Nowadays, the urgency to appraise the structural deteriorating condition of road pavements and ascertain their remaining operational lifespan is more paramount than ever. The limitations of conventional computational methods and measurement techniques such as the Falling Weight Deflectometer (FWD) have paved the way for the emergence of the Traffic Speed Deflectometer (TSD), enabling continuous bearing capacity evaluation without traffic disruption. Given the large amount of data generated by TSD, this paper introduces an innovative Machine Learning (ML) based model for the estimation of the pavement elastic modulus (E1) using vertical deflection velocity (Dv) measurement. The research formulates a robust estimation models by employing Support Vector Machine (SVM) techniques, that subsequently validated through rigorous performance metrics. This research significantly advances pavement assessment by offering promising data-driven approaches and ML prospects for monitoring road durability and safety.