Information about soil properties help the farmers to do effective and efficient farming, and yield more crops with less usage of resources. An attempt has been made in this paper to predict the soil properties using machine learning approaches. The main properties of soil prediction are Calcium, Phosphorus, pH, Soil Organic Carbon, and Sand. These properties greatly affect the production of crops. Four well-known machine learning models, namely, multiple linear regression, random forest regression, support vector machine, and gradient boosting, are used for prediction of these soil properties. The performance of these models is evaluated on Africa Soil Property Prediction dataset. Experimental results reveal that the gradient boosting outperforms the other models in terms of coefficient of determination. Gradient boosting is able to predict all the soil properties accurately except phosphorus. It will be helpful for the farmers to know the properties of the soil in their particular terrain.