Have access to or have Installed Oracle Database 11g Enterprise Edition, Release 2 (11.2.0.1) with Data Mining Option.

Have access to or have installed Oracle SQL Developer, version 3.0, or later.

Note: SQL Developer does not have an installer. To install SQL Developer, just unzip the free SQL Developer download to any directory on your PC.

Have set up Oracle Data Miner 11g Release 2 for use within Oracle SQL Developer.

Note: If you have not already set up Oracle Data Miner, complete the following lesson: Setting Up Oracle Data Miner 11g Release 2.

In the Data Miner tab, right-click the data mining user connection that you previously created, and select New Project, as shown here:

In the Create Project window, enter a project name (in this example ABC Insurance) and then click OK.

Note: You may optionally enter a comment that describes the intentions for this project. This description can be modified at any time.

Result: The new project appears below the data mining user connection node.

Right-click your project (ABC Insurance) and select New Workflow from the menu.

Result: The Create Workflow window appears.

In the Create Workflow window, enter Targeting Best Customers as the name and click OK.

Result:

• In the middle of the SQL Developer window, an empty workflow canvas opens with the name that you specified.
• On the right-hand side of the interface, the Component Palette tab of the Workflow Editor appears (shown below with a red border).
• In addition, three other Oracle Data Miner interface elements are opened:
  • The Thumbnail tab
  • The Workflow Jobs tab
  • The Property Inspector tab

The first element of any workflow is the source data. Here, you add a Data Source node to the workflow, and select the CUST_INSUR_LTV_SAMPLE table as the data source.

A. In the Component Palette, click the Data category. A list of data nodes appear, as shown here:

B. Drag and drop the Data Source node onto the Workflow pane.

Result: A Data Source node appears in the Workflow pane and the Define Data Source wizard opens.

Notes:

• Workspace node names and model names are generated automatically by Oracle Data Miner. In this example, the name "Data Source" is generated. You may not get exactly the same node and model names as shown in this lesson.
• You can change the name of any workspace node or model using the Property Inspector.

In Step 1 of the wizard:

A. Select CUST_INSUR_LTV_SAMPLE from the Available Tables/Views list, as shown here:

Note: You may use the two tabs in the bottom pane in the wizard to view and examine the selected table. The Columns tab displays information about the table structure, and the Data tab shows a subset of data from the selected table or view.

B. Click Next to continue.

In Step 2 of the wizard, you may remove individual columns that you don't need in your data source. In our case, we'll keep all of the attributes that are defined in the table.

At the bottom of the wizard window, click Finish.

Result: As shown below, the data source node name is updated with the selected table name, and the properties associated with the node are displayed in the Property Inspector, located below the Component Palette pane.

Notes:

• You can resize nodes in the workflow canvas by entering or selecting a different value from the Zoom options. Notice that 75% has been selected from the Zoom pull-down list.
• You can add descriptive information about any node by using the Details tab in the Property Inspector.
• The Thumbnail tab also provides a smaller display of the larger workflow window. As you drag nodes around the workflow window, the thumbnail view automatically adjusts.

A. First, click on Models in the Component Palette to display the available list:

B. Then, drag the Classification node from the paleltte to the Workflow pane, like this:

C. Drop the node onto the workflow. After a moment, a "Class Build" node appears in the workflow:

Notes:

• As stated previously, a yellow exclamation mark on the border indicates that more information needs to be specified before the node is complete.

• In this case, two actions are required:

1. A link must be created between the source data node and the classification build node.
2. Two attributes should be specified for the classification build process.

First, connect the data source node to the classification build node using the same technique described previously.

Result: the Edit Classification window appears.

Notes:

• Notice that a yellow "!" indicator is displayed next to the Target field. This means that an attribute must be selected for this item.
• The names for each model are automatically generated, and yours may differ slightly from those in this example.

