Cleveland State University

Building a Data Mining Model using

Data Warehouse and OLAP Cubes
IST 734
SS Chung

14

Sunnie S Chung IST 734

 Build a Data Mining Model using Data
Warehouse and OLAP cubes

Contents

1. Abstract: ................................................................................................................................................ 3
2. Introduction:.......................................................................................................................................... 3
3. Adventure works database: ................................................................................................................... 4
4. Getting familiar with Sql Server Analysis Services (SSAS) tools and various datamining algorithms 5
4.1. Microsoft Association Algorithm .................................................................................................. 6
4.2. Microsoft Clustering Algorithm.................................................................................................... 9
4.3. Microsoft Time Series Algorithm ................................................................................................ 12
4.4. Microsoft Decision Trees Algorithm .......................................................................................... 16
5. Star schema: ........................................................................................................................................ 19
5.1. Fact Tables and Dimension Tables .................................................................................................. 19
5.2. Steps in Star Schema Design: .......................................................................................................... 19
6. Cube AND MDX: ............................................................................................................................... 19
6.1. Cube: ........................................................................................................................................... 19
6.2. Dimensions: ................................................................................................................................ 20
6.3. Measure & Measure Groups ....................................................................................................... 20
6.4. Steps in Building and Deploying a cube: .................................................................................... 20
7. Quering On Cubes Using MDX-Examples ......................................................................................... 26
7.1. Queries: ....................................................................................................................................... 26
7.2. Screenshots: ................................................................................................................................ 27
8. DataMining and DMX ....................................................................................................................... 32
8.1. Business Scenario1: .................................................................................................................... 32
8.2. Business Scenario2: .................................................................................................................... 36

Sunnie S Chung IST 734

 8.3. Business Scenario3: .................................................................................................................... 38
9. Conclusion: .......................................................................................................................................... 41
10. References: ..................................................................................................................................... 41

1. Abstract:

The purpose of this project is learn the application of various database and datamining concpets and its
application in current business using Adventure works database and various database tools.We begin by
designing a star schema and building a DataWarehouse OLAP cube, for Sales Analysis using Sql Server
Analysis Services (SSAS) and query the cube using MultiDimensional eXpressions language(MDX) to
find the current business trends.Next we create data mining structure using Data Mining
Extensions(DMX) and find the hidden pattern and predict things that are helpful in improving the
business and its growth. Some of the data mining techniques that will be considering to accomplish the
above tasks are Microsoft Association Mining, Cluster analysis, Time series and Naïve- Bayes Algorithm.

2. Introduction:

A data warehouse is a centralized repository that stores data from multiple information sources and
transforms them into a common, multidimensional data model for efficient querying and analysis.OLAP
and Data Mining are two complementary technologies for Business Intelligence.Online Analytical
Processing (OLAP) is a technology that is used to organize large business databases and support business
intelligence. OLAP is a database technology that has been optimized for querying and reporting, instead of
processing transactions OLAP databases are divided into one or more cubes, and each cube is organized
and designed by a cube administrator to fit the way that you retrieve and analyze data. OLAP is used for
decision-support systems to analyze aggregated information for sales, finance, budget, and many other
types of applications. OLAP is about aggregating measures based on dimensionhierarchies and storing these
precalculated aggregations in a special data structure. With the help of preaggregations and special indexes,
you can query aggregated data and get decision-support query results back in real time

OLAP provides us with a very good view of what is happening, but can not predict what will happen in
the future or why it is happening.This part is done by datamining.Data Mining is a combination of
discovering techniques + prediction techniques.

Sunnie S Chung IST 734

The sequence of steps that will be followed in this project is

1. Understand the Adventure works database which will be used in this project(fully understand the
transactional data available in the database).
2. Getting familiar with Sql Server Analysis Services (SSAS) tools and various datamining
algorithms such as Clustering,Association,Time Series etc in the SSAS tool
3. The next step will be to come up with a list of questions: what questions need to be answered,
what metrics will help business managers monitor and grow the business.
4. Based on the business questions that need to be answered, data staging layer in a star schema
format will be designed.
5. Then the cube will be built to extract data from the Star schema staging layer and we perform our
data mining on the cube.
6. Perform Datamining in the Adventure works database to find hidden patterns and information
using DMX and MDX.

3. Adventure works database:

In this section we will try to understand the Adventureworks database that will be used
as a part of the project.We try to understand scope of the business its various components and
products etc.

