Random Survival Forests for Lifetime Data: Modeling Recurrent and Terminal Events with RecForest

In many real-world applications, events of interest can occur multiple times for the same subject, requiring methods that go beyond traditional survival analysis. This thesis investigates machine learning approaches for predicting recurrent events in time-to-event data. The study will explore advanced survival models, including Random Survival Forests and other suitable techniques, to handle repeated occurrences of events over time. The goal is to develop a flexible and effective framework for modeling recurrent event data using machine learning, with applications in domains such as engineering, healthcare, or industrial systems.