The present study compares the development experiences and the nature and microstructure of practice activities of super-elite and elite cricket batsmen, domains of expertise previously unexplored simultaneously within a truly elite sample. The study modeled the development of super-elite and elite
cricket batsmen using non-linear machine learning (pattern recognition) techniques, examining a multitude of variables from across theoretically driven expertise domains. Results revealed a subset of 18 features, from 658 collected, discriminated between super-elite and elite batsmen with excellent classification accuracy (96%). The external validity of this new model is evidenced also by its ability to classify correctly the data obtained from six unseen batsmen with 100% accuracy. Our findings demonstrate that super-elite batsmen undertook a larger volume of skills-based practice that was both more random, and more varied in nature, at age 16. They subsequently adapted to, and transitioned across, the different levels of senior competition quicker. The findings suggest that optimizing challenge at a psychological and technical level is a catalyst for the development of (super-elite) expertise. Application of this holistically driven, non-linear methodological approach to talent pathways and other domains of expertise would likely prove productive.