In this chapter, we have discussed the main reasons that justify the employment of machine learning models and how a dataset can be analyzed in order to describe its features, enumerate the causes behind specific behaviors, predict future behavior, and influence it.
We also explored the differences between supervised, unsupervised, semi-supervised, and reinforcement learning, focusing on the first two models. We also used two simple examples to understand both supervised and unsupervised approaches.
In the next chapter, we'll introduce the fundamental concepts of cluster analysis, focusing the discussion on some very famous algorithms, such as k-means and K-Nearest Neighbors (KNN), together with the most important evaluation metrics.