With unprecedented amounts of material data generated from experiments and high-throughput density functional theory, machine learning provides the ability to accelerate the discovery and design of new materials. In this work data-driven density functional theory (DFT), data is employed to develop machine learning models that can predict the densities of sodium-ion battery (SIB) cathode materials. Different machine learning models were successfully developed and validated, using SIB materials’ properties calculated from DFT as input dataset and elemental properties of their constituents. The following models Bayesian ridge, gradient boosting regressor, light gradient boosting machine, extra trees regressor, random forest and orthogonal matching pursuit were developed and evaluated. Extra trees regressor was found to be the best model in predicting density with accuracy measures of 0.95 and 0.09, for coefficient of determination and mean square error, respectively. Thus, the features used have predictive capability with a high accuracy.