Analysis of WTTE-RNN Variants that Improve Performance

Abstract

Businesses typically have assets such as machinery, electronics or their customers. These assets share a common trait in that at some stage they will fail or, in the case of customers, they will churn. Knowing when and where to focus limited resources is a key area of concern for businesses. A prediction model called the WTTE-RNN was shown to be effective for predicting the time to event for topics such as machine failure. The purpose of this research is to identify neural network architecture variants of the WTTE-RNN model that have improved performance. The research results on these WTTE-RNN model variant would be useful in the application of the model.