Breast cancer is one of the main causes of female fatality all over the world and is the major field of research since quite a long time with lesser improvement than expected. Many institutions and organizations are working in this field to lead to a possible solution of the problem or to lead to more understanding of the problem. Many previous researches were studied for better understanding of the problem and the work done already to remove redundancy and contribute to the field, Wisconsin-Madison prognostic Breast cancer (WPBC) data set from the UCI machine learning repository was used for training of 198 individual cases by selecting best features out of 34 predictors. Feature selection algorithms were used with machine learning algorithms for feature reduction and for better classification. Different feature selection and generation algorithms were used to improve the accuracy of classification. Many improvements in accuracies were found out by using different approaches than the earlier studies conducted in the same field. The Naïve Bayes and Logistic Regression algorithms showed 8. 28-12. 32% and 0. 82-1. 52% accuracy via 10 fold cross validation analysis improvement accordingly by using different feature selection and generation algorithms with these classifiers and gave better result than the best results known for these classification algorithms.

Naïve Bayes Feature Selection Logistic