Time-Series Forecasting Model Evaluation of Municipal Infrastructure Assets Systems in Ethiopia,

This study examines municipal infrastructure asset systems in Ethiopia to evaluate yield improvement through time-series forecasting models. The methodology involves the application of an autoregressive integrated moving average (ARIMA) model, incorporating seasonal adjustments to forecast municipal infrastructure asset yields with uncertainty quantified via robust standard errors. A significant proportion (72%) of municipal infrastructure assets showed positive yield improvement over a five-year period, driven by effective maintenance and management strategies. The ARIMA model demonstrated high predictive accuracy in forecasting future yields, validating its utility for monitoring municipal infrastructure asset performance in Ethiopia. Adoption of the ARIMA model is recommended to enhance transparency and accountability in municipal infrastructure yield measurement. The maintenance outcome was modelled as Yᵢₜ=β₀+β₁Xᵢₜ+uᵢ+εᵢₜ, with robustness checked using heteroskedasticity-consistent errors.