3.1. Business Overview:

Adventure Works Cycles is a large multinational bicycle manufacturer, with headquarters located in
Bothell, Washington. The company has approximately 300 employees, 29 of which are sales
representatives. The primary distribution channel for Adventure Works Cycles through the retail stores of
their resellers. These resellers are located in Australia, Canada, France, Germany, the United Kingdom,
and the United States. Adventure Works Cycles also sells to individual customers worldwide by means of
the Internet.

Adventure Works Cycles has five major product offerings:

Bikes – Three primary bike product lines: Mountain, Road, and Touring.

Accessories – Examples include helmets and water bottles.

Clothing – Examples include jerseys and biking shorts.

Components – Examples include bottom brackets and frames.

Services – Examples include premium service and standard service.

Sunnie S Chung IST 734

The version of Adventure works database that will be used in this project is Adventure works 2012

4. Getting familiar with SQL Server Analysis Services (SSAS) tools and
various data mining algorithms
In this section we will learn and understand some data mining algorithms and its applications that will
be used as a part of project later.

Sunnie S Chung IST 734

 4.1. Microsoft Association Algorithm
The Microsoft Association algorithm is an association algorithm provided by Analysis Services that is
useful for recommendation engines. A recommendation engine recommends products to customers
based on items they have already bought, or in which they have indicated an interest. The Microsoft
Association algorithm is also useful for market basket analysis.

Association models are built on datasets that contain identifiers both for individual cases and for the
items that the cases contain. A group of items in a case is called anitemset. An association model consists
of a series of itemsets and the rules that describe how those items are grouped together within the cases.
The rules that the algorithm identifies can be used to predict a customer's likely future purchases, based
on the items that already exist in the customer's shopping cart.

Sunnie S Chung IST 734

Sunnie S Chung IST 734
Sunnie S Chung IST 734
 4.2. Microsoft Clustering Algorithm

The Microsoft Clustering algorithm is a segmentation algorithm provided by Analysis Services. The
algorithm uses iterative techniques to group cases in a dataset into clusters that contain similar
characteristics. These groupings are useful for exploring data, identifying anomalies in the data, and
creating predictions.
Clustering models identify relationships in a dataset that you might not logically derive through casual
observation. For example, you can logically discern that people who commute to their jobs by bicycle do
not typically live a long distance from where they work. The algorithm, however, can find other
characteristics about bicycle commuters that are not as obvious. In the following diagram, cluster A
represents data about people who tend to drive to work, while cluster B represents data about people
who tend to ride bicycles to work.

• Clustering Model View

Sunnie S Chung IST 734

Sunnie S Chung IST 734
Sunnie S Chung IST 734
 4.3. Microsoft Time Series Algorithm
The Microsoft Time Series algorithm provides regression algorithms that are optimized for the forecasting
of continuous values, such as product sales, over time. Whereas other Microsoft algorithms, such as
decision trees, require additional columns of new information as input to predict a trend, a time series
model does not. A time series model can predict trends based only on the original dataset that is used to
create the model. You can also add new data to the model when you make a prediction and automatically
incorporate the new data in the trend analysis.

Sunnie S Chung IST 734

Sunnie S Chung IST 734
Sunnie S Chung IST 734
Sunnie S Chung IST 734
 4.4. Microsoft Decision Trees Algorithm
For discrete attributes, the algorithm makes predictions based on the relationships between input
columns in a dataset. It uses the values, known as states, of those columns to predict the states of a
column that you designate as predictable. Specifically, the algorithm identifies the input columns that are
correlated with the predictable column. For example, in a scenario to predict which customers are likely to
purchase a bicycle, if nine out of ten younger customers buy a bicycle, but only two out of ten older
customers do so, the algorithm infers that age is a good predictor of bicycle purchase. The decision tree
makes predictions based on this tendency toward a particular outcome.

• Decision Tree

Sunnie S Chung IST 734

Sunnie S Chung IST 734
For continuous attributes, the algorithm uses linear regression to determine where a decision tree splits.

Sunnie S Chung IST 734

 5. Building Data Mining Project with Data Warehouse and Cube

In the following section we will understand what a star schema is and the various terms in star schema
such as fact table, dimension table, measures, groups, etc and then design a star schema based on a list of
questions. This understanding will be the first step in our Data mining activity we will be performing as a
part of this project.

5.1. Star schema, Fact Tables and Dimension Tables

The star schema architecture is the simplest data warehouse schema. It is called a star schema because the
diagram resembles a star, with points radiating from a center. The center of the star consists of fact table
and the points of the star are the dimension tables.

