In this chapter, we learned how to develop a real-life application called options trading using a RL algorithm called Q-learning. The IBM stock datasets were used to design a machine learning system driven by criticisms and rewards. Additionally, we learned some theoretical background. Finally, we learned how to wrap up a Scala desktop application as a web app using Scala Play Framework and deploy it in production.
In the next chapter, we will see two examples of building very robust and accurate predictive models for predictive analytics using H2O on a bank marketing dataset. For this example, we will be using bank marketing datasets. The data is related to direct marketing campaigns of a Portuguese banking institution. The marketing campaigns were based on phone calls. The goal of this end-to-end project will be to predict that the client will subscribe a term deposit.