In this chapter, we discussed the significance of model selection; specifically, selecting classification techniques and related estimators. We saw how using the IBM Cloud platform and Watson Studio offers a way to explore the performance of various techniques and estimators in an efficient and effective way. Using this easy exploration process, you can feel confident that your selected model fits to the data well. We also saw how to use Watson Studio to build, deploy, and test a model and configure it for continuous learning.

In the next chapter, we will discuss the difference between supervised and unsupervised learning, as well as looking at semi-supervised learning. Moreover, we will look at the concept of clustering algorithms, and examine online versus batch learning.