Although you may already have some idea about which types of modeling are most appropriate for your organization’s needs, now is the time to make some firm decisions about which ones to use. Determining the most appropriate model will typically be based on the following considerations:

·         The data types available for mining. For example, are the fields of interest categorical (symbolic)?

·         Your data mining goals. Do you simply want to gain insight into transactional data stores and unearth interesting purchase patterns? Or do you need to produce a score indicating, for example, propensity to default on a student loan?

·         Specific modeling requirements. Does the model require a particular data size or type? Do you need a model with easily presentable results?

Choosing the Right Modeling Techniques:

A wide variety of techniques is available in IBM® SPSS® Modeler. Frequently, data miners use more than one to approach the problem from a number of directions.

When deciding on which model(s) to use, consider whether the following issues have an impact on your choices:

• Does the model require the data to be split into test and training sets?
• Do you have enough data to produce reliable results for a given model?
• Does the model require a certain level of data quality? Can you meet this level with the current data?
• Are your data the proper type for a particular model? If not, can you make the necessary conversions using data manipulation nodes?

Many modeling techniques make specific assumptions about the data—for example, that all attributes have uniform distributions, no missing values allowed, class attribute must be symbolic, etc. Record any such assumptions made