Validating ML algorithms for efficient Breast Cancer Prediction using K-fold

Breast cancer has always been a disease that affects a lot of people. There is vast range of factors that may lead to breast cancer and this makes it more difficult to detect at an early stage. The tissues called benign or malignant present in the breast profile are so identical that it makes detecting cancer very complex for the doctors. Performing various tests like uniformity of cell shape and thickness of tissues may result in no valuable insights. This gives rise to machine learning and artificial intelligence that can be used in the prognosis of breast cancer. Here we attempt at correlating diverse machine learning algorithms to effectively predict breast cancer over a dataset. The five diverse machine learning algorithms employed are Naïve Bayes, Decision Tree, Neural Networks (Multilayer Perceptron), SVM and K-nearest Neighbour. An effective comparative study has been done to filter out the best Algorithm based on their Performance.