I notice that most of the writings (aricles, tips and what not) did not indicate which version of sql server it supports. A guess is 2005, however, there seem to be a few good writings regarding ms dm before 2005 release as well. Thanks....more >>

Hi Jamie and All, I have been using SQL Server 2005 data mining for quite a while. They work fine until recently when I use a big database. For example for the market basket analysis, we have 3.6 million of cases and it failed to process the mining model. It ran for 2 days and the serve...more >>

For query_syntax, could I use a stored procedure instead of select statement inside openrowset call? Here is the syntax for openrowset per BOL. OPENROWSET(provider_name,provider_string,query_syntax) TIA.......more >>

I've posted when I using CTP September to build the sequence cluster and the cluster profile Markov's chain will become all black. So I uninstalled it and setup CTP June and the view is ok.Today I use SQL 2005 RTM to build the sequence cluster(use AdventureWoksDw), and the Markov's chains is stil...more >>

Hi! I am writing couple of utility procs for AS. I want to be able to add a data source and a data source view to an existing database without crating a project, by simply using a stored procedure in AS. After that I can create Data Mining models using DMX, therefore I can do everything wit...more >>

Hi, When I try to view the lift report on the Microsoft Naive bayes algorithm mining model, I get the following time-out error: invocation.Microsoft::Analysis Services::Adminserver::AdomdException. Would you please let me know how to work around this? Thanks! Vel...more >>

per subject. ...more >>

Why are all files downloaded from your site are said to be error or corrupted. And as sush could not see, participate nor gain advantage of your site....more >>

Hi everyone: I'm trying the example in "Data Mining Tutorial". Why do I always get the error "login failure:unkown user or incorrect password" while I begin to deploy the project or proccess the model? I have tried the following ways: 1,I have added a new user whose role is dbo into the da...more >>

I'm a beginner in the data mining:There's a table including mobile(varchar(11)) and typeid(long discrete).The contents like the following: mobile typeid 13512345678 1 13512345678 2 13512345678 3 I want to find the association what types may be ordered together by one user. How shoul...more >>

I am trying to follow the example in sql server data mining book by Jamie and Tang. On page 95, step 3 for creating name calculation on customers table, I enter the following expression: CASE WHEN [NUM BEDROOMS] = 1 THEN 'ONE' WHEN [NUM BEDROOMS] <= 1 THEN 'TWO OR THREE' WHEN [NU...more >>

Are there any Webparts for datamining deployment to be used in SharePoint...more >>

Hi,everyone: There are 7 standard schema rowsets in the OLE DB for DM specification.Where can I find these predefined schema rowsets in SQL Server?Thanks! ...more >>

Hello! I was searching if anything about cross validation technique is written in SQL server 2005 documentation. I didn't find any. Cross validation is very useful for building quality data mining models because the testing dataset and teaching dataset are not static. So what will be the best wa...more >>

I'm trying to run DMX queries against an Association model for market analysis. As usual, the basket items are in a nested table. Unfortunately, most of the really interesting DMX functions only take scalar columns. Here is the puzzle: If if use select flattened predicthistogram([Category]) from ...more >>

working thru the sql server 2005 datamining book - in chapter 3 trying to build the mining model for movie click i get the following: Error 1 Error (Data mining): The data type of a foreign key binding (ordinal=1) for the 'Actors' nested table does not match the data type of the corresponding...more >>

This is q derived from an article on using Excel for anormaly detction by Jamie MacLennan, so, it's more for him. Now, when we talk about anormaly, the first thought is, what is considered 'norm' or 'normal'. And let's continue to use the college plan case/scenario. Quick review, in this ...more >>

Hello! I have a problem with integration of my plug-in algorithem into analysis services. First i compiled my ATL project (DLL type). After i build the project I registered my algorithm in msmdsrv.ini file. After that I made a new analysis services project and when i made a new minig structure there...more >>

I can not highlight the both commands and execute. Instead, I have to highlight one at a time and then execute. In a regular sql script, I could separate the commands in terms of batch by "GO" statement and execute the script file. Is it possible to do so with dmx query script file? TI...more >>

Q: Structure xyz has multiple models of tree, clustering and NB. Say, prediction columns is “Bike Buyer”, of data type continous. Since tree and clustering algos support continous it's OK with them. However, NB requires discrete or disretized hence there's a need to create/add a similar...more >>

How to add additional table (naturally related to already selected source table) to an existing structure? Maybe the question can also be phrased as how to add new source table to an existing structure. Thanks....more >>

Q, under what condition(s)/circumstance(s), does MS clustering use EM method and when does it use K-Means instead? Default to EM? Value for K-Means is 2? Thanks. On a related note, the following URL is dead http://go.microsoft.com/fwlink/?LinkId=45964...more >>

This algo param has been checked to remove via the REMOVE button. However, the button action (of the REMOVAL) does not seem to have any impact (even another action of SAVE is followed). When going back to see the paras, this para (Force Regressor) is still there. Another strange thing abo...more >>

When I try to train the following model create mining structure customer ( custid long key, gender text discrete, income long continuous, buyer long discrete ) alter mining structure customer add mining model buyer_dt ( custid , gender, income, buyer predict_only ) us...more >>

Hi, what does the term Realtime Data Mining actually mean? Does it mean that a DM model can be applied to a set of data in realtime? In fact that is the status quo. Or does it rather mean that DM models (e.g. a neural network) are constantly updated by data from operational data sources? Does any...more >>