A fact table typically has two types of columns: foreign keys to dimension tables and measures those that
contain numeric facts. A fact table can contain fact's data on detail or aggregated level.

A dimension is a structure usually composed of one or more hierarchies that categorizes data. If a
dimension hasn't got a hierarchies and levels it is called flat dimension or list. The primary keys of each
of the dimension tables are part of the composite primary key of the fact table. Dimensional attributes
help to describe the dimensional value. They are normally descriptive, textual values. Dimension tables
are generally small in size then fact table.

Typical fact tables store data about sales while dimension tables data about geographic region (markets,
cities), clients, products, times, channels.

5.2. Steps in Star Schema Design:

1. Identify a business process for analysis (like sales)

2. Identify measure or facts (sales dollar)
3. Identify dimensions for facts (product dimension, location dimension, etc)
4. List the columns that describe each dimension (region name, branch dimension, etc)
5. Determine the lowest level of summary in a fact table (sales dollar)

6. Cube AND MDX:

6.1. Cube:
OLAP Cube is the basic unit of storage for Multidimensional data, on which we can do analysis on stored
data and study the various patterns.

Sunnie S Chung IST 734

 6.2. Dimensions:
The primary functions of dimensions are to provide Filtering, Grouping and Labeling on your data.
Dimension tables contain textual descriptions about the subjects of the business. Dimensions in general
we can say are the Master entities with related member attributes using which we can study data stored in
OLAP Cube Quickly and effectively.

6.3. Measure & Measure Groups

Metrics value stored in your Fact Tables is called Measure. Measures are used to analyze performance of
the Business.Measure usually contains numeric data, which can be aggregated against usage of associated
dimensions. Measure Group holds collection of related Measure

6.4. Steps in Building and Deploying a cube:

To build an SSAS cube, you must first start a project by following these steps:

All Programs -> Microsoft SQL Server -> SQL Server BIDS

Create an Analysis Services project.

Name your project FirstCube and click OK.

You’re now presented with an empty window, which seems like a rare beginning to a project with a
template; really, you have nothing to start with, so it’s time to start creating. The first component you’ll
need is somewhere to retrieve data from: a data source.

Building a Data Source

To create the data source you’ll use for your first cube, follow these steps:

Sunnie S Chung IST 734

Navigate to the Solution Explorer pane on the right, right-click Data Sources, and click New Data Source.
This will bring up the Data Source Wizard, which will walk you through the creation process.

The next component you’ll create is the data source view.

Meanwhile, go ahead and click Next to continue creating your data source. In this next screen, it’s time to
set up a connection string.

If your AdventureWorksDW database is visible as a selection already, go ahead and choose it; if not,
click New.

For your server name, enter (local), and then drop down the box labeled Select or Enter a Database Name
and chooseAdventureWorksDW.

Click OK to return to the wizard and then click Next.

You can now enter the user you want SSAS to impersonate when it connects to this data source. Select
Use the Service Account and click Next. Using the service account (the account that runs the SQL Server
Analysis Server service) is fairly common even in production, but make sure that service account has
privileges to read your data source.

For your data source name, type AdventureWorksDW and then click Finish.

Building a Data Source View

Follow the below steps:

Right-click Data Source Views and choose New Data Source View. Predictably, up comes the Data
Source View Wizard to walk you through the process. Click Next.

Make sure the AdventureWorksDW data source is selected and then click Next.

On the Select Tables and Views screen, choose FactInternetSales under Available objects and then click
the right arrow to move it into the Included Objects column on the right.

To add its related dimensions, click the Add Related Tables button as shown in Figure 18-3 and then click
Next. Note that one of the related tables is a fact, not a dimension. There’s no distinction made at this
level. Later, you will be able to select and edit dimensions individually.

Sunnie S Chung IST 734

On the last screen, name your data source view according to its contents: Internet Sales.

Click Finish to create the Internet Sales data source view.

Sunnie S Chung IST 734

Creating an Analysis Services Cube. Right-click Cubes in the Solution Explorer and select New Cube to
bring up the Cube Wizard. This will walk you through choosing measure groups, the measures within
them, and your dimensions for this cube, click Next. On the Select Creation Method screen, make sure
Use Existing Tables is selected, and click Next.

The wizard will now want you to tell the wizard where to find measure groups. You could help it out by
telling the wizard that those are in your fact tables and then click Next.

Sunnie S Chung IST 734

Now the wizard would like to know which measures from your measure groups (fact tables) you’d like to
store in the cube. By default, it’s got them all selected; go ahead and accept this by clicking Next.

