sascom voices - The sascom magazine blog

The recent article, Data-Driven Crime Fighting in Intelligent Enterprise reminded me of the feature we published in sascom earlier this year from Dr. Colleen McCue, a consultant who specializes in the provision of public safety and national security research, analysis and training. From the Intelligent Enterprise piece:

If there was a time when law enforcement agencies suffered from an information deficit, it's passed. Of the more than 18,000 law enforcement agencies across the United States, the vast majority has some form of technology for collecting crime-related data in digital form. The biggest city agencies have sophisticated data warehouses, and even the most provincial are database savvy.

From the sascom piece, Criminal Justice in the Post-9/11 Era:

While information sharing requires a cultural change and paradigm shift in the larger public safety community, advanced analytical techniques are available now. The same tools that were being used to prevent people from switching their cellular telephone service provider and to stock shelves at our local supermarkets before Sept. 11 can be used to create safer, healthier communities and enhance homeland security.

In September, I published a few posts from the Midwest SAS Users Group (MWSUG) conference, including coverage of presentations from SAS VP John Sall, SAS CIO Suzanne Gordon, SAS Consultant Kirk Paul Lafler and JMP Marketing Director Jon Weisz.

Now that the MWSUG organizers have published the conference papers online and announced the best paper winners, I want to highlight my favorite talk from the conference: Revolutionary BI by Charles Kincaid.

Charles, an Engagement Director at COMSYS, describes the ways he thinks analytics and business intelligence will be used and shared inside organizations in the future, and I think even George Jetson's employer Spacely Sprockets could benefit from his ideas.

If you've ever wondered how Web 2.0 will affect reporting and analytics in the future, Charles lays out the most comprehensive predictions I've seen yet. He looks beyond social sharing features like those you find on Facebook and Twitter, and describes intelligent reporting systems that will recognize common users of single data sources and allow report users to favorite or suggest changes to reports that are created by other users.

In addition to the MWSUG talk, Charles has presented his paper at other conferences, including SAS Global Forum 2009 in Washington, DC. In fact, he says his presentation at SAS Global Forum inspired one conference attendee to try some of Charles' ideas in his own banking organization, and that user is now presenting his results at SAS conferences too.

Read the full paper to understand Charles' vision for the future of business intelligence. Maybe you'll be inspired too.

Over at The Data Mining Research blog, Sandro posted a link to the presentations from a recent SAS Forum Switzerland. While browsing the presentation slides, I came across this great list of questions from a UBS presentation by Daniel Rüegge, Head of Business and Client Analytics.

Daniel calls these the top 10 paradigms in analytics to be questioned and asks, "Are they true? Are they of help? How do you apply them?"

What do you think? Which of the ten are true, and which are complete myths?

1. To make analytics successful, the CEO has to have a personal interest in it.
   
2. Analytical organizations have to be positioned in a central high-power position.
   
3. Every company in a competitive environment needs analytics to be successful.
   
4. Analytical expertise can/cannot be out-sourced/in-sourced/off-shored.
   
5. Getting data and technology in place is a long and cumbersome process.
   
6. Without data and technology you cannot do analytics.
   
7. Analytics is a thing mainly insiders and experts understand, and vice versa.
   
8. Communication of analytics is more important than analytical people think.
   
9. Analytics only should do things which have a measurable impact.
   
10. Analytics mainly is applicable in retail/standardized environments.

The customer intelligence event that I attended last month in Boston is making a stop in San Francisco tomorrow. The morning briefing includes a presentation from Forrester Analyst Surresh Vittal, followed by a panel discussion featuring Vittal, HP VP of Customer Intelligence Prasanna Dhore and Stanford University Graduate School of Business Professor James Lattin. Deb Orton, SAS Marketing Director, will be moderating the panel.

In Boston, discussion topics included:

• New rules for marketers.
• Analytics that start with the customer.
• Changing economy = changing priorities.
• Engaging the customer online and offline.
• Optimizing for success.

The opening talk from Vittal presents relevant statistics that reveal the changing roles of marketers. Vittal has practical advice for how to approach the change strategically and realistically.

At the Boston event, Vittal said marketing is undergoing a massive transformation, but most marketers are still playing by the old rules.

