To improve predictive accuracy, databases can be segmented into more homogeneous groups.
Then the data of each group can be explored, analyzed and modeled. Depending on the business
question, segmentation can be done using variables associated with risk factors, profits or
behaviors. Segments based on these types of variables often provide sharp contrasts, which can be
interpreted more easily. Classification maps data into predefined groups or segments.
Classification algorithms require that the classes be defined based on data attributes values. They
often describe these classes by looking at the characteristics of data already known to belong to
the classes. As a result, insurance companies can more accurately predict the likelihood of a
policy based on the premium mode, premium amount, policy period depending upon age, income
and occupation.