In the Edit Classification window:

A. Select BUY_INSURANCE as the Target attribute.

B. Select CUSTOMER_ID as the Case Id attribute.

Notes:

• Although not required, it is advised that you define a Case Id to uniquely define each record. This helps with model repeatability and is consistent with good data mining practicies.
• As stated previously, all four algorithms for Classification modeling are selected by default. They will be automatically run unless you specify otherwise.

Optionally, you can modify specific settings for each of the algorithms by using the Advanced button.

A. Click Advanced at the bottom of the Edit Classification window to display the Advanced Settings window, as shown here:

Notes:

• The Advanced Settings window enables you to specify data usage, algorithm settings, and performance settings for each of the four classificaiton algorithms.
• You can also de-select (and re-select) any algorithm from this window.

B. Select the Support Vector Machine algorithm and click the Algorithm Settings tab.

C. Then, In the Kernel Function option, select Linear, as shown here:

Note: We want to change the value of this Support Vector Machine (SVM) algorithm setting from the system determined value to Linear in order to make the model results easier to interpret.

D. Feel free to view any of the tabs for each algorithm, however do not modify any of the other default settings.

E. When you are done browsing, click OK to save the SVM algorithm setting and close the Advanced Settings window.

Finally, click OK in the Edit Classification window to save your changes.

Result: The classification build node is ready to run.

Note: In the Models tab of the Properties Inspector, you can see the current status for each of the selected algorithms, as shown below:

Save the workflow by clicking the Save All icon in main toolbar.

Right-click the classification build node and select Run from the pop-up menu.

Notes:

• When the node runs it builds and tests all of the models that are defined in the node.
• As before, a green gear icon appears on the node border to indicate a server process is running, and the Workflow Jobs tab shows the status of the build.

When the build is complete, the status column displays a green check mark.

In the workflow pane, the border of the build node changes from a green gear turning to a green check mark, like this:

Once the build process is complete, you can view several pieces of information about the build using the property inspectory.

A. Select the classification build node in the workflow, and then choose the Models tab in the Property Inspector.

Notes:

• All four models have been succesfully built.
• The models all have the same target (BUY_INSURANCE) but use different algorithms.
• The source data is automatically divided into test data and build data.

Right-click the classification build node and select Compare Test Results from the menu.

Results: A Class Build display tab opens, showing a graphical comparison of the four models, as shown here:

Notes:

• Since the sample data set is very small, the numbers you get may differ slightly from those shown in the tutorial example. In addition, the histogram colors that you see may be different then those shown in this example.
• The comparison results include five tabs: Performance, Performance matrix, ROC, Lift, and Profit.
• The Performance tab provides numeric and graphical information for each model on Predictive Confidence, Average Accuracy, and Overall Accuracy.
• The Performance tab seems to indicate that:
  • The Decision Tree (DT) is providing the highest Predictive Confidence.
  • Both the DT and Generalized Linear Model (GLM) are providing the highest Overall Accuracy results.

Select the Lift tab.

Notes:

• The Lift tab provides a graphical presentation showing lift for each model, a red line for the random model, and a vertical blue line for threshold.
  • Lift is a different type of model test. It is a measure of how “fast” the model finds the actual positive target values.
  • The Lift viewer compares lift results for the given target value in each model.
  • The Lift viewer displays Cumulative Positive Cases and Cumulative Lift.

Using this example:

• At the 20th quantile, the DT model provides the greatest Cumulative Lift, just above the GLM model (see above).
• You can move the Quanitile measure point line along the X axis of the graph by using the slider tool. The data in the Models pane at the bottom updates automatically as you move the slider left or right.
• As you move up the quantile range, the Cumulative Lift of the GLM and Support Vector Machine (SVM) models fluxuate near or below that of the DT model, and the Naive Bayes (NB) model shows more of a linear increase, but still below that of the DT model.
• At just above the 52nd quantile (see below), the NB and GLM models provide almost the same Cumulative Lift as the DT model, but none of the other models surpass the lift results of the DT model.

Next, select the Performance Matrix tab.

Note: The Performance Matrix shows that the GLM and DT models have a higher Correct Prediction percentage than the other models, at over 80% each.

