Title:Experimental Analysis towards Realizing Breast Cancer Prognosis Using Diverse Machine Learning Classifiers Authors: Sandeep Chaurasia; Prasun Chakrabarti; Yu Cheng DOI: Aff: Department of Computer Science, School of Engineering, Sir Padampat Singhania University, India Author Email: Keywords: Breast Cancer; Classifier; Decision Tree; Na´ve Bayes; Neural Network; Support Vector Machine URLs:ABSTRACT-HTML | FULLTEXT-PDF | Abstract:The adequate diagnosis of breast cancer is one of the major challenges in the medical field. Supervised machine learning has been used to simulate a model of the distribution of class label in terms of predictor features. The resultant classifier is then used for helping doctorsĺ forms a secondary opinion for better diagnosis. The performance of various machine learning techniques has been analyzed over the four distinguishes breast cancer data sets. A comparison on the performance of the results has produced among the classifiers as decision tree, Na´ve Bayes, Na´ve Bayes using kernel, neural network, auto association multi layer Perceptron and support vector machine. The obtained results shows that SVM could classify more accurate when there is no missing data, but with missing data Na´ve Bayes using kernel method works fast and generate hypothesis more accurately.