Breast Cancer has been a leading cause of death among women across the globe; meanwhile, it is a type of cancer that comes under the treatable category. Although, early diagnosis and accurate detection of this disease promises an extended life-cycle and long survival of the diagnosed patients. The algorithms that are used in this work are Naïve Bayes and Support Vector Machine (SVM). SVM is a part of machine learning classification which uses labels to cluster data. These classifier algorithms are compared based on the performance factors i.e. accuracy of classification and execution time required. From the experimental hybrid algorithm we will overcome the disadvantages that are currently present when computing the prediction with Naïve Bayes classifier. Naïve Bayes has certain drawbacks that affects clustering and classification of data. Data scarcity, unavailability of contiguous data sources and strong presumptions of the shape of data distribution are the primary factors that undermine the utilities of Naïve Bayes classifier. The basic idea while deploying a dual hybrid algorithm is to ensure that there is a much better efficiency and that a single instance can effectively predict the disease unlike in a single algorithm system.
