About Data mining

Hello Experts good morning to all.I have one doubt.ie What is Data Mining.uses & Functions of data Mining.

Hi Anand,
You can use data mining to automatically determine significant patterns and hidden associations from large amounts of data. Data mining provides you with insights and correlations that had formerly gone unrecognized or been ignored because it had not been considered possible to analyze them.
Since each company has different data mining requirements, it is not possible to deliver fixed models for producing prediction results. However, the data mining methods available in SAP BW allow you to create models according to your requirements and then use these models to draw information from your SAP BW data to assist your decision-making. For example, you can analyze patterns in customer behavior and predict trends by identifying and exploiting behavioral patterns. Data mining models can be used to provide answers to decision-making questions like the following:
Which offer is most appropriate to which customers and when should that offer be made?
Which customers are liable to churn?
How high is the cross-selling potential for a new product?
Thanks & Regards
Ramakrishna Kamurthy

Similar Messages

BW Data Mining

Hello!
I need information about the following BW Data Mining topics. Hope, someone can help me?
-What 3rd Party Tools are available für Data Mining? (I just know "IBM Intelligent Miner")
-Does someone have experiences with performance of the DM-algorithms? System requirements? Mass data?
-Are there possibilities to improve the performance?
-What is known about new features in Netweaver BI 7.0 for DM?
-Does someone have special experiences in DM in the automotive industy? Are there typical business processes known, which are useful for BW Data Mining?
Thank you for help!
Regards,
Peter

Hallo!
I need different information about BW data mining.
One thing is, what are typical business scenarios for the different algorithms. So it is easy to find such for decision trees, association analysis and maybe for ABC analysis. But i have little problems to find real scenarios vor weighted score tables and regression analysis. It would be helpful to hear about some.
I have to write a paper for my company about data mining with bw. While we have no experiences in this area I´m looking here for people having.
Also Performance. The problem is not to try out with APD and Data Mining models. But to find experiences with this.
Good or bad performance with this or this algo? Or how can I optimize performance for mass data?
After this I have to design typical business scenarios. Especially for automotive area if possible.
So what the question for me is, what is possible with the algorithms? Where are problems with them?
It would be great if you could provide me with more information about your experiences in this area.
Thanks,
Peter

SQL Server Tutorials for beginners: OLAP / Data Mining

I teach a DBMS + BI course to non-CS (business) students, using SQL Server. To illustrate OLAP I use the nice interactive online demo at "olaponline.radar-soft.com".
Is there a simple tutorial for SQL Server that is similar? Prepackaged, Illustrating OLAP, BI, or Data Mining algorithms? Everything I've seen so far is too complicated and requires many preparation steps before interacting with the model/cube.
Alternatively can you recommend other online tools / demos? Thanks,
-- Shaul

Hello,
The best way to learn about data mining is the list of 22 lessons created y Daniel Calbimonte:
http://www.sqlservercentral.com/Authors/Articles/Daniel_Calbimonte/1486684/
About Business Intelligence, please take the following free training:
http://www.microsoftvirtualacademy.com/training-topics/business_intelligence_topic_page_en
Hope this helps.
Regards,
Alberto Morillo
SQLCoffee.com

Re; Data Mining

Hi All,
I wish to know about Data Mining concept wrt BW 3.5 system. i.e what it is , for what we use. etc...
regards,
Noor

Hi,
Please read the following links of data mining ;
http://help.sap.com/saphelp_nw04/helpdata/en/4a/eb293b31de281de10000000a114084/frameset.htm
http://help.sap.com/saphelp_nw04/helpdata/en/0f/4e0d40312b1e07e10000000a1550b0/frameset.htm
http://help.sap.com/saphelp_nw04/helpdata/en/e8/1509407448c442e10000000a1550b0/frameset.htm
Assign points if helpful,
Regards,
Ravi.

