After the training instance, we should be able to persist the model and then reuse its capabilities as an API. API access to the customer churn model will enable an external application to predict the customer retention. We will use Spring Boot, along with Thymeleaf, for the UI demonstration. We will deploy and run the application locally for the demonstration. In this recipe, we will create an API for a customer churn example.
Deploying the neural network model and using it as an API
Getting ready
As a prerequisite for API creation, you need to run the main example source code:
https://github.com/PacktPublishing/Java-Deep-Learning-Cookbook/blob/master/03_Building_Deep_Neural_Networks_for_Binary_classification/sourceCode/cookbookapp...
