Breast cancer is among the deadliest diseases worldwide and is the leading cause of death for women in developed nations. Considering the unique domain of medical data, the goal of this paper is using different novel algorithms to perform data analysis on the SEER Breast Cancer dataset for data mining, analysis and knowledge discovery. Data pre-processing and prediction model concepts are explained and implemented for knowledge discovery, and data mining methods are selected after analysis and evaluation on which is more suited given the type of data. Visualizations are also used for demonstrating results and methods used. The model and results can help future cancer research and patients determine correlated factors leading to breast cancer and cancer mortality.