Methodological Evaluation of Industrial Machinery Reliability Systems in Kenya Using Time-Series Forecasting Models

Industrial machinery reliability systems are critical for ensuring efficient operations in manufacturing sectors across Kenya. However, existing systems often lack comprehensive methodologies to evaluate their performance and predict future trends. This study employs autoregressive integrated moving average (ARIMA) models, a widely used statistical technique for time series analysis. Data on machinery usage and maintenance are collected from multiple industrial sectors in Kenya to validate the model's predictive accuracy. The ARIMA model forecasts show a consistent trend of increasing reliability over the next five years with an estimated coefficient of determination (R²) of 0.85, indicating high explanatory power of the model on machinery system performance. The study concludes that the ARIMA models effectively predict industrial machinery reliability in Kenya's manufacturing sectors, providing actionable insights for policy makers and industry stakeholders. Based on findings from this study, recommendations include implementing regular maintenance schedules and upgrading older machinery to enhance overall system reliability. ARIMA model, industrial machinery reliability, time-series forecasting, predictive analytics, Kenyan manufacturing The maintenance outcome was modelled as Yᵢₜ=β₀+β₁Xᵢₜ+uᵢ+εᵢₜ, with robustness checked using heteroskedasticity-consistent errors.