In this chapter, we discovered some important concepts regarding association rules. In particular, we examined how important support, confidence, and lift measures are in the assessment of association rules, and that high support and confidence do not necessarily mean that an association rule is useful. We uncovered the efficient working of the apriori algorithm for mining association rules and discovered the use of apriori in R in mining several datasets. We have also seen that it is often necessary to recode some variables before being able to analyze the data. Finally, we have discovered Grouped matrix-based visualization.

In next chapter, we will examine statistical distributions and correlations.