At this point, you have measures, but you still need some dimensions; the wizard will select the
dimension tables from your data source view to create as new dimensions. Again, by default they’re all
selected, and you can click Next.

The wizard is now ready to complete. Verify everything is done as per above steps. If everything appears
to be in order, click Finish.

Sunnie S Chung IST 734

Deploying the Cube

Deploying process can be started by following these steps.

Select Deploy First Cube on the Build menu. You’ll see a series of status messages as the cube is built,
deployed, and processed for the first time. You’ll receive a few warnings when you deploy FirstCube,
and if they’re warnings and not errors, you can safely ignore them for now.

When it’s done and you see Deployment Completed Successfully in the lower right, your first cube is
ready to browse.

Sunnie S Chung IST 734

 7. Querying On Cubes Using MDX-Examples
7.1. Queries:

Find the product which has been ordered more than 500 in all countries??

select filter(crossjoin([Dim Sales Territory].[Sales Territory Country].children,[Dim

Product].[English Product Name].children),
[Measures].[Order Quantity]>500) on rows,[Measures].[Order Quantity] on columns
from [star_sale_trend_analysis];

Retrieve the products whose sales amount > 5000

select {[Measures].[Sales Amount],[Measures].[Fact Internet Sales Count]} on columns,

filter([Dim Product].[English Product Name].children ,
[Measures].[Sales Amount]>5000) on rows
from [star_sale_trend_analysis];

Retrieve all the products in descending order of their Internet sales amount of year 2007

select nonempty([Measures].[Sales Amount]) on columns,

order([Dim Product].[English Product Name].members ,[Measures].[Sales Amount],desc) on rows
from [star_sale_trend_analysis]
where {[Fact Internet Sales - Order Date].[Calendar Year].&[2007]}

What is the product wise sales in United States??

select non empty([Dim Product].[English Product Name].children) on rows,

[Measures].[Sales Amount] on columns from [star_sale_trend_analysis]
where [Dim Sales Territory].[Sales Territory Country].&[United States]

What is sales amount in all the countries??

select non empty([Dim Sales Territory].[Sales Territory Country].children) on rows,

[Measures].[Sales Amount]on columns
from [star_sale_trend_analysis]

What is total sales amount in all countries for the year 2007??

Sunnie S Chung IST 734

select non empty([Dim Sales Territory].[Sales Territory Country].children) on
rows,[Measures].[Sales Amount]on columns from [star_sale_trend_analysis] where [Order
Date].[Calendar Year].&[2007]

7.2. Screenshots:
What is sales amount in all the countries??

Sunnie S Chung IST 734

 What is the product wise sales in United States??

What is total sales amount in all countries for the year 2007??

Sunnie S Chung IST 734

Find the products in descending order of their Internet sales amount of year 2007

Sunnie S Chung IST 734

Find the products whose sales amount is greater than 5000?

Find the product which has been ordered more than 500 in all countries??

Select NON EMPTY {[Measures].[Sales Amount]} on columns,

{[Dim Product].[English Product Name].members} on rows From [nnn_cube]

Sunnie S Chung IST 734

go
WITH
MEMBER [Order Date].[Calendar Quarter].[1st Half Sales] AS 'Sum({[Order Date].[Calendar Quarter].&[1],
[Order Date].[Calendar Quarter].&[2]})'
MEMBER [Order Date].[Calendar Quarter].[2nd Half Sales] AS 'Sum({[Order Date].[Calendar Quarter].&[3],
[Order Date].[Calendar Quarter].&[4]})'
SELECT {[Order Date].[Calendar Quarter].[1st Half Sales], [Order Date].[Calendar Quarter].[2nd Half Sales]} ON
COLUMNS
FROM [nnn_cube]

In the following section we perform the main part of our project i.e the data mining activity as a whole
where we did the bits and pieces so far.

The result of a star schema is nothing more than a table similar to a database table. Based on the business
need we created a table and now we are going to perform our task of finding the hidden activities in the
table in the following section.

Sunnie S Chung IST 734

In the earlier step we set the stage such as creating the table, understanding basically what a data mining
is, how to various algorithms work, how to query on the data using various querying languages like
MDX,DMX etc and now we start the play.

8. Data Mining and DMX:

Initial set up:

Find the tables which contains the data of the activity we are going to perform.

Find the appropriate data mining algorithm which would help us to solve our problem

8.1. Business Scenario1:

Adventure works is introducing a new Mountain bike. It is looking for a way to market its product
and reach customers who are more likely to buy the bike. So it is planning to find the profile of the
people who got Mountain Bikes in the past, and get the email address of the customers who has same
profile and send email.

