Young's modulus is a principle geomechanical property that reflects the material stiffness. Good knowledge about rock mechanical properties significantly facilitates fracturing design and in situ stresses estimation. Conventionally, rock elastic properties are estimated either experimentally or using well log data, known as static and dynamic, respectively. Conducting experiments on core samples is costly, time consuming, and does not provide continuous information. While dynamic Young's modulus provides a complete profile, however, it needs the availability of acoustic logs, and its estimations differ from the static values. The objective of this article is to create a continuous profile of Young's modulus using the drilling rig sensors records. The presented approach relies on the fact that the drilling data such as drill pipe torque, weight on bit, and rate of penetration are available at an early stage without additional cost. Three machine learning algorithms were used to correlate the drilling data with Young's modulus: random forest, adaptive neuro-fuzzy inference system, and functional network. Two different datasets were used in this study, one construct and test the model, while the other was hidden from the algorithms and used later to validate the built models. The two datasets contain over 3900 data points and cover different types of rocks. Two out of the three methods utilized yielded a remarkable match between the given and the predicted values. The correlation coefficients ranged between 0.92 and 0.99 average absolute percentage errors were less than 13%. Supported by these results, the utilization of drilling data and artificial intelligence techniques to predict the elastic moduli is promising. This approach could be investigated for other geomechanical properties, besides the performance of other machine learning methods for the same purpose.