Data Mining on data specified and filtered by the user in runtime

Hi Experts,
i am new to Data Mining in SAP BI (we are on BI 7.0 SP Level 20). I familiarised myself with APD and Data Mining by reading some interesting and useful threads in this forum and some other resources. Therefore I got a understanding about the topic and was able to create basic data mining model for an association analysis and an corresponding APD for it and write the results into a DSO by using the data source. But for now I was not able to find a solution for a concrete customer requirement.
The user shall be able to select an article, a retail location and a month and get the top n combinations sold with that article in the particular location and month. For that he may not access the data mining workbench or any other SAP internal tools but he shall be able to start the analysis out of the portal (preferable a query).
We had some thoughts on the scenario. The first idea would be to create an APD for every location for the last month. As we need to cover more than 100 locations, this would not be practicable. Therefore I think it would be necessary, that the user can select the particular filters, and the data mining would then be executed with the given input.
The other idea was to use a query as source. The user would start this query and filter location and month in it. The result of the query could then be used as the source for the APD with the association analysis. Therefore we would need to create a jump point from that query, which starts the APD with that results. After that the user should be able to start a result query, which displays the result of the association analysis (ideally this result query would start automatically, but starting it manually would be ok, too).
So, I have the following questions for these scenarios:
1.) Is it possible to create variants of a single APD, for automatically doing the data mining for the different locations?
2.) is it possible to start an APD out of a query, with the particular results regarding filtering?
3.) Can we place a query directly on the data mining results (how?) or do we need to write the data mining results in a DSO first?
4.) What about the performance? Would it be practicable to do the data mining in runtime with the user waiting?
5.) Is the idea realistic at all? Do you have any other idea how to accomplish the requirement (e.g. without APD but with a query, specific filter and conditions)?
Edited by: Markus Maier on Jul 27, 2009 1:57 PM

Hi ,
you can see the example : go to se 80 then select BSP Application ,SBSPEXT_HTMLB   then select tableview.bsp , you will get some idea to be more clear for the code which you have written
DATA: tv TYPE REF TO CL_HTMLB_TABLEVIEW.
tv ?= cl_htmlb_manager=>get_data(
                         request = runtime->server->request
                          name    = 'tableView'
                              id      = ''tbl_o_table" ).
IF tv IS NOT INITIAL.
DATA: tv_data TYPE REF TO CL_HTMLB_EVENT_TABLEVIEW.
tv_data = tv->data.
IF tv_data->prevSelectedRowIndex IS NOT INITIAL.
FIELD-SYMBOLS: <row> LIKE LINE OF sflight.
    READ TABLE ur tablename INDEX tv_data->prevSelectedRowIndex ASSIGNING <row>.
    DATA value TYPE STRING.
    value = tv_data->GET_CELL_ID( row_index    =
                               tv_data->prevSelectedRowIndex
                                  column_index = '1' ).
endif.
endif,

Help with data mining add ins-excel 2010

I've wasted hours of my life now trying to figure out how to establish a connection on the data mining add in on excel 2010. I have installed and re-installed the microsoft sql server 2012 express multiple times and don't understand what it takes
to get this to work...Do I need SQL server and why? Do I need to download the adventureworks data file and why? (For some reason I was able to download it properly on my first sql server install, but when I went to work the data mining connection it
said the SQL browser must be connected...What???...I thought it was connected...there are no instructions on how that is fixed...Now I have reinstalled sql 2012 but can't download adventureworks...it says it can't
establish a connection...I am beyond the point of frustration)...I'm not a developer or know anything about code/programming, so a lot of the lingo is way over my head anyway when I am searching for troubleshooting solutions...I just want to be able to use
this feature in excel and it is upsetting me that I can't get it to work. I have followed step by step instructions, watched youtube videos, etc...nothing doing...If anyone can help me it would be greatly appreciated. Thanks.

>I'm not a developer or know anything about code/programming,
You have two choices:
1. Hire a programmer type to assist you
2. Become a programmer
BOL: Data Mining Add-ins
Instead of Express, consider purchasing SQL Server 2012 Developer Edition:
http://www.amazon.com/SQL-Server-Developer-Edition-2012/dp/B007RFXQAM/ref=sr_1_1?s=software&ie=UTF8&qid=1397437432&sr=1-1&keywords=sql+server+2012+developer+edition
Install it.
Download AdventureWorks2012 and AdventureWorksDW2012 sample databases and install them.
Desirable (but not for beginner): install Adventure Works Cube. This is how it looks after installation:
Kalman Toth Database & OLAP Architect
Free T-SQL Scripts
New Book / Kindle: Exam 70-461 Bootcamp: Querying Microsoft SQL Server 2012

Creating Data Mining PL/SQL Package in SQL Developer

hi,
i have built a model and want to create a PL/SQL package.
in SQL developer, i launch a "New Gallery", select "All Items" from the drop-down menu, and click on "Database Objects". but in the right window pane, i am not able to see "Data Mining PL/SQL Package" in the options.
can somebody please tell me how to fix this?
thanks!

