"background": "Municipal infrastructure asset management in developing economies is often constrained by limited data and resources, leading to suboptimal investment decisions. In Rwanda, the rapid urbanisation of recent decades has placed significant pressure on ageing infrastructure systems, necessitating robust, data-driven forecasting tools for sustainable management. ", "purpose and objectives": "This study aims to develop and comparatively evaluate a time-series forecasting model to measure the cost-effectiveness of municipal infrastructure asset management. The objective is to provide a replicable methodological framework for predicting lifecycle costs and performance trade-offs. ", "methodology": "A comparative study was conducted using panel data from water supply, road, and public building assets. The core forecasting model employs an autoregressive integrated moving average with exogenous variables (ARIMAX), specified as \ yt = \ + =1^{p\ \ yt-i + =1^q\ -j + =1^r\ Xk, t + \ₜ, where X represents maintenance expenditure. Model performance was validated against naive and exponential smoothing benchmarks using mean absolute percentage error (MAPE). ", "findings": "The ARIMAX model demonstrated superior forecasting accuracy, with a MAPE of 8. 7% (95% CI: 7. 2% to 10. 3%) for aggregated asset costs, outperforming benchmark models. A key finding was that a 10% strategic reallocation of planned maintenance budgets towards pre-emptive interventions could project a 15–20% reduction in long-term rehabilitation costs across the asset portfolio. ", "conclusion": "The proposed time-series model provides a statistically robust and operationally viable tool for forecasting infrastructure management cost-effectiveness. It enables municipal engineers to shift from reactive to predictive maintenance strategies, optimising limited fiscal resources. ", "recommendations": "Implement the forecasting framework within national asset management software. Prioritise data standardisation across municipalities to
Mukamana et al. (Sun,) studied this question.