tell me more icon Identify Important Attributes

If a data set has many attributes, it is likely that not all attributes will contribute to a predictive model. Indeed, some attributes may simply add noise, that is, they actually detract from the model's predictive value. Oracle Data Mining provides Attribute Importance (AI) that uses the Minimum Description Length algorithm to rank the attributes by significance in determining the target value.

In Data Miner, use a Filter Columns node to determine important attributes. Data Miner builds an Attribute Importance model on a sample of the data and returns the results in the form of hints.

To determine important attributes, select the Attribute Importance setting of Filter Columns, select a target, and run the Filter Columns node.

Select attribute importance setting

After execution completes, the rank of each column is returned in the form of hints.

Hints returned by column filter attribute importance

You must decide which columns to ignore in subsequent nodes (that is, which columns are not passed on). To ignore a column, click output indicator in the Output column for the item.