I have an asp.net application. This application provide consolidated information to the user using Analysis Services 2005. Within it, one aspx page uses MDX query to retrieve the information from the cube. However, we are unable to access AS 2005 because of authentication issues. What would ...more >>

Hello, I want to deploy a linear regression algorithm based on data: ID CaseNum Input1 Input2 Predict 1 1 2 5 7 ... ... ... ... ... 1 200 6 9 12 2 1 5 5 0 ... ... ... ... ... 2 50 44 5...more >>

Is there a way to create a dimension from existing DM structure? Thanks...more >>

How can I filter the following query such that Expression.$AdjustedProbability > 0.60??? Thanks select flattened topcount(predict (zcon,include_statistics) ,$adjustedprobability,5) from cmar natural prediction join (select (select 'angelina' as prof) as zcon) as t...more >>

I tried to script out the data model using sql server management studio but it came out in xmla format w/lots of xml tags. Is it possible to script it out in pure text like a regular table definition?? Please help....more >>

What are the general answers that Data Mining can give for many types of businesses ? ...more >>

Hi, I would like to know the best design for this scenario. I need to store large, varying length text data(upto 16K) in a table. Should i use varchar(8000) or text datatype? (with varchar(8000), splitting the data if size > 8k) Initial row size - 3 million Transaction vol - 15000 updates/...more >>

Hello, How to create an effective DM against dataset with distributed values? I'm doing a demo project in SQL05 to demonstrate reporting against DM & OLAP using The Insurance Company Benchmark dataset(http://kdd.ics.uci.edu/databases/tic/tic.data.html) as a source. Most of the fields in this dat...more >>

Hi everyone: I'm writing a thesis about the plug-in DM algorithm in SQL Server 2005.But the first section is the reason why we should use SQL Server 2005 instead of DB2 or Oracle. Would anyone be so kind to give some hints?Any help will be appreciated,thanks! ...more >>

Hi, I've just got hold of the "Data Mining with SQL Server 2005" book and have been reading chapter 16. However, when I went to the book website to try to download the Excel Addin that the chapter talks about, it wasn't in the zip file of resources for that chapter. Anyone know where I can ...more >>

Hi, I have just downloaded and installed the SQL Server Express Edition 2005. But I dont know, which tool I have to download for Reporting Services (RSS). i.e. Like in the SQL 2000, we use the Reporting Services. Please guide me. Thanks! Rana Khan...more >>

1) Lift Chart seems to fail to support multiple models. I have one structure that entail three models, of which, the two models of tree and clustering work individually. In other words, when only one model is selected Lift Chart functions as it is supposed to while the Lift Chart would gener...more >>

I purchased the "Data Mining with SQL Server 2005" book and I am attempting to follow along with the Movie Click database example. I have downloaded the MovieClick database and converted it to SQL Server 2005 RTM. I have successfully built the Movie Trees and Movie Bayes models, but I cannot train...more >>

Hi There, Right now I am developing a proposal for the purchase of a data mining solution for my organization. We are running SQL2000 and I would like to recommend SQL2005 as the solution. However, my concern is that new algorithms do not perform on our data as good as using other data mining pro...more >>

im trying to order a varchar fild in sql 2000, but i need it in numeric order... and can't convert it to numeric. any way of doing this? ...more >>

1. How to EDIT/CHANGE NUM of Clusters (seems defaults to 10) 2. LIFT CHART for 2+ models instead of current model, how? 3. using Clustering model, input includes firstName and lastName, characteristics indicates that both values are missing -- good and yet, probability histogram/bar h...more >>

Quick question, a model has several attributes from a same table, say, income, houseOwnership, marital_status etc. are all from DimCustomer table, then SaleTotal is from FactSales table. Then in the Column Mapping section when it comes to model fitting processing, the Select (Case) Table, w...more >>

In all earnestness, I have a few quick comments/questions about dm with sql server 2005. But let me say this first, overall, they seem very impressive. 1) C: Model View Nice, but the Legend at bottom, imho, "Node it predicts" should read "Node being predicted", "Node that predicts it" s...more >>

Do you have any cases using DM on retailers customer and prospect database? Do you have any additional info regarding DM for retailers?...more >>

So far, I have been using wizards for creating different models based on decision tree or naieve bayes etc. But I would like to hand code the model as shown in data mining book for ss2k5. I tried navigating the menus and could not view the actual text code of my generated models? Please le...more >>

I am trying to learn association algorithm by practicing the following problem. There are 2 tables customer and customer contact. customer contact contains who is trying to contact who. For example in the following, brad pit contact angelina jolie. I would like to design the model and ...more >>

Hi, I'm wondering if there's any doc that describes the process flow of Build (build | deploy), Database (Process), Mining Model (Process) for the BI Development Studio. I built a decisioin tree model and attempted to process it but failed. Here's a screen that bugged me, password prompt ...more >>

When it is needed to use case and nested table in the decision tree algorithm?. Is only useful when you need to relate tables but is not the same concept that in Association rules, where case is the entity that we want to analyze. (i.e. the Basket in the market basket analysis) Thanks in adv...more >>

hi all, i m working on a data set called mushrooms with lots of attributes like capshape,cap surface, cap-color, bruises, odor, gill-attachment, gill-spacing, gill-size,gill-color, stalk-shape: stalk-root, stalk-surface-above-ring, stalk-surface-below-ring, stalk-color-above-ring, stalk-co...more >>

I am implementing Web site functionality whereby a user who enters a string (which will usually not contain spaces/words) will be presented with the nearest pre-existing string that matches their entry. Ideally, from what I've seen of SQL Server 2005's functionality, I would like to apply Fuz...more >>