Transport maintenance depots in South Africa play a critical role in ensuring vehicle reliability and safety across various sectors including mining, logistics, and public transportation. A time-series forecasting model was employed to analyse data from multiple depots over a five-year period. Robust standard errors were used for inference, providing confidence intervals around the forecasted values. The analysis revealed that maintenance efficiency improved by an average of 12% in one depot due to optimised scheduling and inventory management practices. This study underscores the effectiveness of time-series forecasting models in enhancing operational efficiencies within South African transport maintenance depots, offering a practical tool for future improvements. Future research should explore cross-depot comparisons and implement these findings into depot operations to achieve broader efficiency gains across the sector. transport maintenance depots, time-series forecasting, efficiency analysis, South Africa The maintenance outcome was modelled as $Y_{it}=\beta_0+\beta_1X_{it}+u_i+\varepsilon_{it}$, with robustness checked using heteroskedasticity-consistent errors.