Predicting from a clustering model

Hi,

I have built a Clustering model that captures customer demographic information

and identify various hidden clusters based on the information.

What kind of predictions can I make using the above model?

You can do multiple types of queries with a clustering model:

Get the most likely cluster for each case (or a new singleton case) - SELECT Cluster() FROM [model]|||

Thanks Raman,

The 1st, 2nd and the 4th points are clear but I have certain doubts

regarding the 3^rd point you mentioned

Firstly as the attributes are customer characteristics like

age, gender and other demographic information and we suppose that the values

for these always exist for all the cases (new/old). What will be the point of

making them predictable and predicting their values again.

Secondly if I want to predict an attribute(s) like

MovieBuyer (determines whether a customer has bought a movie(s) or no) for new

cases, wouldn’t it be better if I use ‘decision trees’ or ‘neural networks’

algorithm rather than clustering.

Basically I cannot imagine a scenario in which clustering

stands out as the best suited algorithm for prediction.

It seems that Clustering is best suited for exploring and

understanding the data rather than for prediction.

I hope I have expressed my problem adequately and clearly.

Any help would be most appreciated.

|||

Your assessment is correct in that clustering is more suitable for data exploration/understanding - I was just pointing out that it is *possible* to do prediction with the SQL Server DM Clustering algorithm (which was your original question).

|||Thanks ramansql

Predicting from a clustering model

Hi,

I have built a Clustering model that captures customer demographic information

and identify various hidden clusters based on the information.

What kind of predictions can I make using the above model?

You can do multiple types of queries with a clustering model:

Get the most likely cluster for each case (or a new singleton case) - SELECT Cluster() FROM [model]|||

Thanks Raman,

The 1st, 2nd and the 4th points are clear but I have certain doubts

regarding the 3^rd point you mentioned

Firstly as the attributes are customer characteristics like

age, gender and other demographic information and we suppose that the values

for these always exist for all the cases (new/old). What will be the point of

making them predictable and predicting their values again.

Secondly if I want to predict an attribute(s) like

MovieBuyer (determines whether a customer has bought a movie(s) or no) for new

cases, wouldn’t it be better if I use ‘decision trees’ or ‘neural networks’

algorithm rather than clustering.

Basically I cannot imagine a scenario in which clustering

stands out as the best suited algorithm for prediction.

It seems that Clustering is best suited for exploring and

understanding the data rather than for prediction.

I hope I have expressed my problem adequately and clearly.

Any help would be most appreciated.

|||

Your assessment is correct in that clustering is more suitable for data exploration/understanding - I was just pointing out that it is *possible* to do prediction with the SQL Server DM Clustering algorithm (which was your original question).

|||Thanks raman

Posting Multi-Value Parameter

Hi,

I tried Posting the values for a multi value parameter from my application to the reporting services, But the query string is not being hidden. Why is that ? since the the data is sent through the browser address bar, I am not able to send values more than the allowed lenght. Is there any work around ?

Thanks In Advance

Regards

Raja Annamalai S

Hi Raja-

Yes, you will be limited to the URL length restriction. If possible I might suggest using the Web Service to render reports rather than crafting the URL. This will not be limited by URL length.

Otherwise you can perform a POST instead of a GET on the http call. The post will send the parameter values in the body rather than appended to the URL. However, all parameters need to be in the body if you perform a POST.

Thanks, Jon

Possible to know if I'm on the first page or not?

I want to do a visibility check. If I'm looking at the first page of a
multipage report, I want an item to be hidden. If I'm looking on all pages
except page 1, I want the item to be visible. Is this possible? How? I've
tried creating a page footer, and added a textbox which shows the page
number with Globals!PageNumber. Unfortunately, I can't figure out to
reference this textbox. I've tried =IIF(MyTextBox.value > 1, True, False),
but then I get an error message saying that "MyTextBox" is not declared.
Please give me some advice.
Kaisa M. Lindahlwell dear in the hidden property of the textbox(field) which u want to
hide on first page n visible on all other pages write the following
expression
=iif(globals!pagenumber=1,trrue,false)
REMEMBER write this expression in the HIDDEN property of the textbox
which u want to hide
hope this ll resolve the problem
take care|||You can't use Globals!PageNumber in the body section of a report.
It can only be used in header and footer.Which is why I created my textbox
in the footer, and found out I can't reference the value of it.
Anyway, it's the whole report header I want to hide on this first page. But
the "Hidden"-expression is just the same for all items.
Kaisa M. Lindahl
"** Spirits **" <muhammadhammad78@.gmail.com> wrote in message
news:1112248349.597510.309570@.g14g2000cwa.googlegroups.com...
> well dear in the hidden property of the textbox(field) which u want to
> hide on first page n visible on all other pages write the following
> expression
> =iif(globals!pagenumber=1,trrue,false)
> REMEMBER write this expression in the HIDDEN property of the textbox
> which u want to hide
> hope this ll resolve the problem
> take care
>