To verify that Oracle Data Mining PL/SQL Package extension is properly installed, please do the following:
Select Menu Help->About, click on "Extensions" tab. Look for "Oracle Data Mining PL/SQL Package" in the Name column ( you can sort it).
If it is, please make a note of the version installed and post it here as well as the SQL Developer version.
Just to clarify, you don't see "Data Mining PL/SQL Package" item in the "Database Objects" at all or is it grayed out?
Thanks

Association rule in SQL Server Data Mining

I have been working on a problem on association rules in SQL Server Data Tools (Visual Studio 2008) for quite a while but have not yet been able to figure out the solution.
The problem is: I have a table named Sales_history in my SQL database. This table has following columns: CustomerID, ItemID, Month (from May2012 to April 2013), QtyShipped. I am looking to find association between Items and i want to provide recommendation
to the Customer (In this case CustomerID) based on their purchases.
Note: there are around 630 customers and about 34000 products in my table.
My approach:
I marked History_Table as both Key and nested. And in the Key, i checked CustomerID as input and Key whereas in nested, i checked ItemId as Key, input and Predict.
When i run the model, i get a solution but i am not sure if i am configuring it right. Also i am not sure how i can write prediction join query to generate Item recommendations . I am really struggling with
this problem, eagerly waiting for the reply. Thank you.

Hi Tatyana,
Thank you so much for your reply. I have now been able to create the data mining model using association rule and by writing a DMX query, i am able to generate the item recommendations to be given to customers for items they have purchased. However, i have
noticed one thing that in the DMX query, it gives the same item recommendation for any item i put inside the query.
Also, if i put any item in the DMX query from the generated list of recommended items, the output of that query also shows the item that is inputted inside the query.
Here is the query, that i am writing to generate item recommendations
SELECT predictassociation (CrossSellingModelV3.[Ztb Customer Item v3],INCLUDE_STATISTICS,5)
FROM CrossSellingModelV3
NATURAL PREDICTION JOIN
(SELECT
(SELECT '17IS56126' as m )
AS Ms)
AS t
What can be the possible reason behind this? Is this something related to the kind of data i have? In my data, there are 632 distinct customers and 34000 distinct products.
If i execute this query in management studio.
select customer_CD, COUNT(Item_CD) from ztb_Sales_History
group by customer_CD
order by 2 desc
the output shows that there are some customers who have bought just 1 item and also there are customers who have bought 2400 items. i mean the range is very high.

Something new in Data Mining in BI 7.0

Hello experts!
Does someone know if there is something new in Data Mining in BI 7.0? As far as I understand there is no more WebItem for prediction (Clustering and Decision Tree) and this is now integrated in SAP Analytics/Visual Composer.
Are there any new methods or functions. I can see nothing...
Best regards,
Peter

Hello all!
It is very sorrowful that no one seems to be interested in SAP BI Data Mining. There is even a new book from SAP Press about this topic.
So after all I can say that I had found nothing new so far. There are some new things in APD which are very interesting, but nothing new in Data Mining.
Peter

How to use Data Mining for a blind DBA?

Hi, I'm a blind DBA and I need some input and some suggestions from the forum on how to access the Data Mining feature.
This feature is becoming more and more an essential part of my daily tasks, so I need a way to use it.
Database: Oracle 11.1.0.7.0
OS: Windows XP Pro and Linux
Adaptive Technology:
JAWS Version 11.0.1467 by Freedom Scientific BLV Group, LLC
JAVA Access Bridge by SUN Microsystems
I know there is a Windows program called Data Miner, unfortunately my JAWS speech synthesizer does not work with the interface and I need an alternative. I
read Oracle's documentation on the Data Miner API., but it is short on examples, details , and step by step instructions. Does anyone have a more
comprehensive set of examples on how to use the Data Mining API. from start to finish, specifically for market basket analysis? Any help would be
appreciated.
Thanks.

Hi,
I am not very knowledgeable about Oracle Data Miner, the graphical user interface to Oracle Data Mining, but I can respond to your question about API documentation.
You may find the source files for the Data Mining sample programs to be very helpful. They provide many examples. After installing Oracle Database, install Oracle Database Examples. This separate installation process installs the sample programs in the DEMO directory under Oracle Home. Instructions for installing and configuring the sample programs are provided in Oracle Data Mining Administrator's Guide. Here is the link to the relevant chapter in the 11.1 Administrator's Guide.
http://download.oracle.com/docs/cd/B28359_01/datamine.111/b28130/sampleprogs.htm#BABEHFEB
As for the API documentation, the best place to start is probably the Data Mining Application Developer's Guide. Here is the link to the 11.1 Application Developer's Guide.
http://download.oracle.com/docs/cd/B28359_01/datamine.111/b28131/toc.htm
The Data Mining PL/SQL API for creating data mining models is implemented in the DBMS_DATA_MINING package. The syntax of Oracle PL/SQL packages is documented in PL/SQL Packages and Types Reference. Here is the link to the chapter in the 11.1 version of that manual.
http://download.oracle.com/docs/cd/B28359_01/appdev.111/b28419/d_datmin.htm#i1062150
The Data Mining functions for scoring (applying mining models to new data) are implemented as SQL functions. The syntax of Oracle SQL is documented in SQL Language Reference. Here is the link to the Data Mining SQL functions in the 11.1 version of that manual.
http://download.oracle.com/docs/cd/B28359_01/server.111/b28286/functions001.htm#sthref953
Hope this helps,
Kathy
Edited by: ktaylor on Nov 10, 2010 8:14 AM