I love this idea of the analytics community being the "translation layer" within an organization. Customer Lori Bieda introduced the concept in the fourth quarter 2009 sascom column, Lost in translation:

For large organizations with many lines of business and deep, rich databases, making sense of information has become a business itself. What is needed now is a “translation layer” to ground businesses in fact-based decision making. The analytics community is ideally positioned to become the translation layer.

Bieda, who leads a team of 80 analysts at Canadian bank CIBC, explores this idea further in the new white paper, The Translation Layer.

The paper includes a useful chart defining and describing three roles for analytic workers in the tranlation layer:

• Analytics Community as SERVICE PROVIDER: Facilitates execution of analysis and research for the organization and provides analytical support to enable business decisions.
  
• Analytics Community as CONSULTANT: Acts as a centralized hub for all analytics and research knowledge and expertise in the organization and facilitates best practice information exchange related to that expertise.
  
• Analytics Community as BUSINESS DRIVER: Leverages domain expertise in analytics and
  research, combined with business knowledge, to filter, challenge and prioritize incoming requests for the benefit of overall business.

Which of these roles sounds familiar to you? Does one of them fit your job description? Or does your organization still need to create a translation layer?

Is it even possible to reduce fraud? This pointed question was asked Tuesday at the SAS Media Day fraud panel. After all, today’s fraudsters are smart, global, networked and hi-tech. As soon as you catch one, another steps in. And once you put a system in place to combat a certain type of fraud, a whole different type of fraud appears that you probably never anticipated.

“Fraudsters are very much like a pack of wolves,” says Chris Swecker, corporate security expert and former Assistant Director of the FBI. “And the financial institutions are the prey: They’re really trying not to be the next victim, and they’re trying to outrun each other or hide the best they can.”

But it doesn’t have to be that way. “I think those roles can be reversed,” says Chris. “With the help of analytics designed to look at ring-related network activity, you become the hunter and the fraudsters become the prey.”

Rex Pruitt, a Business Analyst at PREMIER Bankcard LLC, agrees that it is possible to reduce fraud, and he has the numbers to prove it. Using predictive models to anticipate fraud activity before it occurs, his organization reduced the rate of application fraud in its portfolio from an estimated 4 percent down to an estimated 3 percent.

“That equates to about $9 million in total revenue to the company,” says Rex. “You gain a lot by being able to identify those fraudsters.”

How does it work? The predictive model identifies fraudsters with a score during the application process. Applicants identified as fraudulent are eliminated from the portfolio before the bank has even incurred the cost of fraud. Rex says early identification can also free up volume capacity, so the bank can bring on more good applicants.

To build on the type of analysis PREMIER is already doing, Chris Swecker suggests banks use network analysis to identify rings of fraudsters that can be observed in the bank’s data. “You’re not going to eliminate fraud – but you can create better deterrents and a much higher risk environment for fraud,” he says. ” What I advocate, and the record is very clear: the way to get at financial crimes is to look at them, address them and detect them as a network.”

Chris worked with a large, international bank on a networked fraud detection project using SAS and was able to identify 40 new fraud rings almost instantly. “We had billions of transactions, hundreds of thousands of customer accounts, and myriad of products and services. SAS provided a way to look at the data and see the broad network activity that’s going on using our own data.”

Chris says there’s a clear supply chain that you can see when investigating networked crimes, especially with Internet crime: You have individuals that steal and sell the data, buyers who usually resell it, and eventually the data makes its way to the people who exploit it by manufacturing credit cards and debit cards, which then pop up somewhere in the hands of someone committing the detectable fraud act.

“I’m careful not to use the word ‘organized crime,’ because it’s ‘network crime,'’’ says Chris, and there's a difference. “It’s not like a hierarchy with a crime boss on top and layers below him in an org chart. Fraud networks are spidered out. It is a network, and we ignore the network at our own peril.”

Hear more from Chris and Rex – and learn about SAS fraud solutions by visiting the Media Day press kit or watching video snippets of the panel discussion by topic area:

SAS is hosting three big events this week, and you can follow along from your computer through video, photos, blog posts and more. Quickly, the three events are:

• SAS Media Day in Cary.
  
• The M2009 data mining conference in Las Vegas.
  
• The Premier Business Leadership Series in Las Vegas.