Compare the details for the GLM and DT models.

First, select the GLM model to view the Target Value Details for this model. Recall that the "Target Value" for each of the models is the BUY_INSURANCE attribute.

Note: The GLM model indicates a 92.6% correct prediction outcome for customers that don't buy insurance, but only a 47.3% correct prediction outcome for customers that do buy insurance.

Next, select the DT model.

Notes: The DT model indicates an 82.5% correct prediction outcome for customers that don't buy insurance, and an 80.2% correct prediction outcome for customers that do buy insurance.

After considering the initial analysis, you decide to investigate the Decision Tree model more closely.

First, dismiss the Class Build - Compare Models tab, as shown here:

Back in the workflow canvas, right-click the Class Build node again, and select View Models > CLAS_DT_2_2 (Note: The exact name of your Decision Tree model may be different).

Result: A window opens that displays a graphical presentation of the Decision Tree.

The interface provides several methods of viewing navigation:

• The Thumbnail tab provides a high level view of the entire tree. For example, the Thumbnail tab shows that this tree contains five levels, although you view fewer of the nodes in the primary display window.
• You can move the viewer box around within the Thumbnail tab to dynamically locate your view in the primary window. You can also use the scroll bars in the primary display window to select a different location within the decision tree display.
• Finally, you can change the viewer percentage zoom in the primary display window to increase or descrease the size of viewable content.

For example, set the the primary viewer window for the decision tree to 100% zoom. This provides a more narrow view than 75%, but the content within the view is somewhat larger.

First, navigate to and select Node 2 and click on it to select it.

Notes:

• At each level within the decision tree, an IF/THEN statement that describes a rule is displayed. As each additional level is added to the tree, another condition is added to the IF/THEN statement.
• For each node in the tree, summary information about the particular node is shown in the box.
• In addition, the IF/THEN statement rule appears in the Rule tab, as shown below, when you select a particular node.
• Commonly, a decision tree model would show a much larger set of levels and also nodes within each level in the decision tree. However, the data set used for this lesson is significantly smaller than a normal data mining set, and therefore the decision tree is also small.

Notes:

• At this level, we see that the first split is based on the BANK_FUNDS attribute, and the second split is based on the CHECKING_AMOUNT attribute.
• Node 2 indicates that if BANK_FUNDS are greater than 225.5, and CHECKING_AMOUNT is less than or equal to 157.5, then there is a 61.38% chance that the customer will buy insurance.

Next, select Node 6, at the bottom level in the tree.

Notes:

• At this bottom level in the tree, a final split is added for the MONEY_MONTHLY_OVERDRAWN attribute.
• This node indicates that if BANK_FUNDS are greater than 225.5, and CHECKING_AMOUNT is less than or equal to 157.5, and CREDIT_BALANCE is less than or equal to 462, and MONEY_MONTHLY_OVERDRAWN is greater than 53.88, then there is a 96% chance that the customer will buy insurance.

Dismiss the Decision Tree display tab as shown here:

In the workflow, select the Class Build node. Then, using the Models tab of the Property Inspector, deselect all of the models except for the DT model.

To deselect a model, click the large green arrow in the model's Output column. This action adds a small red "x" to the column, indicating that the model will not be used in the next build.

When you finish, the Models tab of the Property Inspector should look like this:

Note: Now, only the DT model will be passed to subsequent nodes.

Next, create a new Data Source node in the workflow.

Note: Even though we are using the same table as the "Apply" data source, you must still add a second data source node to the workflow.

A. From the Data list in the Component Palette, drag and drop the Data Source node to the workflow canvas, like this:

B. In the Define Data Source wizard, select the CUST_INSUR_LTV_SAMPLE table, and then click FINISH.

Result: A new data souce node appears on the workflow canvas.

C. Select the new data source node, and using the Details tab of the Property Inspector, change the Node Name to CUST_INSUR_LTV_APPLY, like this:

Result: The new table name is reflected in the workflow.