Steps to be followed:

Step1: Cluster the database using Microsoft Clustering Algorithm

CREATE MINING STRUCTURE CIS698_Mountain_Bike_Marketing
(
[Marketingbike Key] LONG KEY,
[GeographyKey] LONG CONTINUOUS,
[Commute Distance] TEXT DISCRETE,
[House Owner Flag] LONG DISCRETE,
[Marital Status] TEXT DISCRETE,
[Number Cars Owned] LONG CONTINUOUS,
[Number Children At Home] LONG CONTINUOUS,
[Model] TEXT DISCRETE,
[Total Children] LONG CONTINUOUS,
[Yearly Income] LONG DISCRETIZED
)

INSERT INTO CIS698_Mountain_Bike_Marketing

(
[Marketingbike Key], [GeographyKey], [Commute Distance], [House Owner Flag],
[Marital Status], [Number Cars Owned], [Number Children At Home], [Model], [Total Children],
[Yearly Income]
)
OPENQUERY([Adventure Works DW2012],'SELECT [MarketingbikeKey],[GeographyKey], [CommuteDistance],
[HouseOwnerFlag] ,
[MaritalStatus],[NumberCarsOwned], [NumberChildrenAtHome], [Model], [TotalChildren],
[YearlyIncome] FROM [dbo].[cis698_marketing_bike]')

ALTER MINING STRUCTURE CIS698_Mountain_Bike_Marketing

ADD MINING MODEL CIS698_Mountain_Bike_MarketingCL
USING Microsoft_Clustering WITH DRILLTHROUGH

Sunnie S Chung IST 734

Step2: Find the cluster which has maximum probability of Mountain Bikes
SELECT NODE_NAME, NODE_CAPTION ,NODE_SUPPORT, NODE_DESCRIPTION
FROM [CIS698_Mountain_Bike_MarketingCL].CONTENT

SELECT FLATTENED PredictHistogram(Cluster())

From [CIS698_Mountain_Bike_MarketingCL]
NATURAL PREDICTION JOIN
(SELECT 'Mountain-500' AS [Model]) AS t

Sunnie S Chung IST 734

Step3: Use that profile to the company Customer database and get the email address of the customers who
are more likely to buy the bike and send them offers on the new product

Step 2 Result:

Number Cars Owned =0 , Yearly Income < 40419 , Commute Distance=0-1 Miles ,

55 <=GeographyKey <=337 , Number Children At Home =0 , 0 <=Total Children <=3 , House

Owner Flag=1 , Marital Status=M , Model=Road-350-W , Model=Road-750 , Model=Touring-3000 ,
Model=Road Bottle Cage , Model=Touring-2000 , Model=Touring Tire , Model=Cycling Cap ,
Model=Road-550-W , Model=Touring Tire Tube , Model=Mountain-400-W , Model=Long-Sleeve Logo
Jersey , Model=Mountain-500 , Model=Sport-100 , Model=ML Road Tire , Model=LL Road Tire ,
Model=Road-250 , Model=Road Tire Tube , Model=Water Bottle

SELECT distinct [LastName],[FirstName],[MiddleName],[EmailAddress] FROM

[dbo].[cis698_marketing_bike] where
NumberChildrenAtHome=0 and
TotalChildren BETWEEN 0 and 3 and
NumberCarsOwned =0 and YearlyIncome BETWEEN 10000 and 40419
and GeographyKey BETWEEN 55 and 337 and
CommuteDistance='1-2 Miles' or CommuteDistance='0-1 Miles'
and HouseOwnerFlag=1 and MaritalStatus='M'

Sunnie S Chung IST 734

Sunnie S Chung IST 734
 8.2. Business Scenario2
Adventure works tries to improves its market on Mountain Bikes further by offering offers or deals
on the items which are more likely to be purchased with Mountain Bikes.
CREATE MINING MODEL SubcategoryAssociations
(
[Customer ID] LONG KEY,
[Subcategories] TABLE PREDICT
(
[Subcategory] TEXT KEY
)
) USING Microsoft_Association_Rules

Train the association rules model:

INSERT INTO SubcategoryAssociations([Customer ID], [Subcategories](SKIP,[Subcategory]))

