Juice Analytics

Attorneys like to use phrases like “res ipsa loquitor” and “crimes of moral turpitude.” Doctors talk about pharyngitis and rhinorrhea rather than sore throats and runny noses. Language can give an aura of authority, not to mention result in a slate of prime-time TV dramas.

If data analysts are to be appreciated as the keystone of the knowledge economy, we need to develop a language of our own. We need phrases and terms that mask our meaning from outsiders and provide a short-hand for common situations and struggles.

It starts here—with your help. We’ve collected a few of the words, phrases and sniglets (“a word that should be in the dictionary, but isn’t”) that capture the flavor of our profession. But there is more work to be done; share your ideas in the comments and we will update this post on the fly. With any luck, we can be bamboozling your data-phobic friends in no time.

A starter list:

1. Chart-based encryption: A chart that has managed to fully masked the message of the data through poor design.

2. Execu-hole: A senior manager who requests analysis and reporting but doesn’t appear to read, comprehend or otherwise absorb the information.

3. Chartjunk: Popularized by Edward Tufte, “unnecessary or confusing visual elements in charts and graphs. Markings and visual elements can be called chartjunk if they are not part of the minimum set of visuals necessary to communicate the information understandably.” [Wikipedia]

4. Pimp my chart: The process of creating reports, dashboards or individual charts that have a shiny surfaces, 3-D elements, and other exaggerated design elements. Related to chartjunk. Pimped-up charts are sometimes mistakenly presented as well-designed executive dashboards.

5. You sunk my battleship: When someone requests a meeting time that conflicts with one of only a few events you have on your calendar.

6. Atomic baloney slicer: Massive and complex enterprise software solution that attempts to do more than is necessary to solve the problem.

That’s a start, but we need your thoughts on these:

7. __________: A presentation that attempts to distract from the lack of substantive content or evidence with use of screenbeans, clip art, and other stock pictures or illustrations.

8. __________: A data file with more than 65,536 rows, thus making it impossible to load in Excel versions prior to Excel 2007.

9. __________: Charts that are left with the default Excel formatting.

10. __________: A spreadsheet that has grown organically to become thoroughly incomprehensible outside of the mind of the owner.

11. __________: A situation when someone describes a series of complex-sounding statistical techniques (e.g. multi-variate logistic regression, cluster analysis, ANOVA) in an attempt to impress others.

12. __________: An organizational problem where there is an excessive number of reports being generated and little understanding of the purpose.

Magic Ink: Information Software and the Graphical Interface

Yesterday I presented to an B-eye-network audience our perspective on why business intelligence is broken and what can be done to fix it. The full PDF-version (4mb) of the presentation can be downloaded.

A sampling of the fun:

“Chart-based encryption — data goes in, no information comes out”

On the excessive emphasis on reporting over analysis…

“Technologists are looking to build an atomic-baloney slicer”…”Nobody ever got fired for adding more requirements”

“Data analysis isn’t just for the data analysts anymore”

“Have you ever working with a reporting tool that outputted to PDF?”

Hopefully we stirred the pot a little with this presentation. A recording of the B-eye-network event should be available soon.

David Rumsey Historical Map Collection

Ah, the sweet smell of a swindle. Don’t you just hate it when consulting companies cajole deals with hand-wringing about technology and, especially, preying on clients’ lack of expertise?

I’ve seen some of these situations up close but nothing so ugly as this story.

$80 million supercomputer to analyze NYC student achievement

March 6, 2007, 7:58 AM EST NEW YORK (AP) — To understand student performance, the city will spend $80 million on a massive supercomputer that will crunch huge amounts of data and offer up-to-the-minute reports to teachers, principals and eventually parents, the Daily News reported Tuesday.

One million students and no high-volume transactional data? That might be huge to Dr. Evil but even by late 90’s standards that’s not huge. You want to talk huge? Now these are huge. The system that was sold to New York is more along the lines of a CRM system for a medium-sized insurance company.

