In this article I present a complete system for clustering non-numeric data. The underlying algorithm is based on a metric called category utility (CU). The CU metric is a measure how much information ...

In analysis, continuous data may be reduced to several categories, eg, age or blood pressure, but do not be tempted to record numerical data as categorical at the outset (“age range, 40–49 ...

In this article I'll show you how to cluster non-numeric, or mixed numeric and non-numeric data, using a clever idea called category utility (CU). [Click on image for larger view.] Figure 1.