ARCHIVES

Abstract: Breast cancer is one of the most widespread diseases among women in the India and worldwide. There is a chance of fifty percent for death in a case as one of two women diagnosed with breast cancer die in the cases of Indian women. This paper compares three of the largely popular machine learning algorithms and techniques commonly used for breast cancer prediction, namely Random Forest, Logistic Regression and kNN (k-Nearest-Neighbor). The Wisconsin Diagnosis Breast Cancer data set was used as a training set to compare the performance of the three machine learning techniques in terms of key parameters such as accuracy, precision and Recall. The results obtained are very competitive and can be used for detection and treatment.