SAS Enterprise Miner Exersice

Chapter 8 – Pattern Discovery Association

1.   Conducting anAssociation Analysis

A store is interested in determining the associations betweenitems purchased from the Health and Beauty Aids Department and theStationery Department. The store chose to conduct a market basketanalysis of specific items purchased from these two departments.The TRANSACTIONSdata set contains informationabout more than 400,000 transactions made over the past threemonths. The following products are represented in the data set:

bar soap

bows

candy bars

deodorant

greeting cards

magazines

markers

pain relievers

pencils

pens

perfume

photo processing

prescription medications

shampoo

toothbrushes

toothpaste

wrapping paper

There are four variables in the data set:

Name	Model Role	Measurement Level	Description
STORE	Rejected	Nominal	Identification number of the store
TRANSACTION	ID	Nominal	Transaction identification number
PRODUCT	Target	Nominal	Product purchased
QUANTITY	Rejected	Interval	Quantity of this product purchased

2.   Create a new diagram. Namethe diagram Ch_08_Assoc_Transactions.

3.   Create a new data source.Use the data set AAEM.TRANSACTIONS.

4.   Assign the model roleRejected to the variables STORE and QUANTITY. These variables arenot used in this analysis. Assign the ID model role to the variableTRANSACTION and the Target model role to the variable PRODUCT.

5.   Add the node for theTRANSACTIONS data set and an Association node to the diagram.

6.   Change the setting forExport Rule by ID to Yes.

7.   Do not change the remainingdefault settings for the Association node and run the analysis.

8.   Examine the results of theassociation analysis.

What is the highest lift value for the resultingrules?                                                              

Which rule has thisvalue?                                                                                                      

Identify all rules that have a Lift greater than2.0.  For each rule, provide the Support, Confidence,Expected Confidence, Lift, and the actual Rule.

For any two different rules (i.e., not symmetric) with a liftgreater than 2.0, for each rule:

Provide an explanation of why you think this rule makessense

Three different methods that a store manager can use this ruleto increase their profit on the related products.  

9.   The submittal for thischapter will be a Word document containing the screen shotscaptured. Make sure to clearly label each of the screen shots toexplain the purpose of the screen shot.

10.   Additionally, as yougenerate results using SAS Enterprise Miner, you need to explainyour results from a business perspective.  This meansthat you need to explain the results in non-technical terms as wellas the business implications of the results.