ABSTRACT
This chapter discusses data exploration. The techniques discussed in this chapter can be used to examine new incoming data for patterns, regularities, and to get a “feel” for what issues may be relevant in the data. The techniques discussed in this chapter can be divided into two broad categories: descriptive analyses and unsupervised learning. Descriptive analyses involve initial exploration of the data. With reporting, analysts aim to provide management information on some relevant descriptive statistics about specific KPIs, such as market share, customer satisfaction, and/or customer profitability. With profiling, analysts aim to provide insights into differences between brands or customer segments. The chapter considers five important steps when executing an analysis: selection of cluster variables, data preparation, running the analysis, selecting the number of clusters, and profiling the clusters.
