Since business analytics is all about turning data into insight that will drive future decisions, it makes perfect sense that as editor of the SAS Business Report, I’d use this mid-year month of June to study the newsletter’s data – and make sure it continues to provide you with valuable information. I reviewed a couple of data points: subscriber demographics and most popular articles over the last five issues. Here are some conclusions.

Overall, analytics and management-related content takes the cake in terms of the highest click-through and engagement rates for this newsletter. That’s not too surprising since the majority of subscribers represent management-level titles. These articles outranked others by far.

• All About Analytics: Five Essential Papers
• Understanding Analytics
• The New World of Business Analytics
• Staffing for Intelligence
• Driven by Data: The Importance of Building a Culture of Fact-Based Decision-Making
Continue reading "And the data says? Analytics wins."

We're ending the day here at what Thornton May calls a post-industrial campfire. May's objective as the last presenter on the first day of The Premier Business Leadership Series is to get our analytical minds "popping" and to get attendees "barking dog excited" about the future.

In addition to being an author and a college professor, May is first and foremost a Futurist. Donning a red bow-tie and speaking with fast-paced excitement, he says he is pathologically observant. As a futurist, much like an analyst, his job is to observe, interpret and hypothesize. In his day-to-day work that often means his objective is "to inform and stimulate efficacious behaviors."

One of the primary jobs of futurists is to measure how fast things are changing. In fact, May has spent 20 years studying how organizations make decisions and focusing on the knowable trends that will impact our lives. May is very convincing in his contention that we are living through a monumental moment in history where major changes in the business environment are taking place every five years, as opposed to the 20 to 50 year periods that marked revolutionary changes in the past.

Every five years we have a:

• New world.
  
• New game.
  
• New behaviors.

Getting value out of masses of data was one of the key themes of Tuesday’s sessions and May drove that idea to the limits. But our thinking has not yet caught up with the reality. Thornton used an analogy from history. In the Middle Ages, nobody felt they were in the Middle Ages because there was no sense of change, of transition. By contrast during the Renaissance, people were aware that the world was on the verge of something big. Well today we have a Renaissance reality but a lot of people are still stuck in Middle Ages thinking. We have enough data to know everything about everything but most of us, even people in IT, haven’t yet worked out how to deal with it.

There are exceptions: some CEOs like Mark Hurd of Teradata and Paul Otellini of Intel are getting excited about the possibilities of analytics. They have seen that ignorance is no longer an option, it is becoming obsolete. So the big question for the rest of the 21st century is going to be what to be figuring out what to do with all this information because there is nothing we cannot know.

It's critical for business leaders to be asking, "Do the people in your organization know there is NOTHING they cannot know?"

In case you're still underestimating the changes that May is discussing, consider his analogy: "Knowing is to 21st century man what walking or building fire was to our pre-historic ancestors."

Now, Google the phrase, "too much information." You get more than 200 million results. There's a de-synchronization between how much information we can access and store - and how much we can actually understand, says May, but business analytics technologies like statistical reporting, forecasting and optimization make it possible to find answers, and CEOs are excited about what they can learn about the business with analytics.

"Being able to expeditiously understand and efficaciously act on all this data is the only thing that lies between you and success," concludes May.

Semi-additive measures can produce unexpected results when used with VisualTotals and calculations requiring a dimension reference When a calculated measure uses a function that requires a dimension reference, the resul

Solve order specification is defined in MDX Solutions: With Microsoft SQL Server Analysis Services by George Spofford as A higher number indicates that the member is calculated using the values that

They say opposites attract – and that seemed to be the conclusion of the panel discussion “Competing on Analytics – The Winners and Losers” at The Premier Business Leadership Conference featuring Jim Davis of SAS, author and academic Thomas H. Davenport and Giles Pavey, Head of Analysis at dunnhumby.

