Breast cancer recurrence presents a significant challenge that affects patient well-being, healthcare systems, and society at large. Contemporary sensing technologies offer significant potential for obtaining insights and identifying patterns associated with recurrent events. Despite the potential, limited research has explored survival analysis of breast cancer recurrences utilizing the extensive healthcare data available. Utilizing this data is essential for comprehending the factors that contribute to breast cancer recurrence. This study presents an ensemble method called random survival forest for the analysis of time-to-event patterns in breast cancer recurrences, utilizing data from the Surveillance, Epidemiology, and End Results (SEER) program. The model delineates the survival probabilities for patients with and without recurrences of breast cancer. Ensemble models are developed through systematic sampling and bootstrapping of large data sources. The experimental findings indicate that the age at cancer recurrence and the interval between recurrences approximate Gaussian and exponential distributions, with means of 61.35 ± 14.03 years and 2.61 years, respectively. The results indicate significant factors, including age, surgical status, tumor stage, and histological grade, that affect the likelihood of breast cancer recurrences. This proposed method in survival analysis has significant potential to assist healthcare practitioners in the prognosis, treatment, and decision-making related to breast cancer recurrences.