BREAST CANCER DETECTION USING ENSEMBLE TECHNIQUES IN MACHINE LEARNING

Abstract

Breast cancer which is the second most frequent form of cancer in females around the world after skin cancer, is a common disease. The number one killer in the world, breast cancer significantly contributes to this statistic. In actuality, breast cancer is the main reason why women die. The unchecked division and multiplication of cells throughout the body is a hallmark of this illness. In the medical field, numerous studies have been done to differentiate among tumors as benign and malignant early on. Healthcare sector has been profoundly impacted by machine learning technology, which has made it feasible to predict such diseases early and give patients prompt treatment. The Wisconsin dataset, which contains a variety of patient information, was used in this investigation. In this the project�s main aim is to predict the disease of breast cancer by using ML algorithms and further comparing the accuracy results of the algorithms. After prediction, ensemble techniques such as bagging and boosting are been implemented in which the algorithms are combined to provide better accuracy or results. The accuracy is been compared with the previous results and is concluded that Ensemble techniques provide better accuracy results in the prediction of the breast cancer.