Application of Random Forest (RF) via variable importance measurements (VIMs) and prediction is a new data mining model, not yet wide spread in the applied science and engineering fields. In this study, the VIMs (proximate and ultimate analysis, petrography) processed by RF models were used for the prediction of Hardgrove Grindability Index (HGI) based on a wide range of Kentucky coal samples. VIMs, coupled with Pearson correlation, through various analyses indicated that total sulfur, liptinite, and vitrinite maximum reflectance (Rmax) are the most importance variables for the prediction of HGI. These effective predictors have been used as inputs for the prediction of HGI by a RF model. Results indicated that the RF model can model HGI quite satisfactorily when the R2 = 0.90 and 99% of predicted HGIs had less than 4 HGI unit error in the testing stage. According to the result, by providing nonlinear VIMs as well as an accurate prediction model, RF can be further employed as a reliable and accurate technique for the evaluation of complex relationships in coal processing investigations.