Analysis of breast cancer data: a comparative study on different feature selection techniques

Choosing the relevant features is important to provide a better understanding of the data and improve the prediction performance. In this paper, we present a comparative study of various feature selection methods applied on a breast cancer dataset. In addition, this work investigates the stability of these techniques when perturbation on the dataset is added. Artficial Neural Network and Random Forest are used for classification. The results are compared when using all the features and when using only the top ranked. The classification performance are comparable in either cases.