One of the main causes of death is cancer. The most common cancer in women is breast cancer. This disease if it be known early could be overcome and even prevented. Data classification techniques could be used to predict which patients had breast cancer and not with some parameters. Using the Neural Network method and Rapid Miner 9.0 tools aims to predict breast cancer diagnosis and then produced an accuracy value of 71,83%, precision 81,08% and recall of 69,17% with AUC of 0,806 which means that the classification was good so that patients with parameters there could be predicted which ones were breast cancer patients and which were not, so this pattern could be used as a benchmark for diagnosis so that it could be detected earlier and was expected to reduce the number of deaths from breast cancer.