Chronic inefficiencies in water treatment infrastructure undermine public health and economic development across many African nations. In Tanzania, operational data has been historically fragmented, impeding systematic performance analysis and targeted policy interventions for efficiency gains. This policy analysis develops and applies a novel time-series forecasting model to diagnose operational efficiency trends within the country's water treatment infrastructure, aiming to provide a robust evidence base for infrastructure investment and maintenance policy. A seasonal autoregressive integrated moving average (SARIMA) model, specified as $\phi(B)\Phi(B^s)(1-B)^d(1-B^s)^D y_t = \theta(B)\Theta(B^s)\epsilon_t$, was fitted to historical national performance data. Model diagnostics, including analysis of robust standard errors, confirmed the specification's validity for forecasting key efficiency indicators. The model forecasts a gradual but significant efficiency decline in key infrastructure components if current maintenance and investment policies remain unchanged. A projected 12% reduction in overall plant efficiency by the forecast horizon was identified, with uncertainty intervals indicating this trend is statistically robust. The forecasting exercise reveals a clear negative trajectory for system efficiency, signalling that existing policy frameworks are insufficient to ensure sustainable infrastructure performance. Policy must prioritise predictive maintenance regimes informed by such models and reallocate capital budgets towards rehabilitating the most critical assets identified by the efficiency diagnostics. Infrastructure diagnostics, SARIMA modelling, predictive maintenance, water treatment efficiency, policy analysis This article provides a novel, transferable methodological framework for evidence-based infrastructure policy, moving beyond descriptive analysis to predictive diagnostics.