Tired of Misattribution, Modeling Player Fatigue in the NBA

The prevailing belief propagated by NBA league observers is that the workload of the NBA season dramatically influences a player's performance$^{1,2,3,4,5}$. We offer an analysis of cross game player fatigue that calls into question the empirical validity of these claims. The analysis is split into three observational studies on prior NBA seasons. First, to offer an analysis generalized to the whole league, we conduct an examination of relative workloads with in-game player tracking data as a proxy for exertion. Second, to introduce a more granular perspective, we conduct a case study of the effectiveness of load management for Kawhi Leonard. Third, to extend the analysis to a broader set of fatigue sources, we examine the impact of schedule features structurally imposed on teams. All three analyses indicate the impact of cumulative player fatigue on game outcomes is minimal. As a result, we assert in the context of the measures already taken by teams to maintain the health of their players,$^6$ the impact of fatigue in the NBA is overstated.