The Deep Promotion Time Cure Model
This provides an incremental improvement for researchers and practitioners in survival analysis, particularly in finance or healthcare, by enhancing predictive accuracy and interpretability in large-scale datasets.
The paper tackles the problem of predicting time-to-event data with cure fractions by integrating flexible survival models into a deep neural network, achieving better predictive performance and more realistic covariate effects in simulations and a US mortgage loan application.
We propose a novel method for predicting time-to-event in the presence of cure fractions based on flexible survivals models integrated into a deep neural network framework. Our approach allows for non-linear relationships and high-dimensional interactions between covariates and survival and is suitable for large-scale applications. Furthermore, we allow the method to incorporate an identified predictor formed of an additive decomposition of interpretable linear and non-linear effects and add an orthogonalization layer to capture potential higher dimensional interactions. We demonstrate the usefulness and computational efficiency of our method via simulations and apply it to a large portfolio of US mortgage loans. Here, we find not only a better predictive performance of our framework but also a more realistic picture of covariate effects.