Evaluation of Ensemble Machines in Breast Cancer Prediction

Abstract

Breast cancer is one of the most deadly diseases encountered among women for which the cause is not clearly defined yet. Early diagnosis may help the physicians in the treatment of this deadly disease which could turn out fatal otherwise. Machine Learning techniques are employed in the process of detecting breast cancer with greater accuracy. Individual classifiers employed in this process, predicted the disease with less accuracy when compared with ensemble models. Ensemble methods employ a group of classifiers to individually classify the data. It then combines the result of the individual classifiers using weighted voting of their predictions. Ensemble machines perform better than individual models and show improved levels in the accuracy of the prediction system. This paper examines and evaluates different ensemble machines that are used in the prediction of breast cancer and tries to identify the combinations that prove to be better than the existing ones.