Support Vector Machine Classifier for Prediction of Breast Malignancy Using Wisconsin Breast Cancer Dataset

Abstract

Cancer is the world's second largest cause of death. In 2018, 9.6 million people died from cancer. In any medical sickness, breast cancer is one of the most delicate and endemic diseases. This is one of the primary causes of female death in the world. Breast cancer kills one out of every eleven women around the world. "Early detection equals improved odds of survival," says a well-known cancer adage. As a result, early detection is essential for successfully preventing breast cancer and lowering morality. Breast Cancer is a type of cancer that affects one of the most significant issues that humanity has faced in recent decades has been diagnosis and prediction. Cancer detection that is accurate can save millions of lives. Effective technologies for diagnosing malignant breasts aid healthcare providers in diagnosing and treating patients in a fast and accurate manner. Experiments were carried out in this study to categorise breast cancer as benign or malignant using the Wisconsin Diagnosis Breast Cancer (WDBC) database. Support Vector Machine is a supervised learning technique (SVM). The SVM classifier's classification performance is evaluated. Experiments demonstrate that the SVM model has a fantastic performance, with a classification accuracy of 96.09 percent on the testing subset.