For SAS Media Day today, my colleagues in external communications are hosting 20 journalists and bloggers from six different countries. Attendees heard presentations this morning from SAS CEO Jim Goodnight and SAS CMO Jim Davis. Customer panels were part of the event too, with panel topics on optimization and fraud detection. You can follow journalist commentary from the event live on Twitter by searching for SAS Media Day. Current interesting tidbits include:

• JohnGallant1: From #SAS Media Day. Former G-man describes networked (vs organized) crime. Supply chain of folks involved, from stealing info to using it.
  
• MendezABC11: Discussing business optimization and fraud prevention at #SAS media day. Interesting technological applications.
  
• ESLundquist: #SAS 2009 revenues will be close or surpass 2008 $2.26billion says #businessanalytics SAS boss Jim Goodnight at media day at HQ

The media day panels are being recorded, and I'm told video will be available tomorrow, so come back for that later this week. James Taylor, blogger and decision management consultant, has already posted three entries from SAS Media Day, including this one about SAS customers using optimization.

M2009 is taking place in Vegas today, where hundreds of analysts, statisticians and managers in the data mining field have been discussing business uses of data mining. My colleagues Kelly LeVoyer and Anna Brown will also be recording interviews with the winning poster presentations, which will be available after the event.

Kelly and Anna will be staying in Vegas for The Premier Business Leadership Series later this week, where they'll be semi-live blogging the keynote talks and interviewing some of the customer presenters. Watch for those posts to appear here Wednesday and Thursday. You can also track this event on Twitter and see who's attending on Crowdvine.

I asked a cross-section of SAS bloggers for their blogging advice, and documented their answers in a recent presentation. Click through the slides below to see what they said.


If the slides don't work for you, you can also see the tips typed out below.

I'm listening to Jon Weisz, marketing director for JMP, talk about data-driven story telling. He's explaining the differences between statistics and data visualization. Statistics are often used to confirm a hypothesis, he says. Data visualization is used for exploration. Jon's defining models as approximations: "We're attempting to experiment and determine factors and effects." Often, when statisticians are working with models, they're attempting to answer the question, "What if ...."

Jon is walking through a simple example in the JMP profiler, to introduce some very basic visualization techniques. The questions he's asking are, "What time will I be home from work? And what affects the arrival times?" With just a few variables to account for changes in arrival times, he ends up showing that his assertion, "I'll be home from work before 6:00," is right only about 78 percent of the time.

Moving on to a more complex example, Jon is looking at U.S. housing data from Freddie Mac. He pulled the public data set directly into JMP and is now using the Graph Builder, and showing rules within the product that can tell you how best to display the data.

He's asking the questions, "Was there really a bubble? And did it really pop?" The graph for California shows a clear peak in prices and a huge drop off. In Michigan, there's less of a bubble and more of a gradual decrease.

When looking at graphs for all 50 states side-by-side, you can see that the real estate markets have behaved very differently in each state. Realizing this, Jon decides to cluster the states based on real estate growth data. Using JMP to determine the optimal number of clusters, he separates the states into six groups. The clusters show clearly that AZ, CA, FL and NV experienced the crash in the housing market most dramatically.

Next, Jon is moving the data to SAS Enterprise Guide. "Enterprise Guide is very complementary to JMP," says Jon. JMP's purpose is all about discovery. What Enterprise Guide presents you with is a flow chart. You have to know the answer to get the flow - which you found in JMP. "Once you know the proper analysis flow, then you go into EG and document it."

The final report Jon shows of the state housing market data clustered into 6 groups is very easy to digest at a quick glance. He asks: wouldn't it be nice for these organizations to provide the data in this format on their Web sites instead of just as raw data files or Excel spreadsheets? Wouldn't it be nice for you to do the same in your company?

The title of this presentation is, "Connect with SAS Professionals around the World with LinkedIn and sasCommunity.org." Kirk Paul Laffler is presenting the talk that he co-wrote with Charles Shipp. Originally this presentation was written to cover only sasCommunity.org, but they updated it recently to include LinkedIn, in recognition of the popularity of that site for business networking.

The objective of this talk is to show you how you can connect with other SAS users around the world, says Kirk. "I like to connect and share knowledge," he says. He's in 50 different groups in LinkedIn.

