Relative variable importance standardizes the importance values for ease of interpretation. The most important variable always has a relative importance of 100%, and the other variables follow in order of importance. If a variable is not used in the model at all, it is not important.
In this example, the most important predictor variable for predicting heart disease is Major Vessels. If the importance of the top predictor variable, Major Vessels, has a relative importance of 100%, then the next important variable, Thal, has a relative contribution of 89.7%. The next most important variable is Chest Pain Type which has a relative contribution of 77.6%. This means that the type of chest pain is 77.6% as important as the number of major heart vessels that are impacted.
