In this chapter, we described the most widely used methods to establish correlations between variables, which will later be used as features in a machine learning model. This is a long and difficult task, but is the basis of a good predictive model.
No method can be used alone to determine which features are important and which can be discarded. A combination of methods, plus a deep knowledge of the dataset, are fundamental to complete this task.
In the next chapter, we will leave the preliminary tasks and start focusing on some real use cases of the machine learning models.