Dunnhumby’s most successful client is UK retailer Tesco, and Giles summed things up well when he described the culture and decision making process at Tesco. First, there is a fanatical culture of customer-centricity. Second, the Tesco Board is prepared to back the experience and gut feel of senior executives – but they want those gut instincts backed by quantified information, which is where dunnhumby comes in. Moreover, they measure success rigorously, not just in terms of discrete cause and effect (such as increase in sales by individual product item) but also in terms of total increases in sales of the affected customers (in other words, the observable increase in customer loyalty).

Asked by presenter Marc Davis, “With so much data, where do you start?” Jim Davis underlined that an analytics project is a very different animal compared with, say, an ERP project. “The key is to start with specific business problems, solve them, and demonstrate ROI. It won’t solve everything but you can build on success incrementally. It might take weeks of months but it certainly won’t take years to deliver value like an ERP project.”

Thomas Davenport expressed the belief, backed by research, that few organizations – perhaps only ten percent – understand the value of analytics. He advised organizations to set a clock on projects and measure value. “Do not simply measure ROI. Experiment using analysis after the event and learn from it. We need to be students of error.” In the long run, this will make organizations ever more sophisticated in their use of analytics and they will progress towards prescriptive analytics, which not only tell us what will happen in the future but also what we should consider doing about it.

But while fact-based decisions are generally more effective, there will always be a place for experienced and gut feel. A pilot still needs to look out the window, no matter how many navigational aids s/he has.

In a thought-provoking keynote speech at The Premier Business Leadership Series in Berlin, Soumitra Dutta asked, "Are we born innovative?" The answer, according to Dutta and a majority of hands raised in the audience is, Yes.

Children, for example, experiment, ask questions, observe and tolerate a high-level of risk, all of which are also key traits for innovators.

"So what happened to that spirit of exploration and innovation we had as children?" asked Dutta, the Roland Berger Chaired Professor at INSEAD and Director of elab@INSEAD. In his view, the educational system, and then (most) organiations have gotten very good at suppressing innovation. There are good reasons for this: primarily, that these organisations have to focus on repeatability, quality, reliability, cost-efficiency. Too often we become "victims of routine." We look for incremental changes to the status quo, rather than the big, innovative shift. But Dutta asks leaders, "Did you design your organisation for Innovation?’ – if not, then it begs another question: how to deal with the disruptive change that comes from outside your organisation?

Another major consideration is the impact of the internet on stimulating social and cultural change. Today’s young employees have never experienced life without the internet. They have expectations and behaviours derived from their experience of the world through the lens of pervasive connectedness and don’t understand traditional hierarchical leadership. This is both a curse and a blessing for the modern leader. A curse in that it is challenging to lead these people, a blessing in that they are the ones most comfortable with collaborating through the frontier of your business and therefore with valuable sources of potential innovation – your customers, your business partners and of course, they themselves.

My enduring take-away from this session will be that we need to create an environment that cultivates and nurtures innovation. Furthermore, we need also need to provide a platform for turning innovation on the "new normal."

The hardest thing about offering advice to businesses about social media, says Clay Shirky, is convincing business leaders to see the process as a cultural change not a technology change. For most businesses, cultural changes are harder than technology changes, and that is especially true when the culture change is led by people outside the organization.

Shirky, a professor at NYU and author of the new book Cognitive Surplus, presented today at The Premier Business Leadership Series in Berlin.

Offering case studies from organizations like HSBC, Etsy and Modernista alongside social science studies of group behavior and negative reinforcement, Shirky showed how changes in the media landscape are occurring hand-in-hand with changes in the way we understand human behavior.

According to Shirky, the media change with the biggest impact is not the change to two-way communication between a business and its customers. Rather, it's the organized communication efforts taking place between consumers that are creating the biggest shift right now. "The loss of control you fear is already in the past," says Shirky. "What's left is what you decide to do about it."

To illustrate, Shirky used Amazon.com as an example of a business that is embracing this change. Amazon is not a retailer with a Web site, explained Shirky. It's a search engine with a warehouse. I'd add that it's a search engine AND a consumer review site with a warehouse. This example, to me, is especially compelling, because Amazon has been around so long that we do forget that they are a great social media success story. And, says Shirky, they have succeeded primarily by treating customers as a group that is valued and offered resources to share a conversation and influence the business.

