In the present study, both classification and correlation approaches have been successfully employed for development of models for the prediction of CDK4 inhibitory activity using a dataset comprising of 52 analogues of 4-aminomethylene isoquinoline-1,3-(2𝐻,4𝐻)-dione. Decision tree, random forest, moving average analysis (MAA), multiple linear regression (MLR), partial least square regression (PLSR) and principal component regression (PCR) were used to develop models for prediction of CDK4 inhibitory activity. The statistical significance of models was assessed through specificity, sensitivity, overall accuracy, Mathew’s correlation coefficient (MCC), cross validated correlation coefficient, 𝐹 test, $r^2$ for external test set (pred_$r^2$), coefficient of correlation of predicted dataset (pred$_-$r²Se) and intercorrelation analysis. High accuracy of prediction offers proposed models a vast potential for providing lead structures for the development of potent therapeutic agents for CDK4 inhibition.