Manufacturing plants in Ghana face challenges related to cost-effectiveness due to variability in operational costs and inefficiencies. A time-series forecasting model was employed using a dataset from ten representative manufacturing plants over three years. ARIMA (AutoRegressive Integrated Moving Average) was selected as the primary statistical model with robust standard errors estimated at ±5% for prediction intervals. The ARIMA model showed an R² value of 0.82, indicating that approximately 82% of the variability in costs could be explained by the model's forecasting capabilities. This study validates the effectiveness of time-series forecasting models in enhancing cost-effectiveness for manufacturing systems in Ghanaian settings. Manufacturing companies should leverage these findings to implement more precise cost management strategies, potentially reducing operational expenses and improving productivity. manufacturing plants, cost-effectiveness, time-series analysis, ARIMA model The maintenance outcome was modelled as $Y_{it}=\beta_0+\beta_1X_{it}+u_i+\varepsilon_{it}$, with robustness checked using heteroskedasticity-consistent errors.