SHAPE
{
OPENQUERY([Adventure Works DW],'SELECT [OrderNumber] FROM [dbo].[vAssocSeqOrders] ORDER BY
[OrderNumber]')
}
APPEND
({OPENQUERY([Adventure Works DW],'SELECT [OrderNumber],[Subcategory] FROM (SELECT DISTINCT
vAssocSeqLineItems.OrderNumber,
DimProductSubcategory.EnglishProductSubcategoryName AS Subcategory FROM DimProduct
INNER JOIN DimProductSubcategory
ON DimProduct.ProductSubcategoryKey =
DimProductSubcategory.ProductSubcategoryKey
INNER JOIN vAssocSeqLineItems
ON DimProduct.ModelName = vAssocSeqLineItems.Model)
AS [CustomerSubcategories]
ORDER BY

Sunnie S Chung IST 734

 [OrderNumber]')
}
RELATE
[OrderNumber] TO [OrderNumber]
) AS [CustomerSubcategories]

Determine the top two subcategories a customer is likely to purchase that has purchased a road bike and a jersey:

SELECT
Predict([Subcategories],2) as [Subcategories]
FROM
[SubcategoryAssociations]
NATURAL PREDICTION JOIN
(SELECT
(SELECT 'Mountain Bikes' AS Subcategory
UNION SELECT 'Jerseys' AS Subcategory
) AS Subcategories
) AS t

Sunnie S Chung IST 734

 8.3. Business Scenario3
Adventure works is trying to forecast their sales based on the current trend and based on its results
whether it meets its expectations it is planning to change its business strategy.

CREATE MINING MODEL [cis698Forecasting]

(
[Reporting Date] DATE KEY TIME,
[Model Region] TEXT KEY,
[Quantity] LONG CONTINUOUS PREDICT,
[Amount] DOUBLE CONTINUOUS PREDICT
)
USING Microsoft_Time_Series (AUTO_DETECT_PERIODICITY = 0.8, FORECAST_METHOD = 'MIXED')
WITH DRILLTHROUGH

ALTER MINING STRUCTURE [cis698Forecasting_Structure]

ADD MINING MODEL [cis698Forecasting_ARTXP]
([Reporting Date],
[Model Region],
[Quantity] PREDICT,
[Amount] PREDICT
)
USING Microsoft_Time_Series (AUTO_DETECT_PERIODICITY = .08, FORECAST_METHOD = 'ARTXP')
WITH DRILLTHROUGH

INSERT INTO MINING STRUCTURE [cis698Forecasting_Structure]

(
[Reporting Date],[Model Region],[Quantity],[Amount]
)
OPENQUERY(
[Adventure Works DW2012],
'SELECT [ReportingDate],[ModelRegion],[Quantity],[Amount] FROM vTimeSeries ORDER BY [ReportingDate]'
)

Sunnie S Chung IST 734

Sunnie S Chung IST 734
Sunnie S Chung IST 734
 9. Conclusion:
In this project we learn the application of various database and data mining concepts and its application
We designed a star schema and then built a Data Warehouse OLAP cube, for Sales Analysis using SQL
Server Analysis Services (SSAS) and queries the cube using MultiDimensional eXpressions
language(MDX) and found various answers for some business questions . Next we created data mining
structure using Data Mining Extensions(DMX) and found the hidden pattern and predicted things that
were helpful in improving the business and its growth. We also learned various techniques that were
available to create data mining structure. That was demonstrated through both the usage of DMX
Queries and a Wizard to create Data mining structure in SSAS tool.

10. References

1. Data-Mining-With-Sql-Server-2008
2. SQL Server 2012 Tutorials - Analysis Services Data Mining
3. Data Mining: Concepts and Techniques by Jiawei Han (Author), Micheline Kamber (Author)
4. Internet resources:
• http://www.codeproject.com/Articles/658912/Create-First-OLAP-Cube-in-SQL-Server-
Analysis-Serv

• http://www.codeproject.com/Articles/710387/Learn-to-Write-Custom-MDX-Query-First-Time

• http://msdn.microsoft.com/en-IN/library/ms175595.aspx

• http://marktab.net/datamining/2010/08/21/mining-olap-cubes

• http://www.erpsoftwareblog.com/2014/04/using-ssas-sql-server-analysis-services-data-
mining-to-automate-marketing-analysis-part-1/

• http://msdn.microsoft.com/en-us/library/cc280440.aspx

5. Software Used:
• Microsoft SQL Server,
• Microsoft Visual Studio 2012 or any higher
• Microsoft SQL Server 2012 Business Intelligence

Other Useful System Guides:

Sunnie S Chung IST 734

Sunnie S Chung IST 734
Sunnie S Chung IST 734
Sunnie S Chung IST 734