Nowadays, breast cancer is the most emerging diseaseamong women both in developed as well as developing countries. Due to increased life prospects, increased urbanization, and therelinquishment of western societies, the rareness of breast cancer is supersizing in the developing world. Even it became a second popular cause of cancer that has already been announced. It's very hard to identify the early symptom of this type of cancer for reducing numerous death. Different methods of machine learning and data mining techniques are using for medical diagnosis. In this study, four machine-learning algorithms are applying to analyze breast cancer in the inflammation stage and dig up the most cabbalistic and non-cabbalistic risk factors. To analyze breast cancer data from the Coimbra dataset from the UCI machine learning repository to create accurate prediction models for breast cancer. For getting better performance and to get higher accuracy Naïve Bayes (NB), Random Forest (RF), Multilayer Perceptron (MLP), Simple Logistic Regression (SLR) are using to find out some higher accuracy sequentially 70%, 68%, 85%, and 75%. Among all the above algorithms a better accuracy was achieved using Multi-layer Perceptron. Linear Regression (LiR) models are applying to dig up the most cabbalistic and non-cabbalistic risk factors of breast cancer. These results will help the doctor to detect breast cancer easily in the early stage and take the necessary steps.