In this chapter, we discussed machine learning and why it is everywhere. We also looked at supervised and unsupervised machine learning. We discussed the reason that machine learning creates its own vocabulary and how it relates to the statistical vocabulary.

Many other methods were discussed:

• tree models, their strengths and weakness
• essemble methods such as random forests
• hierarchical and k-means clustering

Finally, the chapter introduced feedforward neural networks with R using the h2o package. In the next chapter, we will cover ways in which we can evaluate the quality and characteristics of various datasets in an effort to find insights from the data.