anna_holland Tracker

Re: Intivation to SGF e-poster presentation of Text Mining Reveals the Secret of Success: Identification of Sales Determinants Hidden in Customers' Opinions

anna_holland — Tue, 01 Apr 2014 15:31:48 GMT

Hi Rafał, This looks like a great resource. Thanks for sharing! Best, Anna-Marie

Re: Problem with scd2 loader in DIS 4.3

anna_holland — Tue, 25 Mar 2014 14:08:59 GMT

Hi bkv1958, Typically, you are only allowed to mark one answer as correct. Since there are a number of "helpful" answers, it may not let you mark one as correct. Please tell which answer was most helpful, and I will mark it as "correct" on your behalf. Thanks! Anna-Marie

SAS Global Forum 2014 content!

anna_holland — Mon, 24 Mar 2014 19:41:03 GMT

Can't attend SAS Global Forum to take advantage of all the great content? Be sure to tune in to watch select live and on-demand sessions from the event. See technology demos, presentations and interviews featuring conference leaders, presenters and the SAS staff posted on this SGF Support Portal. In addition, you can find all the keynote speakers and sessions by viewing the Visual Analytics SGF agenda. What SGF content would you like to see featured on the Visual Analytics community? Would you like to see the content featured as a discussion, article, or community topic?

Enjoy!

Anna-Marie

Re: mysql access

anna_holland — Mon, 24 Mar 2014 14:47:23 GMT

Thanks for jumping in with such a quick resolution, Bruno! Nbirkett, sometimes the small adjustments make a big difference in performance. Anna-Marie

Methods to the March Madness: Visual Analytics

anna_holland — Mon, 17 Mar 2014 19:05:26 GMT

The NCAA Tournament and its "March Madness" are now upon us - but before the games begin there is this stress for many teams about whether they will make the final four. Using Big Data concepts and SAS Visual analytics, we were able to create a predictive model in SAS Visual Analytics. To complete this task, we opted to use a SAS VA Geo Map.

Have you used a Geo Map in VA yet? It’s easy to create one! We created the charts below by taking these few simple steps:

1. We made a SAS data set containing the names of all the teams in the final four since 1979.

2. We then added US state abbreviations for each team to the list to create the geo map.

3. We dragged over both final four team names and the state codes to the workspace in VA to create the attached graphs.

Also, we took other basketball data into account. Here are some other helpful (and some not-so-helpful) factors for selection. Here’s what’s been successful in the past:

• RPI (Rating Percentage Index), based upon wins, losses, and strength of schedule

• Jeff Sagarin rankings from USA Today

• Wins against top 25 teams (per RPI rankings)

• Wins against teams ranked 26-50

• Neutral court wins (Note: conference tournaments matter!)

• Record and rank in-conference (regular season championships matter!)

• Strength of conference (conferences do matter!)

Based on the historical data and the current basketball factors/trends, this is our final four prediction: Duke, Carolina, Kansas, and Kentucky. Now it’s your turn! Let's submit a community bracket to prove that SAS has the best modelers around! Please submit your entries to this thread during the tournament. Entries can be submitted prior to the start of the NCAA tournament or during the tournament. Having a hard time viewing the charts on your browser? Please see the attached .pdfs for an example. Thanks!

Most Common Final Four Teams

States Represented by the Final Four:

Re: Methods to the March Madness: Data Mining

anna_holland — Fri, 14 Mar 2014 15:54:33 GMT

Hi Reeza, That's exactly why we wanted to open up this discussion for ALL members! Traditionally, entries must be completed prior to the NCAA tournament. The community brackets/predictions can be submitted through the tournament. I believe Kathy originally used some historical data of each team and other factors listed above. This discussion is just for fun, and a great way to use your Data Mining skills.

-Anna-Marie

Re: Is there "SAS Code" behind VA?

anna_holland — Mon, 10 Mar 2014 16:03:58 GMT

DavidHenderson@SAS, I agree with Jaap Karman! That is an excellent summary of what SAS-VA does.

-Anna-Marie

Re: Using Period to Date Calculations

anna_holland — Thu, 06 Mar 2014 14:39:29 GMT

Hi DamianMcLoughlin, you bring up a great point about using the period calculations with a financial year field. Would you mind posting your question as a new thread? I think current and future community members would benefit from this example.

