Psychosocial and Physiological Factors Affecting Selection to Regional Age-Grade Rugby Union Squads: A Machine Learning Approach

Abstract

Talent selection programmes choose athletes for talent development pathways. Currently, the set of psychosocial variables that determine talent selection in youth Rugby Union are unknown, with the literature almost exclusively focusing on physiological variables. The purpose of this study was to use a novel machine learning approach to identify the physiological and psychosocial models that predict selection to a regional age-grade rugby union team. Age-grade club rugby players (n = 104; age, 15.47 ± 0.80; U16, n = 62; U18, n = 42) were assessed for physiological and psychosocial factors during regional talent selection days. Predictive models (selected vs. non-selected) were created for forwards, backs, and across all players using Bayesian machine learning. The generated physiological models correctly classified 67.55% of all players, 70.09% of forwards, and 62.50% of backs. Greater hand-grip strength, faster 10 m and 40 m sprint, and power were common features for selection. The generated psychosocial models correctly classified 62.26% of all players, 73.66% of forwards, and 60.42% of backs. Reduced burnout, reduced emotional exhaustion, and lower reduced sense of accomplishment, were common features for selection. Selection appears to be predominantly based on greater strength, speed, and power, as well as lower athlete burnout.

Special Issue “Talent Identification and Development in Youth Sports”

“…Not only do these approaches provide novel insights into talent identification and development, but they also offer researchers the opportunity to replicate studies in different settings. One rapidly emerging quantitative analysis approach that was used twice in this Special Issue [15,16] is machine learning. For instance, Owen and colleagues [16] used Bayesian machine learning to create predictive models for selected and non-selected Welsh male U16 and U18 rugby players.…”

“…One rapidly emerging quantitative analysis approach that was used twice in this Special Issue [15,16] is machine learning. For instance, Owen and colleagues [16] used Bayesian machine learning to create predictive models for selected and non-selected Welsh male U16 and U18 rugby players. Whilst they showed their physiological and psychosocial models correctly classified 67.5% and 62.3% of all players, respectively, they also provided a unique method to explore selection into talent pathways that may be replicable to other researchers in the future.…”

Why size matters; rugby union and doping

“…These mismatches seemingly increased perceptions regarding physical size and strengthexposing some individuals to a greater degree of doping vulnerability and risk. (Owen et al, 2022;Howard et al, 2016;Lewis et al, 2015). In youth rugby, sixteen-and eighteen-yearolds may compete against one another (WRU, 2021) and while the chronological ages of players are shared in relatively narrow bands, biological age differences vary considerably (Lewis et al, 2015).…”

A Multidisciplinary Investigation into the Talent Development Processes at an English Football Academy: A Machine Learning Approach

“…Weighted k-NN outperformed all the tested models with reasonably good accuracy (83%) for the prediction of ‘high-potential’ (i.e., top of group) and ‘low-potential’ (i.e., bottom of group) developmental level (aged 13 to 20 years) archers. Most recently, Owen and colleagues [ 22 ] used a Bayesian machine learning approach to identify the physiological and psychosocial models that predict selection to a regional age-grade rugby union team. They showed their physiological models correctly classified 67.55% of all players, whereas their psychosocial models correctly classified 62.26% of all players.…”