sales department, sales efforts that are guided by more quantitative data mining approaches can
lead to more focused and more successful results. A traditional sales approach is to increase the
number of policyholders by simply targeting those who meet certain policy constraints. A
drawback to this approach is that much of the marketing effort may yield little return. At some
point, sales become more difficult and greater marketing budgets lead to lower and lower returns.
Hence in this situation it is important to identify population segments among already insured
customers through which uninsured customers could be targeted. A statistical technique called
“cluster analysis,” sometimes used in the private sector to identify various market segments, was
used to identify target groups of uninsured adults based on the previous available data of policy
holders. Clustering is a technique of partitioning or segmenting the data into groups that might or
might not be disjointed. The clustering usually accomplished by determining the similarity among
the data on predefined attributes. The most similar data are grouped into clusters. Since clusters
are not predefined, a domain expert is often required to interpret the meaning of the created
clusters.