Abstarct: Rock Elastic properties, such as Young's modulus and Poisson's ratio, influence wellbore stability, in-situ stresses estimation, drilling performance, and hydraulic fracturing design. Conventionally, estimating these elastic properties requires laboratory experiments or data obtained from sonic and density logs. In this study, an alternative method using drilling parameters like weight on bit, penetration rate and torque and machine learning was presented. The significance of this approach is that drilling parameters are more likely to be available and can be collected in real-time during drilling operations without additional cost. The data used in this study were collected baxsed on real data points from two wells. These data include drilling parameters, core data, and sonic and density log data. The dataset from Well 2, containing 1,717 data points, was used for training and testing the models, with the data split into 80% for training and 20% for testing. An unseen dataset from Well 6, containing 1,355 data points, was used for evaluation. After data preprocessing, four features weight on bit, mud weight, rate of penetration, and drill string rotation were used as inputs for estimating Young's modulus. Additionally, for estimating Poisson's ratio, the features weight on bit, penetration rate, torque, and flow rate were selected as input for the models. Hyperparameter evaluation indicated that the best models for estimating Young's modulus were an artificial neural network with 1 hidden laxyer, 24 neurons, ReLU as the activation function, and Adam as the training function, and a random forest with 200 trees, a maximum tree depth of 10, a minimum of 5 samples to split a node, and a minimum of 2 samples in a leaf node. Similarly, the best models for estimating Poisson's ratio were an artificial neural network with two hidden laxyers, 24 neurons, ReLU as the activation function, and Adam as the training function, and a random forest with 200 trees, a maximum tree depth of 20, a minimum of 10 samples to split a node, and a minimum of 4 samples in a leaf node. Young's modulus in the evaluation well was estimated using the artificial neural network and random forest with coefficients of determination of 0.93 and 0.88, and root mean square errors of 2.81 and 3.52, respectively. Poisson's ratio in the evaluation well was estimated using the artificial neural network and random forest with coefficients of determination of 0.91 and 0.86, and root mean square errors of 0.0062 and 0.0078, respectively. The results showed that the artificial neural network method outperformed the random forest method. Therefore, in this study, the artificial neural network model demonstrated better performance in estimating Young's modulus and Poisson's ratio compared to the random forest, with a higher coefficient of determination and lower root mean square error.