Identification & interpretation of playing styles in the National Football League (NFL)

The ability to predict opposition behaviours informs critical decision-making. Moreover, understanding differences in offensive and defensive patterns of play has emerged as a limitation in American football. However, an absence of data-driven foundations from which to understand areas of play confounds current perceptions of team interactions. Therefore, the aim of this study was to derive and label playing styles in the NFL. Principal component analysis was used to explore underlying structures responsible for correlations among variables over a period of five seasons (2018–2022, 2622 team observations). Optimal coordinates extraction derived 8 distinct features accounting for 57% of the total variance within the dataset. Direct oblimin (oblique) rotation identified a low, yet meaningful positive correlation between the short and long passing latent variables (.35). Offensively, yards before and after the catch or contact alongside third down success were associated with passing, rushing, and scrambling-related playing styles. Including exclusively defensive performance variables led to 3 factors interpreted as coverage, disruptions and tackling. These methods provide a means by which team performance may be further analysed, categorised, and potentially aid in predicting and rationalising play design.