Another factor affecting how businesses operate in this space is that big changes are happening at a small scale. "One near-law of social media is that everything today that's big and good started as little and good," says Shirky, using Wikipedia and Linux as examples that began with their creators sending a humble note inviting friends to give this new little thing they created a try.

What can business leaders do to embrace these changes in their own organizations? "Take everyone who's excited about social media and lock them out of the building. Tell them not to come back until they have 12 little ideas," says Shirky.

In a later presentation, Jim Davis espoused a similar theory, saying shiny objects can be good things. As long as employees don't get so distracted that they lose site of the original task, their interest in shiny objects can often lead to innovation and new ideas.

Sometimes, when you give users a platform to interact, they will even solve problems for the business. Shirky's example here comes from Etsy.com, a crafting marketplace with a member who is also a lawyer. When a new consumer law was passed that affected members of the site, this member posted a comprehensive article explaining how the change would affect members. "This could not have happened if Etsy had not been in a position to convene this conversation," says Shirky. And since the article was searchable and saved and promoted throughout the site, "when this member solved the problem once for one person, the problem stayed solved for everyone all the time."

Today, former US Secretary of State Madeleine Albright is wearing a silver pin of a globe encircled by hands. On bad days, she has been known to wear insect or predatory animal pins. On good days, she wears butterflies or flowers. She first communicated her mood via her jewelry after former Iraqi leader Saadam Hussein called her "an unparalleled serpent." In response, she purchased and proudly wore a snake broche when she next spoke to the press about Iraq.

But let's get back to today. Like the economists on an earlier panel at The Premier Business Leadership Series in Berlin this morning, Albright is cautiously optimistic about the future. Or, as she puts it, "I am an optimist that worries a lot." What is Albright optimistic about? Capitalism as a positive force, global cooperation for the good of all people and business competition that inspires confidence and innovation.

And her worries? She is concerned that government leaders do not feel accountable to the world at large, but focus too much attention on the opinions within their own nations, which tend not to be as altruistic as we might hope. The result, according to Albright is that we often see more lofty rhetoric than concrete action from politicians and heads of state. Likewise, we see more incremental measures rather than bold steps.

If we are to move forward, says Albright, we must cooperate, restore faith in institutions and even in capitalism itself.

Albright offered three tools to help us move in right direction:

1. International coordination, with the upcoming G20 summit as a positive exxample.
   
2. The Power of government to establish and enforce the rule of law.
   
3. Trade policies that encourages creation, treat businesses fairly and reward customers.

Albright's talk was peppered with anecdotes from her time as secretary of state and her analysis of the decisions being made today by world leaders. She likened policy decisions to complex decisions and encouraged business leaders at the conference to listen to opposing voices, make compromises and act confidently when making decisions.

In conclusion, she pointed to the pin on her jacket and said, "We all need to work together in confidence for world leadership."

Two sharply contrasting – though by no means opposing – views of innovation were offered by Andrew Rashbass and Jim Goodnight in the panel discussion on “Managing the Complexity in Business” today at The Premier Business Leadership Series.

Andrew Rashbass, CEO of the Economist Group addressed the question from the point of view of an organization that has stayed true to its mission since 1843, fighting ignorance with intelligence as expressed by its anonymous editorial team. “On the editorial side, we never do any quantitative research into where our customers want to go in the future. We don’t need focus groups because we already know that our mission is to deliver a reflective and pleasurable reading experience.”

“Our editors write for each other,” said Rashbass, explaining that if their articles pleased their colleagues, they would delight their audience.

Of course, The Economist has moved with the times on the way it delivers content. But it does so cautiously, in order not to disturb that reflective and pleasurable reading experience. This is key to the brand’s success at a time when the publishing industry as a whole is going through such upheaval: innovation must be put at the service of a tradition stretching back to 1843.

