Breast cancer is still a major worldwide health concern, and in order to enhance patient outcomes and guide treatment decisions, precise prognostic tools are required. In this work, we utilize factor analysis and ensemble machine learning techniques to present an improved method in order to forecast breast cancer survivorship. In order to use the combined predictive ability of many algorithms, we utilize a collection of machine learning models, such as Gradient Boosting, AdaBoost, Random Forest, Extra Trees, and Bagging. Our method seeks to improve prediction robustness and accuracy by integrating the advantages of several models. In order to find latent determinants underlying breast cancer survivorship, we also use factor analysis in the prediction framework. We assess the efficacy of our suggested methodology using extensive datasets that include clinical, genetic, and demographic characteristics of individuals with breast cancer. Performance indicators metrics like recall, accuracy, and exactness are utilized to evaluate the predictive capacity of the models. Random Forest & XGBoost outperform other ensemble techniques for survivability prediction of breast cancer sufferers. Our findings show that factor analysis combined with ensemble machine learning produces better prediction performance than single models.