Industrial machinery fleet systems play a crucial role in optimising productivity and efficiency in various sectors of Ethiopia's economy. A randomized controlled trial design was employed to assess the impact of different fleet management strategies on equipment utilization and maintenance costs. Data collection involved monitoring machinery performance metrics over a six-month period. The analysis revealed that implementing predictive maintenance schedules led to a reduction in unplanned downtime by approximately 15%, resulting in an estimated annual cost savings of $20,000 per fleet unit. The randomized field trial demonstrated the efficacy of adopting advanced fleet management techniques for improving industrial machinery efficiency. These findings provide valuable insights for policymakers and industry stakeholders looking to enhance resource utilization and reduce operational costs. Based on the study's outcomes, it is recommended that Ethiopian industries adopt predictive maintenance models and invest in data analytics platforms to further optimise their machinery fleets. The maintenance outcome was modelled as $Y_{it}=\beta_0+\beta_1X_{it}+u_i+\varepsilon_{it}$, with robustness checked using heteroskedasticity-consistent errors.