<p>This study compares machine learning and deep learning models with a traditional statistical model. The inverted exponentiated Rayleigh distribution has been applied to model the failure time of turbofan engines. For the statistical model development, we employed maximum likelihood estimation to determine the model’s parameters. The performance of the model has been explained in terms of four survival measures: hazard rate function, cumulative hazard rate function, probability density function and reliability function. Furthermore, we have employed four different machine learning models and two deep learning models, including artificial neural networks and gated recurrent units. In deep learning models, two hidden layers of 8 and 6 neurons, respectively, have been considered for the development of artificial neural networks. The gated recurrent unit model is a type of recurrent neural network that is more suitable for processing sequential data. It can learn the dependencies between consecutive time steps and, therefore, is suitable for modeling failure datasets. All the models have been trained on data, and we have calculated their mean squared error and coefficient of determination for testing datasets to compare their performance. Furthermore, we also performed an error band analysis to check the correctness of predictions for all models. Hence, based on the findings, machine learning and deep learning models can be used to represent survival measures.</p>