A comparison of three class separability measures

Measures of class separability can provide valuable insights into data, and suggest promising classification algorithms and approaches in data mining. We compare three simple class separability measures used in supervised machine learning. Their relative effectiveness is evaluated through their functional relationships and their random projections of data onto R for visualization. We conclude that the simple direct class separability measure of a dataset is an easier and more informative measure for separability than the class scatter matrices approach and it correlates well with Thornton’s Separability’s index.