Deformational properties, such as, Young's modulus and Poisson's ratio are considered to be among the most critical parameters of coal measure rocks for coal bed methane (CBM) extraction, CO2 sequestration, and mining activities. The inherent heterogeneity of these rocks from basin to basin makes the accurate estimation of deformational properties very complex. Here, these properties were evaluated using artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS), and compared with the traditional multiple regression analysis (MRA). Multiple index geomechanical parameters, such as, compressive strength, tensile strength, shear strength, and P-wave velocity have been used as the inputs to build the prediction models. In total 69 data sets, developed from laboratory measurements were used for the analysis. First 57 datasets were used to train the soft computing models, and the rest 12 were used to measure the accuracy and validity. Performance of the each of the statistical and soft computing models were evaluated using correlation coefficient (R2), root mean square error (RMSE), variables accounted for (VAF), and mean absolute percentage error (MAPE). Results show that ANFIS model gives the best prediction model for both the Young's modulus and Poisson's ratio. Therefore, the present study shows that it is possible to build accurate and generalized soft computing model than can incorporate heterogeneity and predict deformational properties of coal measure rocks very well without resorting to time consuming test procedures. © 2019 Elsevier Ltd