Thanks,

Anna-Marie

Re: Live SAS Data Mining Q&A March 5 12:30-1:30pm EST

anna_holland — Wed, 05 Mar 2014 17:54:38 GMT

Hi Irina, We have a chat via a "live thread" format. Please post your question to the forum, and our product experts are waiting to answer your questions. Thanks! -Anna-Marie

Re: Live SAS Data Mining Q&A March 5 12:30-1:30pm EST

anna_holland — Wed, 05 Mar 2014 17:14:23 GMT

We are very excited to host a live chat today! Community members, please either post your question(s) to this main thread or post a new thread and "mark" it as a question. We will have internal experts waiting to answer your questions. Thanks, Anna-Marie

Advanced Scenario: Processing a large data set

anna_holland — Wed, 26 Feb 2014 19:45:58 GMT

We thought we would give the community members another chance to answer a use case scenario thread. After we receive a few responses, we will post the answer that was provided by our internal product experts so that you can see how the various responses compared. This week we are sharing best practices on Data Management Studio to speed up processing of large data sets. We want to know what your approach would be?

Scenario: “What are the best practices for splitting up work that involves performing address verification on a large number of records? Specifically, what is the best way to split up the job processing and shorten the overall execution time of the job? Alternatively are there some DMSERVER settings I can change? What are the techniques / recommended best practice for doing this?"

As a community member, what would be your solution?

Re: Visual Analytics || newbie

anna_holland — Thu, 20 Feb 2014 16:12:28 GMT

Hi narenderrawal,

First of all, welcome to the VA community! We love having all of your questions. I will pass your questions along to some of our internal experts, but it looks like mojerry_realdolmen has given you some great feedback. Additionally, you may want to check out our current VA resources:

Thanks!

Anna-Marie

Re: Advanced Scenario: Commit Intervals

anna_holland — Tue, 18 Feb 2014 18:51:51 GMT

Hi Patrick, I am sorry for the delay. Our internal product experts took a different approach to answering this use case scenario question.

"Since every commit requires opening and closing the connection to the data, you are correct that you should do them no more often than necessary. But you also don’t want them building up too much – it can cause timing issues or memory usage problems. For large (multi-million record) table writes, a commit every 1000 records or so doesn’t have a significant impact on write time."

As a community member, would you take this approach? Or would you approach this scenario with a different solution? I look forward to seeing your responses!

Anna-Marie

Re: What's New in Enterprise Miner 13.1 - Live SAS Talks Session

anna_holland — Mon, 17 Feb 2014 18:27:25 GMT

Yes, please grab your lunch and join us!

Re: Enterprise Miner Timeline

anna_holland — Mon, 17 Feb 2014 15:01:32 GMT

GemmaR, I think that is a great idea! What type of challenge did you have in mind? You are welcome to share more detail here on this thread or please email me with more information on this idea: anna.holland@sas.com .

Thanks!

-Anna-Marie

Re: Using Period to Date Calculations

anna_holland — Wed, 05 Feb 2014 14:33:06 GMT

Andreas, we are happy to share the paper and hope you find it valuable! Michelle, you present some great ideas for more detailed examples. I will present the ideas to my team and will get back with you!

Regards,

Anna-Marie

Using Period to Date Calculations

anna_holland — Wed, 25 Nov 2015 14:11:07 GMT

Happy Tuesday Everyone,

In Visual Analytics 6.3, we released some very powerful and intuitive functionality around period to date calculations. I have attached a document written by our SAS VA product management team. This article covers the conceptual approaches of creating solid base understanding of the functionality. With powerful ways of solving business problems, there can be a learning curve. We tried to flatten that learning curve for you in the document. If you have some good use cases for this type of functionality, please chime in. We would love to hear some of the ideas people have around using functions like these to solve business problems. If you have used Visual Analytics 6.3, please let us know how you have used period to date calculations already as well.

Regards,

-Anna-Marie

Re: Inserting into SQL (Auto Identity Columns / Auto Date colums)

anna_holland — Thu, 30 Jan 2014 20:13:11 GMT

mrtball , I'm glad you found the solution to your problem! Thank you for marking the answer as "correct." This allows other community members to benefit from reading your solution.

Thanks,

-Anna-Marie

Advanced Scenario: Commit Intervals

anna_holland — Fri, 17 Jan 2014 18:46:36 GMT

Occasionally questions about Data Management products will come up through channels outside of the Data management Community. Rather than simply answer the question in a vacuum and not publicize it, we thought we would give you, the community members a chance to post your thoughts on the answer. After a week, we will post the answer that was provided by our internal product experts so that you can see how the various responses compared.

This week we present a question about commit intervals. As a community member, what would be your approach?

“Does anyone having guidelines around what the commit intervals should be when using the Data Output Insert or Update nodes? Generally I’m a believer in the fewer commits the better (i.e. more rows per commit) but I could listen to other arguments. I also understand that it might depend on the application – a real-time query (so 1 row per commit) vs. a batch job (lots of rows per commit).”

Re: What insights are you gaining with SAS Visual Analytics?

anna_holland — Fri, 17 Jan 2014 16:59:49 GMT

Pathak, thank you for sharing how your company is benefiting from VA. There is no project that is too small. Every project counts! What resolution did your organization come to?

-Anna-Marie