In the modern automotive industry, improving fuel efficiency while reducing carbon emissions is a critical challenge. To address this challenge, accurately measuring a vehicle’s road load is essential. The current methodology, widely adopted by national guidelines, follows the coastdown test procedure. However, coastdown tests are highly sensitive to environmental conditions, which can lead to inconsistencies across test runs. Previous studies have mainly focused on the impact of independent variables on coastdown results, with less emphasis on a data-driven approach due to the difficulty of obtaining large volumes of test data in a short period, both in terms of time and cost. This paper presents a road load energy prediction model for vehicles using the XGBoost machine learning technique, demonstrating its ability to predict road load coefficients. The model features 27 factors, including rolling, aerodynamic, inertial resistance, and various atmospheric conditions, gathered from a decade’s worth of coastdown certification data. The developed model has successfully demonstrated its ability to predict road load energy without the need for actual coastdown testing. The Random Forest algorithm was also employed to identify factors that influence road load energy, analyzing each factor based on its magnitude of impact, which provides valuable insights. To further validate the model’s applicability, additional tests were performed using an independent dataset obtained from certification tests conducted in 2024. Finally, this paper proposes the application of a road load energy prediction model to estimate a vehicle’s road load force coefficients. This approach is unique and underscores the value of machine learning methodologies in achieving data consistency. We believe that our approach can be applied across various test fields, including certification compliance, future audit tests under diverse conditions, and as a predictive tool for mass production-level data in strategic vehicle development.