Deployment of a predictive model so that it can be leveraged in routine decision-making is typically a somewhat complex process due to a variety of challenges, and let's face it—predictive models that never get deployed never add value.
When you create a model by using the IBM Watson Studio model builder, you can deploy the model directly from the model builder after you train it. Even better, after you deploy your model, you can set up a continuous learning and evaluation process for your model.
When you deploy a model, you save it to the model repository that is associated with your Watson Machine Learning service, where you can then use your deployed model to score data and build an application.