Methodological Framework for Time-Series Forecasting of Manufacturing Plant Efficiency Gains in Kenya (2000–2026)

{ "background": "The Kenyan manufacturing sector is a critical component of national economic development, yet robust methodologies for quantifying and forecasting long-term operational efficiency gains are lacking. Existing approaches often rely on static analyses, failing to capture dynamic system improvements over time.", "purpose and objectives": "This article presents a novel methodological framework for constructing and validating time-series models to forecast efficiency gains within manufacturing plant systems. The objective is to provide a replicable, data-driven procedure for engineers and plant managers to project performance trajectories.", "methodology": "The framework integrates production data with key performance indicators to fit a seasonal autoregressive integrated moving average (SARIMA) model, specified as $\\phi(B)\\Phi(B^s)\\nabla^d\\nabla^Ds yt = \\theta(B)\\Theta(B^s)\\epsilont$, where $\\epsilont$ is white noise. Model selection employs the Akaike Information Criterion, with parameter uncertainty quantified via 95% confidence intervals derived from robust standard errors.", "findings": "Application of the framework to a case study plant demonstrates its operational utility, revealing a forecasted mean efficiency gain of 18.7% over the projection period, with a key theme being the significant role of automated system integration in driving improvements. The model's out-of-sample forecast errors remained within acceptable engineering tolerances.", "conclusion": "The proposed framework provides a statistically rigorous and practically applicable methodology for forecasting manufacturing efficiency, moving beyond descriptive analysis to predictive capability.", "recommendations": "Practitioners should adopt this framework for strategic capacity planning, ensuring data collection systems are aligned with the required temporal granularity. Further research should adapt the model to incorporate real-time sensor data from industrial Internet of Things networks.", "key words": "time-series forecasting, manufacturing efficiency, SARIMA modelling, industrial engineering, predictive maintenance, Kenya", "contribution statement": "This paper introduces a novel integrated SARIMA modelling framework, specifically tailored for the Kenyan industrial context, which successfully forecasts a mean efficiency gain of 18.