Abstract
{ "background": "The operational efficiency of industrial machinery fleets is a critical determinant of productivity and economic output in developing economies. In Nigeria, a lack of robust, data-driven methodologies for assessing and forecasting fleet performance has hindered strategic maintenance and capital investment planning, leading to suboptimal asset utilisation.", "purpose and objectives": "This case study aims to develop and evaluate a methodological framework for analysing fleet efficiency. Its core objective is to construct a predictive time-series model to forecast key performance indicators, thereby enabling evidence-based management decisions for efficiency gains.", "methodology": "A longitudinal dataset of operational parameters from a representative sample of heavy machinery fleets was analysed. The core forecasting model is an Autoregressive Integrated Moving Average (ARIMA) model, specified as $\\nabla^d yt = c + \\sum{i=1}^{p}\\phii \\nabla^d y{t-i} + \\sum{j=1}^{q}\\thetaj \\epsilon{t-j} + \\epsilont$, where $\\nabla^d$ is the differencing operator. Model diagnostics included analysis of robust standard errors to account for heteroskedasticity.", "findings": "The application of the ARIMA(1,1,1) model yielded a statistically significant forecast trend. Projections indicate a potential 18–22% improvement in aggregate fleet availability over the forecast horizon, contingent on the adoption of predictive maintenance protocols. The 95% confidence interval for this gain underscores the model's utility for strategic planning.", "conclusion": "The methodological framework demonstrates that systematic, model-driven analysis can effectively forecast machinery fleet performance. This provides a substantial advance over traditional reactive maintenance approaches, offering a pathway to enhanced industrial productivity.", "recommendations": "Fleet operators should integrate time-series forecasting into their asset management systems. Policymakers are encouraged to support the development of standardised data collection protocols to enable wider application of such predictive models across the industrial sector.", "key words": "asset management, predictive maintenance, ARIMA