Time Series Data Mining

All,
I'd like to know how to model a time series table to submit it to Oracle Data Mining. I've already tried a reverse pivot, but is there something different?
Regards,
Paulo de Tarso Costa de Sousa

If you are trying to do something like create a demand forecasting model like ARIMA, ODM does not have explicit support for this type of modeling. Data mining is usually more about creating a "prediction" rather than a forecast. You may want to look at Oracle's OLAP capabilities for this.
If you are trying to include variables that contain the element of "time", such as "blood pressure before" and "blood pressure after", you can include these a variables (attributes) in the model. ODM has no real limit on the number of variables it can include in the model, so you don't have to worry about creating too many of them (usually).
You may want to "clump" the data so as to create a set of variables at certain check points in time like the "before" and "after" approach above. Rather than entering for example the measurement off an instrument ever 10 seconds (which would ordinarily create new variables for each time period), you may want to only detect "events". That is, only record the amount of time between events--sort of Mean Time Between Failure (MTBF) type of modeling.
Hope this helps with your thinking about how to approach your problem

Data Mining Framework SDK

Hi,
Is there a link where I can download the Essbase Datamining framework SDK?
I would also like to read more about the licensing of the Essbase Data Mining features. Tried searching a lot but havent been able to find a singe link which can give any info on the Data Mining Framework SDK.
Thanks,
Neetesh

Add-in for Excel?
Ed Price, Power BI & SQL Server Customer Program Manager (Blog,
Small Basic,
Wiki Ninjas,
Wiki)
Answer an interesting question?
Create a wiki article about it!

Help to do data mining and transformation...

I have a specific task to accomplish and I am wondering if Oracle Data Mining is the correct tool to use, and if not what possibly might be. Here is brief description:
I have a table with about 500 millions rows of data per day, transactional internet traffic data. It contains about 20 columns/dimensions. The requirement is to transform this flat data into a new table that contains (as one column each) each unique variation of those dimension values recorded.
So for example, if we have 3 dimensions of say gender, age and zip code we would determine each unique combination of those found in the actual data and write out x number of columns to identify them and store a count value for each one. The count will just tell us how many of that combination was found in the data, and the end result will be of course an aggregated table for fast querying on all observed dimensions.
For performance reasons we want to pass through the data only only.
We tried cubes but this takes too long (because it also tries to build out all the non-observed combinations), and we know we could try a code approach but fear this may take too long also. The problem is more of a performance one of course, with that many rows and possible combinations to consider.
Any ideas?
Thanks in advance.

After doing some research I realize what I need is a cube, but one that does not contain every single dimension combination but only those that actually exist (to speed up the creation time and reduce storage space). Is this something Oracle supports? Anyone?

How to learn data mining?

Hi
I am an Oracle developer with DBA experience
How can I learn data mining and launch a career as a data miner?

Hi,
You can certainly start by using ODMr and walking through the tutorial.
To be expert in the field, I would suggest going to any of the book sites and searching for books on datmining. You will find alot of material useful in learning about the art of datamining.
Typically it is not just knowledge of datamining techniques that is important, but understanding the domain. If you have experience with domains such as retail or financial, then you should consider studying datamining implementations that target those domains. The more direct benefit you can bring your users the better.
Good luck, Mark

Oracle Data Mining VS Weka

Everyone,
Does anyone have already used Weka with Oracle Database? I must do a
comparison between ODM and Weka.
What are the advantages and the drawbacks of ODM and Weka ?
Thank you for your answer.
PY

I agree with Mark Kelly, ODMr has inherent advantages of in-database mining in Oracle Database.
I haven't used Weka much, I tried once. It basically gets the data from the database using JDBC driver and does the mining in the desktop environment.
Another advantage of Oracle Data Miner (ODMr) is it is designed to give good prediction results very quickly even for data mining beginners who doesn't know much about the required transformations, algorithm settings etc. Especially with the Guided Analytic using "Activity" template based approach that derives intelligent defaults for the transformations, algorithm settings etc. ODMr does provide required flexibility for the advanced users who wants to control the transformations, algorithm settings etc.
-Sunil

About Data mining

Similar Messages

Maybe you are looking for