Jim Goodnight explained that SAS has enjoyed 34 years of unbroken revenue growth and profitability precisely because it has stayed close to its customers. “We are constantly looking for new problems to solve in different industries,” he said. For example, a bank based in the Far East recently told SAS that it was unacceptable that it still took 24 hours to calculate its financial risk position. By applying the latest blade hardware and threaded processing techniques in SAS software, SAS reduced this to 15 minutes. “In effect this means the bank will be able to calculate risk positions before, rather than after the event,” said Goodnight.

The big mistake, said Goodnight, is to use technology for its own sake and develop products that do not interest customers. This was why so many of the dotcom bubble companies failed. “There must be a customer base. Products must solve real problems.”

By the way, if you ever wondered why The Economist’s articles are always anonymous, Andrew Rashbass provided the answer.

First of all it is a point of differentiation in a world dominated by celebrity journalists. It gives The Economist a unique voice, and it enables journalists to write with that voice, and expressing The Economist’s house opinions, with integrity.

Most importantly however, it creates a collaborative, collegiate environment that is ideal for generating quality content. “Economist journalists aim to write the best possible story, which requires a collaborative effort,” concluded Rashbass.

Continue reading "Two paths to innovation"

I'm at The Premier Business Leadership Series in Berlin, Germany, where I'm semi-live blogging the first panel discussion of the day: Dynamics of the Global Economy: What's Next? The experts on the stage are:

• Gerard Lyons, PhD, Chief Economist and Group Head of Global Research, Standard Chartered.
  
• Joseph Quinlan, Managing Director and Chief Market Strategist, Bank of America Global Wealth and Investment Management.
  
• Norbert Walter, PhD, Former Chief Economist of Deutsche Bank and Managing Director of Walter & Daughters Consult.

Mark Jeffries is the panel host. He's introducing each individual panelist with a one-on-one interview before moving into the panel format.

Gerald Lyons begins by encouraging attendees to be positive about the economy in the long term but to remain cautious in the near term. The big uncertainty, he says, is the United States, where the economy tends to pull back faster than the experts ever expect. Questions that remain: Will that happen again? And what happens when the stimulus money goes away? "We can't ignore near-term, down-side risks, and we need to be prepared not only for the expected but also the unexpected," he says.

The biggest challenge in Europe is the loss of confidence, says Lyons. In China, of course, the pace of change is phenomenal, even outside of the major cities. Overall, he believes that markets in the east will continue to grow, but in the near term, he says, "If the west is not booming, the world can't boom." After all, the west still accounts for two thirds of the global economy. How big is the global economy? It was $31 trillion a decade ago and $61 trillion before the economic crisis, and it shrank $4 billion during the crisis.

Returning to his optimistic outlook, Lyons reminds attendees that not everything broke during the economic crisis. Canada, Australia and parts of the UK did well, for example.

What do we need in the future, according to Lyons? More balance in the world economy. The West needs to spend less and save more. Asia needs to do the opposite. And currencies need to adjust. As the stimulus policy wears off, economies have to have plans for reducing debt and keeping interest rates low.
Continue reading "What's next for the global economy?"

My colleagues Tapan Patel, Wayne Thompson & Chris Stephens hosted over 550 live attendees on June 16th for our Data Mining 101 live webinar, part 3 of the Applying Business Analytics Webinar Series. Folks joined from all over North America as well as 32 other countries around the world. Since many people had similar questions during the webinar, I thought it was worth sharing some of the Q&A with you! Enjoy the read:

Q: What is the rate of false hits in using this kind of discovery tool, e.g. in detecting criminal activity?
A: Unfortunately, it depends on several factors and there is not an easy answer to this. Some of the factors include the modeling techniques used with EM and any data preparation used (imputation, transformations, etc.). It is also very data dependent.

Q: How can we use scoring for collection agencies?
A: Scoring is just the process of applying the model to data from new customers. You could build a model to predict which accounts are most likely to be "un-collectable" and then apply that model to new accounts to decide how much effort to put in.

Q: Can we achieve the goals for credit scoring using Base SAS instead of SAS Enterprise Miner?
A: It's possible to write SAS code. However, you will not get some of the automation benefits of SAS Enterprise Miner, especially the automated generation of score code, which greatly facilitates putting the model into a production environment.

