TO IMPROVE THE ACCURACY IN IDENTIFYING BREAST CANCER USING VARIOUS TECHNIQUES OF BIG DATA ANALYSIS

In present, breast cancer in women is most is the prominently discovered life-threatening cancer in women and took over too many life?s of women all around the world. This project deals with the Breast Cancer Wisconsin dataset to compare the accuracy of various machine learning algorithm in predicting the breast cancer in women. The various classification model are built and trained with the Wisconsin dataset. The different classifiers that are used to construct the model are Naive Bayes, Support Vector Machine, Regression Tree, Random Forest and K-Nearest Neighbor. The efficient working of these model are assessed by estimating the accuracy score of each model with the usage of unstandardized and standardized dataset. Once the performance of the model are evaluated, the optimal working algorithm are used to identify the type of breast cancer in the patient entry.