The “super” reference here is pure drive-through mentality. In the same way that we are a nation that’s overfed and undernourished, this is about a super-sized services contract that sits atop something that could be handled by a regular-sized computer.

The information fed into the IBM-designed system called Aris, or “Achievement Reporting and Innovation System” could include existing data on students—such as gender, race and any disabilities—along with new data from incremental testing.

Some aren’t so pleased with the system’s price tag.

“You can lower a lot of class sizes with that money—or buy a lot of supplies,” teachers union President Randi Weingarten said in a statement obtained by the Daily News.

Mayor Michael Bloomberg told the tabloid the cost was worth it.

“Every child in this city deserves a quality education and we will spare no expense,” he said.

This is where the sweet smell of swindle comes in. There is a difference between being willing to make the investment and having a no-bid contract.

Jim Liebman, the Education Department’s chief accountability officer, also lauded the system.

“Aris will bring together every bit of learning information that we have on every one of our 1.1 million students,” Liebman said. “Now, school professionals will be able to slice and dice that data to see what’s wrong.”

Teachers are underpaid, hardly appreciated, and overworked. I can only wonder what the half-life is of a system that asks teachers to log on to get information delivered by the “chief accountability officer.”

And from an article in InformationWeek, we’re enthralled by a description of the system capabilities:

“Think of a teacher trying to help a student struggling with geometry,” says Michael Littlejohn, VP of public sector for IBM global services. “The teacher could tap into the system and search for best practices on geometry instruction, and get contact information for teachers identified as having strong skills in that area.”

Sometimes it’s good to reinvent the wheel – usually when you’re trying to learn about wheels. But not when you’re drawing away cash from an entity that doesn’t have it to spare. Something like this could be built with off-the-shelf, mature products for a fraction of this wasted time and effort.

Sure, a fully-integrated, one-stop solution is going to run up the price but the functionality doesn’t sound particularly whiz-bang. Best practices for teaching geometry can be found at Curriki or Edutopia or Wikiversity or Openplanner.

The real shame is not allowing such a system to connect more than just the overworked NYC school system teachers. But what would we call such a thing? An inter-net, perhaps?

Nah, that would never catch on.

Related articles

• “Super-mugging” at Tweed
• New Game in Town
• Boon or Boondoggle

Recently I caught up with my college friend John Swigart who now runs the marketing organization at Esurance. When the conversation inevitably drifted to business, I asked about how Esurance was using data to make decisions. I was expected to hear the same old story—big failed data warehouse projects, piles of underutilized reports, frustration about not being able to understand how the business was performing. I was way off.

It seems that John works for the rare company that has managed to live the analytics dream. Esurance competes on analytics—not in the idealistic model highlighted by Tom Davenport, whose “full-bore” analytics competitors are defined by:

“Top management had announced that analytics was key to their strategies; they had multiple initiatives under way involving complex data and statistical analysis, and they managed analytical activity at the enterprise (not departmental) level…

…Employees hired for their expertise with numbers or trained to recognize their importance are armed with the best evidence and the best quantitative tools. As a result, they make the best decisions: big and small, every day, over and over and over.”

That’s window-dressing. John didn’t make any grandiose pronouncements of Esurance’s analytical achievement or talk of the best tools and most complicated models. He simply stated that data-based decision-making has been a part of the culture from the very beginning and he considers it essential to running a smart business. A few points that he emphasized:

• Clear linkages between metrics. There needs to be a well-understood hierarchy that has important financial measures at the top (i.e. revenue) and connects to the underlying drivers.
• Frequent reviews of reporting. Senior managers get together on a regular basis to look through the core reporting. These meetings are detailed, but somehow useful enough that people stay committed to the process.
• Learning takes time. John recognized that Esurance cound not be as evolved in their understanding of the business without a commitment to this approach from the very beginning.

After getting off the phone with John, I asked him to respond to a few questions so our readers could get a taste of their approach:

How has Esurance managed to develop a culture that embraces decisions using data?