Kirk says he has abandoned his own personal Web site and uses sasCommunity and LinkedIn instead as his main home pages on the Web. That's where he directs business contacts to learn more about his work.

sasCommunity is free and just for SAS users, says Kirk. SAS provides the hardware and networking capabilities, but the site was built by SAS users to meet the networking and collaboration needs for sharing with other SAS users. It's set up as a wiki, so all registered users can easily contribute and edit content.

Features on sasCommunity.org include forums, user blogs, upcoming events and watch lists that can alert you to updates on specific topics or conferences. You do not have to create an account to access sasCommunity.org. "That's one of the virtues, in my opinion," says Kirk. If you're shy or if your company discourages sharing, you can still benefit. Another option is to create an account with a pseudonym if you're not comfortable sharing your full name on the Web.

sasCommunity has 38 blogs in a wide range of topics, including one for SAS Global Forum 2010, some for consultants, and some authored by SAS employees. It also inludes an area called Sasopedia, which links to dozens of SAS-related resources, including conference proceedings, white papers, Webcasts and FAQs.

For those who use SAS-L, Kirk says sasCommunity is not a replacement for SAS-L. It's another channel for people interested in all things SAS. It's currently growing, but Kirk says he'd love to see it grow even more. He's very interested in hearing feedback from other SAS users about the site.

SAS CIO Suzanne Gordon starts her speech by asking groups of us to stand if we're programmers, statisticians, analysts or communicators.

She's going to talk to us about prospering - both in a down economy and in a good economy.

Suzanne received a degree in math & computer science. She says she had really good grades but graduated during a recession, and several months went by without her getting a job. Then, on the same day, she received two job offers: one from IBM and one from North Carolina State University.

She took the job at NC State.

When it comes to making career decisions - or any big decisions - Suzanne likes to remember this advice from a friend: There's no right or wrong decision, just two different paths.

Suzanne started by working in user services at NC State, where a lot of PhD students and professors were using SAS. "I found that although a lot of people were familiar with SAS, not a lot of them knew statistics," says Suzanne. "I saw a void, so I took some stats courses, and was able to help students with that." She also became the SAS consultant for the university and would go across the street to talk talk with Jim Goodnight, John Sall and the rest of the staff.

When Jane Helwig went on maternity leave from SAS, Suzanne was recruited to help fill in for some of the work Jane did, and she became the first MIS manager at SAS.

Here, Suzanne offers advice from her dad who used to say, "Work hard, let the boss know you're working, and ask for promotions and raises." So when SAS hired a second MIS person she asked if that person,"could work for me instead of with me?"

For awhile, Suzanne worked as director of consulting, which provided a different view of the customer. Even though this wasn't directly related to her career path, the different perspective ended up helping when she returned to IT.

Even in good times, Suzanne tells her children, you should always have a plan A, a plan B and a plan C.

Four things Suzanne recommends you do to prosper:

I'm posting this live from the Midwest SAS User's Group (MWSUG) in downtown Cleveland, Ohio. Attendees are eating dinner, and we're about to hear John Sall, Executive Vice President of SAS, talk about the history of the company he co-founded along with Jim Goodnight, Tony Barr and Jen Helwig in 1976. Following John's walk down memory lane, we'll be hearing from Suzanne Gordon, SAS CIO, during the Opening Ceremony. Suzanne is slated to talk about prospering in a down economy.

John starts out talking about Gertrude Cox, who came from Iowa State to Raleigh and founded the statistics departments at NC State, UNC and Research Triangle Institute.

The presentation is accompanied by a lot of great, grainy photos of the early days.

John says one of the first computers at NC State was an IBM 1410. Jim Barr was hired as an intern in the statistics department to program the 1410. Jim Goodnight, an Assistant Professor at NC State, and Jim Barr created the program SAS in the late 60s.

John Sall joined the department in 1974 and Jane Helwig joined a year later to help do documentation. In 1976, SAS turned from a project inside the statistics department to a private company. "We were just a group of six," says John. "It started out very small."

Of course, this was before venture funding was common around Universities. Now NC State has Centennial Campus, and it's part of the University's mission to spin off companies. That was not the case in 1976, so they did everything on their own.

