Summary

In this chapter, we have learned to differentiate between supervised and unsupervised learning. We also performed and compared the DIANA, AGNES, and k-means clustering techniques, and discussed the applications of clustering.

We have thus covered the basics of identifying machine learning-related business problems, preparing datasets for analysis, and selecting and training suitable model architectures and evaluating their performance. We covered the basics of a commonly used set of machine learning methods and used different R packages, such as rpart, randomForest, MICE, groupdata2, and cvms. Having worked with tasks such as classification, regression, and clustering, you now possess the tools required to tackle many of your data-related business problems.