The operational efficiency of transport maintenance depots is critical for infrastructure sustainability, yet robust forecasting tools for yield improvement in such systems are underdeveloped, particularly in sub-Saharan contexts. This study aims to develop and methodologically evaluate a novel time-series forecasting model to measure and predict yield improvement within a national network of transport maintenance depots. A seasonal autoregressive integrated moving average with exogenous variables (SARIMAX) model, formalised as $\phi(B)\Phi(B^s)\nabla^d\nabla_s^D y_t = \theta(B)\Theta(B^s)\epsilon_t + \beta X_t$, was applied to longitudinal operational data. Model diagnostics included analysis of robust standard errors and out-of-sample validation. The model demonstrated strong predictive accuracy, with a mean absolute percentage error of 8.7% on test data. Forecasts indicate a sustained positive trajectory in system yield, with a projected increase of approximately 15% over the medium term, contingent on continued current investment levels. The proposed SARIMAX framework provides a statistically sound and operationally viable methodology for forecasting depot system performance, offering a significant advance over descriptive, non-predictive analyses. Depot managers and policymakers should integrate this forecasting approach into routine performance monitoring and resource allocation cycles to proactively enhance system yield. time-series forecasting, maintenance depots, yield improvement, SARIMAX, infrastructure management, operational efficiency This paper presents a novel application of a SARIMAX model to forecast yield in transport maintenance systems, generating a validated tool for evidence-based infrastructure management.