talent identification; and (4) the effect of the base rate on the utility of talent identification procedures. Based on these four issues, we highlight opportunities and challenges for future soccer talent identification studies that may contribute to developing evidence-based selection procedures. We suggest for future research to consider the use of individual soccer criterion measures, to adopt representative, high-fidelity predictors of soccer performance, and to take restriction of range and the base rate into account.

Challenges and [Possible] Solutions to Optimizing Talent Identification and Development in Sport

The modern-day landscape of Olympic and Professional sport is arguably more competitive than ever. One consequence of this is the increased focus on identifying and developing early athletic talent. In this paper, we highlight key challenges associated with talent (athlete) identification and development and propose possible solutions that could be considered by research and practice. The first challenge focuses on clarifying the purposes of talent identification initiatives such as defining what talent is and how its meaning might evolve over time. Challenge two centers on ways to best identify, select and develop talent, including issues with different approaches to identification, the need to understand the impact of development and the need to have appropriate resourcing in the system to support continued development of knowledge. Finally, we discuss two challenges in relation to the 'healthiness' of talent identification and development. The first examines whether a talent identification and development system is 'healthy' for athletes while the second focuses on how sport stakeholders could discourage the apparent trend toward early specialization in youth sport settings. Whilst this paper discusses the research in relation to these challenges, we propose multiple possible solutions that researchers and practitioners could consider for optimizing their approach to talent identification and development. In summary, talent is a complex and largely misunderstood phenomenon lacking robust research evidence, and given concerns that it is potentially unhealthy, talent identification and selection at younger ages is not recommended.

Waste Reduction Strategies: Factors Affecting Talent Wastage and the Efficacy of Talent Selection in Sport

Coaches are faced with the difficult task of identifying and selecting athletes to their team. Despite its widespread practice in sport, there is still much to learn about improving the identification and selection process. Evidence to date suggests selection decisions (at different competitive levels) can be inaccurate, bias driven, and sometimes even illogical. These mistakes are believed to contribute to "talent wastage," the effect of a coach's wrongful selection and/or deselection of an athlete to/from a team. Errors of this scale can lead to negative repercussions for all stakeholders involved and therefore deserve further exploration. It is the purpose of this paper to shed light on the potential factors influencing talent wastage and to illuminate possible psychological pitfalls when making decisions under uncertainty.

Observation Criteria for Physical Education Teachers to Identify Gifted Children through Invasion Games

Whilst in other curriculum subjects, it exists observation criteria to detect gifted pupils, there is a paucity of information in Physical Education. For that reason, we aimed to reveal the observation criteria for identifying gifted pupils in Physical Education in an invasion game. Physical Education (PE) talent was evaluated combining results of questionnaire to experts, parents, and students. A validated nomination scale (NSIFT) and the Game Performance Evaluation Tool (GPET) were used. The research approach used in this study was transversal, descriptive, and inferential. The talent pool was composed of 18 gifted pupils aged 8-14 (M_age = 11.67, SD = 1.53). The results showed that the most discriminating criteria to identify PE talent were found to be precocity in both execution and decision-making in the acquisition of tactical principles and tactical-technical skills. Getting free was the skill that they best mastered. In conclusion, the importance of tactical principles and decision-making as observation criteria is emphasized. Future studies should focus on developing mentoring programs in Physical Education.