Classification models
In the previous chapter, we covered predictive modeling. Classification is a type of predictive modeling; specifically, classification is a regression analysis where the dependent attribute or the target is categorical instead of numerical.
Even though classification is a subset of predictive modeling, it is the area of data mining that has received the most attention due to its usefulness. At the core of many machine learning (ML) solutions in the real world today is a classification algorithm. Despite its prevalent applications and complicated algorithms, the fundamental concepts of classification are simple.
Just as with prediction, for classification, we need to specify our independent attributes (predictors) and the dependent attribute (target). Once we are clear about these and we have a dataset that includes these attributes, we are set to employ classification algorithms.
Classification algorithms, just as with prediction algorithms, seek to find...