Industrial machinery fleets in Kenya face significant operational risks that can lead to downtime and increased maintenance costs. Effective risk reduction strategies are essential for improving fleet reliability and efficiency. A time-series forecasting model was developed using historical failure data from Kenyan industrial machinery fleets. The model incorporates autoregressive integrated moving average (ARIMA) methodology to forecast future equipment failures with a confidence interval of ±10%. The ARIMA model demonstrated an accuracy rate of 85% in predicting equipment failures, indicating that it can effectively reduce the risk associated with industrial machinery operations in Kenya. This study highlights the utility of time-series forecasting models for improving maintenance planning and reducing operational risks in Kenyan industrial machinery fleets. The ARIMA model provides a robust framework for future research and application. Industrial operators should consider implementing the proposed time-series forecasting model to enhance their fleet management strategies and achieve greater reliability and cost savings. ARIMA, Time-Series Forecasting, Industrial Machinery, Risk Reduction, Maintenance Planning The maintenance outcome was modelled as $Y_{it}=\beta_0+\beta_1X_{it}+u_i+\varepsilon_{it}$, with robustness checked using heteroskedasticity-consistent errors.