Q: Is optimized binning possible in Base SAS? I believe it is just possible in SAS Enterprise Miner.
A: That's correct - It's only available in SAS Enterprise Miner.

Q: Does the data have to complete for logistic regression? What if we have a lot of missing values?
A: You do need to account for missing values. SAS Enterprise Miner provides tools for imputing missing values as part of the data mining process flow.

Q: How would one incorporate a model built to run via SAS Enterprise Guide into this software?
A: You can use the Import Model Node. It can import and assess a model that was not created by one of the SAS Enterprise Miner modeling nodes.

Q: Would the assessments be model performance recommendations or model design recommendations?
A: The assessment statistics are based on the model created in Base SAS, SAS Enterprise Guide, etc. It will calculate Lift, ROC, Gini, etc. It does not recommend any alternate designs.

Q: Will the SAS add-in work for Excel 2010 and allow for interface with Power Pivot?
A: The SAS add-in does support Excel 2010. I'm not familiar with Power Pivot, but I don't believe that SAS provides any specific integration with that feature.

Q: Can models be stored that are created by hand (SAS code) rather than by GUI?
A: Yes

Q: Is it easy to import data? Can you show examples of importing data from different file types?
A: Yes - There is a file import wizard that enables you to import data from various sources. However, I don't believe that Wayne will be showing that today

Q: Is there any source (maybe your website) that could show me how robust SAS capabilities are?
A: There are a number of sources. To ensure we best address what you mean by robustness, I suggest you contact us directly which you can do from www.sas.com. You might also check out our support site.

Q: I noticed that several of the input variables did not have a normal distribution. Do you need to use the Transformation node to normalize inputs before using in models? How do you treat interval, nominal and ordinal data differently in transformation proc?
A: You don't have to but you should. The best practice would be to normalize the inputs. We have several different transformations specific to interval and non-interval models. Most of the time, the transformed input variables make for a more robust model.

Q: Is SAS Model Manager sold separately from SAS Enterprise Miner or is it bundled?
A: You can buy them separately or in a bundle. SAS Enterprise Model Manager is the name of the bundle.

Q: What is the storage space consumed when creating the different models?
A: The storage space required in SAS Model Manager is minimal since you are storing the model logic and not the data associated with the model.

Q: Can these do Bayesian data mining?
A: SAS Enterprise Miner does not provide built-in capabilities for Bayesian data mining. However, SAS does provide capabilities for Bayesian analyses through the SAS/STAT module

So, keep them coming! If you watch any of the Analytics On Demand webinars and have some questions that you need answers to, please ask away! We hope to see you next month on July 21st at Forecasting 101!

When performing a query in SAS Web Report Studio, you might see "Libname xxxx is not assigned" when the query uses a preassigned library.

If you encounter problems with SAS Financial Management and you are asked to increase the logging level, complete the following steps: Note that this example details the steps to increase the logging level for t

If you are working in a SAS Financial Management Data-entry table and you enter a simple reference to another cell within the table, such as =C25 that simple cell reference is converted

Beginning with SAS Financial Management 4.3, ODCS/Calculation Clustering can be used to reduce the time multiple queries need to complete. SAS Financial Management Calculation Clustering, (also known as ODCS Cl

To determine who is logged on to SAS Financial Management Studio, the SAS Information Delivery Portal, or the SAS Financial Management Add-In for Microsoft Excel, perform the following: ensure that SAS R

If you are unable to log on to SAS Financial Management Studio and you receive the error message: You are not authorized to use this application ensure that you have been assigned the F

When using SAS Financial Management software, the following information should be considered when determining whether to use modeling formulas or driver formulas. The most important decision for a planning im

In SAS Financial Management software, efficient formulas are the result of two separate actions: writing and scoping. Writing efficient formulas identifies the explicit members of the formula, while scoping controls

When creating models and queries in SAS Financial Management release 4.4, consider the following guidelines: Practical Limits of Model Size: A cycle or model should not exceed 12 dimensions.<