SQL/MX Data Mining Guide

HP NonStop SQL/MX Data Mining Guide—523737-001
4-1
4 Mining the Data
This section describes the next three steps of the process, Steps 7 through 9.
1. Identify and define a business opportunity.
2. Preprocess and load the data for the business opportunity.
3. Profile and understand the relevant data.
4. Define events relevant to the business opportunity being explored.
5. Derive attributes.
6. Create the data mining view.
7. Mine the data and build models.
Model building can be done by extracting the mining data into a special mining
tool, such as Enterprise Miner from the SAS Institute. A detailed discussion of the
use of this tool is beyond the scope of this manual.
However, this manual does include building a decision tree as an example of a
technique that could be used by a data mining tool for building a model. See
Building the Model on page 4-2.
8. Deploy models.
Deployment can take many different forms. For example, deployment might be as
simple as documenting and reporting the results, or deployment might be
embedding the model in an operational system to achieve predictive results.
See Deploying the Model on page 4-10.
9. Monitor model performance.
Performance of the model must be monitored for accuracy. When accuracy begins
to decline, the model must be updated to fit the current situation.
See Monitoring Model Performance
on page 4-11.