Jim was good at marketing, says John, while showing a picture of Jim on the phone with a few papers scattered around his desk. "Jim Goodnight is known as a clean desk person," explains John. "This is probably the messiest his desk has ever been."

Next, John shows an old photo of himself at a desk, "... thinking about making some phone calls." At the time, John was teaching short courses on SAS, and he says he was not as good at marketing.

"Have you heard the M&M story?" asks John.

I'm heading to MWSUG, the Midwest SAS Users Group, on Sunday by car. If you'll be there too, look for me and tell me what you'd like to see us write about on this blog or in sascom magazine.

I'm excited to attend the statistics 101 sessions and a few of the tutorials. I'm also looking forward to hearing John Sall talk about the history of SAS and hearing what long-time SAS users Kirk Paul Lafler and Charles Shipp have to say about the conversations they're having at sasCommunity.org and LinkedIn.

Keep reading to see the preliminary schedule I've created for myself - but it was very hard to pick for some of the time slots, so it's subject to change. If you have others to suggest, let me know.

Last week I told you about the person I sat next to on the plane ride from Boston to Columbus, and I promised to tell you about the cab driver I met on my way to the airport in Boston. He had trained to drive trucks at a school in Chicago. His first long haul - as part of that training - was from Chicago to Solon, Ohio. He told me about it after I told him I was in town from Ohio.

From there, I learned that he lost his job driving trucks a year and a half ago in a layoff that also took the jobs of a few thousand other drivers. He decided to drive a cab after the layoff partly because licensed Boston cab drivers keep their cab six days a week. It's his for errands and everything else for six days out of seven, saving him car payments, gas and insurance. That's a smart move. His wife is working on her master's degree in nursing. When she completes that he plans to return to school for his master's in forensic accounting. He has three children. Two of them - twins - are seniors in high school. One of the twins also wants to go to school for forensics. The other is considering a career in either nutrition or dentistry. He shared more about his finances and his mortgage and other legal matters - but we won't get into all that.

My point in talking about the cab driver here is that his story resonates with the theme we tried to carry through the fourth quarter issue of sascom magazine: People - like organizations - are feeling the affects of the economy, but they're adjusting. They're making smart decisions now to come out stronger when the economy recovers. You'll find this topic covered in these sascom articles:

• A cover story that describes Family Dollar's growth during the downturn & how they achieved it.
• A look at three companies using analytics to outsmart the recession.
• 11 ideas for economic recovery, which actually started as a blog post on this site.

What are you doing to recover? What is your organization doing?

I flew to Boston earlier this week to attend a half-day presentation about marketing optimization that was co-sponsored by SAS and HP. The posts I'm writing about the details of that event are still rolling around in my mind and scratched away in my steno notepad.

In the meantime, I'm jotting down this post about the people I met on my way home.

I was in Boston for less than 24 hours, so there wasn't a lot of time for socializing or site seeing, but I lucked into a few interesting conversations with the cab driver who took me to the airport and the passenger beside me on the flight back home to Columbus.

The passenger beside me was using the credit card miles he'd built up buying construction equipment, he said. He doesn't fly much because he doesn't have the time, but he found an excuse to use the miles here recently to return to his alma mater. He graduated from Antioch College in Yellow Springs, Ohio. I didn't realize it, but Antioch College (not to be confused with Antioch University) shut down last year. Now the alumni of the college have banded together to rebuild the college, and he's part of the effort. I told him briefly about my Alma Mater (Ohio University) before the flight took off, and we chatted some about small, liberal arts college towns before we both returned to our reading materials for the flight. After landing, he handed me his card and encouraged me to visit Yellow Springs some time to see the progress they're making at the college. I handed him my card in return, and he kindly inspected it, making note of my title, then my company name. "Oh, SAS!" he said. "My wife uses your software! She works in the banking industry."

When you work in Cary and tell people you work at SAS, everyone knows where that is. But when you live in a small town in Ohio and tell people you work for SAS, you don't get a lot of head nods. So finding someone on a flight from Boston to Columbus who knows what we do is a good way to end a day. Plus, he was a nice guy and I really have been meaning for years to visit Antioch College. Maybe now I'll add that to my list of fall family road trips.

I'm running out of time, so I'll promise to tell you about the second person - my cab driver - in a post next week.