This study explores a drilling-based test methodology for nondestructive estimation of in-situ concrete strength. An experimental campaign has been carried out to develop a relationship between the drilling-resistance parameter, DR, and compressive strength of concrete. Rebound hammer (RH) and ultrasonic pulse velocity (UPV) tests were also performed and multivariate regression models complementing DR with RH and UPV data have been developed. A machine learning approach utilizing support vector machines (SVM) was implemented. The experimental data support that combined usage of DR with UPV and/or RH provides a robust tool for compressive strength prediction. Even with the limited data available, the support vector regression model shows promising performance.