Next, open the Evaluate and Apply list in the Components Palette, like this:

A. Drag and drop the Apply node to the workflow canvas, like this:

Result: An Apply node is added to the workflow with a yellow exclamation mark in its border. This, of course, indicates that more information is required before this node may be run.

B. Using the Details tab of the Property Inspectory, rename the Apply node to Apply Model.

Using the techniques described previously, connect the Class Build node to the Apply Model node, like this:

Then, connect the CUST_INSUR_LTV_APPLY node to the Apply Model node:

Notes:

• The yellow exclamation mark disappears from the Apply node border once the second link is completed.
• This indicates that the node is ready to be run.

Before you execute the apply model node, consider the resulting output. By default, an apply node creates two columns of information for each customer:

• The prediction (Yes or No)
• The probability of the prediction

However, you really want to know this information for each customer, so that you can readily associate the preditive information with a given customer.

To get this information, you need to add a third column to the apply output: CUSTOMER_ID. Follow these instructions to add the customer id to the output:

A. Right-click the APPLY MODEL node and select Edit.

Result: The Edit Apply Details window appears. Notice that the Prediction and Probability columns are defined automatically in the Apply Columns tab.

B. In the Edit Apply Details window, select the Data Columns tab, and then click the green "+" sign, like this:

C.In the Edit Output Data Column Dialog:

• Select CUSTOMER_ID in the Available Attributes list
• Move it to the Selected Attributes list by using the shuttle control
• Then click OK.

Result: the CUSTOMER_ID column is added to the Data Columns tab.

D. Finally, click OK in the Edit Apply Details window to save the change.

Now, you are ready to execute the Apply node. Right-click the Apply Model node and select Run from the menu.

Result:

• As before, small green gear icons appear in each of the nodes that are being processed, and the Workflow Jobs tab displays the progress.
• When the process is complete, green check mark icons are displayed in the border of all workflow nodes, and the workflow document is automatically saved.

Optionally, you can create a database table to store the model prediction results (the "Apply" results).

The table may be used for any number of reasons. For example, an application could read the predictions from that table, and suggest an appropriate response, like sending the customer a letter, offering the customer a discount, or some other appropriate action.

To create a table of model prediction results, perform the following:

A. Using the Data list in the Component Palette, drag the Create Table or View node to the workflow canvas, like this:

Result: an OUTPUT node is created.

B. Connect the Apply Model node to the OUTPUT node.

C. Specify a name for the table that will be created (otherwise, Data Miner will create a default name):

1. Right-click the OUTPUT node and select Edit from the menu.
2. In the Edit Create Table or View window, change the default table name to DT_PREDICTIONS, as shown here

3. Then, click OK.

D. Lastly, right-click the DT_PREDICTIONS node and select Run from the menu.

Result: When the process is complete, the workflow document is automatically saved, and all nodes contain a green check mark in the border, like this:

Note: After you run the OUTPUT node (DT_PREDICTIONS), the table is created in your schema.

A. To view the results, right-click the DT_PREDICTIONS Table node and select View Data from the Menu.

Result: A new tab opens with the contents of the table.

Notes:

• The table contains two columns: one for the predicted outcome (Yes or No) and one for the probability of the prediction.
• You can sort the table results on any of the columns using the Sort button, as shown here.
• In this case, the table will be sorted using the Predicted outcome (CLAS_DT_2_2_PRED column), in Descending order.

B. Click Apply Sort to view the results:

Notes:

• Each time you run an Apply node, Oracle Data Miner takes a different sample of the data to display. With each Apply, both the data and the order in which it is displayed may change. Therefore, the sample in your table may be different from the sample shown here. This is particularly evident when only a small pool of data is available, which is the case in the schema for this lesson.
• You can also filter the table by entering a Where clause in the Filter box.
• The table contents can be displayed using any Oracle application or tools, such as Oracle Application Express, Oracle BI Answers, Oracle BI Dashboards, and so on.

C. When you are done viewing the results, dismiss the tab for the DT_PREDICTIONS table, and click Save All.