We don’t make decisions based “I think we should this.” We look at data to find out what we know, then decide what to do based on the facts. We identify expected outcomes up front and determine how we are going to measure the change before we implement something. Also, a data-driven culture starts at the top of our organization.

What processes do you have in place to get the right data in front of the right people?

We have centralized data warehouse and reporting structure. Everyone gets their data from the same place and the metrics are universal. This took 3-4 years to get it right, and we built it from scratch. It takes a substantial commitment to pull off.

What is the role of the analyst in your organization? What tools do they use?

We have technical analysts and DBAs in our business intelligence group that deal with the more technical issues. In Marketing, then, we have analysts how are on the individual marketing teams that work closely with the business people. The use some basic tools, nothing terribly fancy.

From an analysis perspective, what do you do when you are testing new marketing opportunities?

All tests are done with as much of a controlled environment as possible. With so many moving parts, this can be difficult, but is important.

How has analytics contributed to the success of Esurance?

Truly one of our competitive advantages. We would not be where we are today without great data and a dedication to using it through all levels of the organization.

Our friends at Tableau invited us to lead off a webinar about the broken bits of Business Intelligence and what is needed to fix it. With the provocative title “The Score: IT-centric BI — 5, Information Worker — 0″, we intend to hit blog-themes such as the plight of the noble but beaten-down analyst, the misplaced emphasis on bulky technology solutions, and the false deification of the Executive Dashboard.We’d love to have you stop by on March 22 at 2:00 ET. Go here to register.

The session abstract is below:

Empowering the “Everyday Data” Analyst

Like it or not, we’ve all become “everyday data” analysts during the last decade. We became document specialists and spreadsheet experts ten years before that. We have standard tools for creating documents, spreadsheets, and presentations right on our desktops. These applications are familiar and easy to use — even if we only use them infrequently. Why don’t we have the same for working with data?

Everyone agrees that we have plenty of data—it streams through our departments and across our desktops everyday. But despite the big, IT-centric BI solutions that exist in our organizations, it’s the tools and skills for investigating and making sense of “everyday data” that we’re missing. The people who have the most to gain from data analysis are often the least capable of doing so. Where’s the BI equivalent of Word or Visio?

Join Zach Gemignani, co-founder of Juice Analytics for this free web seminar. Based on his years of experience with analytics client engagements, you will hear him present the real-world struggle of “everyday data” analysts. You will learn:

• How the IT-centric view of BI should change
• How do we empower our “everyday data” analysts in our organizations
• What shifts in approach and technology are necessary for effectively working with data

Scott Maxwell sums up 10 ways to lie with metrics. This is great advice for the political strivers and schemey backstabbers and a great antipattern for the readership of this blog. To summarize, here are his ten ways to lie when presenting data:

1. Only present metrics that are positive. That’s why you collect all those metrics.
2. Only present metrics that are easy to manage.
3. Use many metrics.
4. Be extremely precise with your numbers.
5. Present quickly, drown ’em with data.
6. Say “you don’t break down metrics” if they aren’t flattering to you.
7. Put lipstick on that pig—apply lots of gloss to your charts. Hello, Crystal XCelsius!
8. Show off your bona fides by sharing some metrics “off the cuff”.
9. Prep your team by feeding them lines.
10. Your job isn’t to educate your audience about your metrics. If people don’t know what you’re talking about, it’s because they’re stupid.

This is a great list, and it’s hard to avoid committing some of this sins from time-to-time. I think the best tool to improve your honesty when presenting numbers is to respect the intelligence and good judgment of your audience.

This isn’t easy; we all have people who can drive us crazy, who can derail a presentation with niggling questions or who ask for information they’ll never use.

There is no magic bullet when presenting numbers. Your job is not merely to show a few columns of numbers, but to teach your colleagues what those numbers mean.

[Editors note: Read the comments! David has some timely additions to this list.]