July 31, 2013

2001: Oh Boy

Five popular songs from 2001:
  • "Hanging By A Moment" - Lifehouse
  • "Fallin'" - Alicia Keys
  • "All For You" - Janet Jackson
  • "Drops of Jupiter" - Train
  • "I'm Real" - Jennifer Lopes featuring Ja Rule
New job - Vice President of Direct Marketing at Nordstrom Direct.  I have to fix my part of a $300,000,000 net sales business that was losing $30,000,000 a year.

By April 2001, merchandise productivity had dropped a whopping 45% from the previous year.  I was "Hanging By A Moment" ... the business was "Fallin'"!

There's no amount of magic that instantly fixes a 45% merchandise productivity decline ... other than by fixing the merchandise problem.

If you're an analytics/marketing person, you have to fix several problems at the same time.
  1. You have to describe, analytically and clearly, what is happening, and you have to provide a path to the future without alienating your Executive Team - especially your Chief Merchant.
  2. You have to have the very best people working for you, so that you can chart a path to the future.
  3. You have to keep the wheels on the bus today so that you get to the future.
In inherited 10 individuals in January 2001.  Individually, folks were fine.  As a team, performance was not acceptable.

Within six months, 8 of the 10 inherited team members were gone.  That made it really hard to keep the wheels on the bus.  And with only a handful of employees, I did not have the best people working for me - nobody capable of helping chart a path to the future.

So I focused on (1) above - describing what was happening.

This strategy put my career at risk.  Nobody wants to hear the following:
  1. Merchandise productivity is down 45% - it is "their" fault.
  2. Customers are shifting behavior online, and this has long-term implications for catalog marketing, and there's nothing we can do in the next three months to change this or adapt to it.
  3. Therefore, I toss my hands in the air - no solutions.
Then September 11 happened, and productivity sunk even further.

Pressure.

I did one thing right - I linked my future to a corporate "multi-channel" database being built by the Mothership.  This would pay enormous dividends from 2003 - 2007.

On Twitter, the Analytics Community take rolled-up newspapers, and swat Executives over the head for mass incompetence, as if they could immediately improve merchandise productivity by 50% while implementing space-age, untested technologies on the fly.

I quickly learned that, as a new Executive, everything is interconnected.  You can't always do what you want, the way you want to do it, without consequences.

For instance, we set up a lifetime value calculation at Nordstrom Direct - we would invest to a loss of $10 ... in other words, when we acquired a customer, we were willing to pay about thirty marketing dollars to acquire the customer, because thirty marketing dollars led to a $10 profit loss ... a loss that we'd more than make up for within twelve months, leading to a profitable twelve-month plan.

We had to do this to improve profitability ... the decision would eventually lead to $3,000,000 to $4,000,000 in annual profit.

Then we couldn't implement the strategy immediately.

See, to implement my idea, we'd have to cut way back on circulation - and because we had paid for paper ahead of time, we could not cut back as fast as we wanted to, costing us money.  And by cutting back, we lowered our demand forecast further, which required us to have to liquidate merchandise, which further hurt profitability in the short-term.  And when you cut back even further on sales, Management goes sideways!

In other words, I made decisions that, in the short-term, would made the business worse. So I had to compromise my strategy in the short-term, which perpetuated bad business, which angered Management.  

It's hard to sell a positive future when your boss sees that you're mucking up the present!

Oh boy.

Let's say that you are an analyst, early in your career.  Please understand that, yes, your Management team might act in a way that causes you to question capitalism.  Often, however, there are reasons for unusual behavior.  Find out what their goals are, ask how you can help support their goals, then do just that - support their goals!  Too many analysts want to rock the boat and implement new, whiz-bang ideas that make the analyst feel good.  Then leadership veto the idea, and the analysts thinks that Management is stupid.  Not true.  There are consequences for actions - learn what the consequences are.

And if you are a new Director / Vice President, try helping your team understand what you're up against.  Explain why you are doing what you are doing, explain what the short term pain/gain might be, and illustrate how your team will benefit in the long term.

As is popular to say these days ... in 2002, "it gets better".

Your Input Desired on Barnes & Noble

Dear Readers - give this little ditty some consideration (click here please).  I'll wait for you to finish.

Good, welcome back!

In the comments section, describe what you would do if you were CEO of Barnes and Noble. What would you do if you followed the omnichannel playbook (Nook) and your investments caused hundreds of millions in losses ... what would you do if the old-school multi-channel playbook of bricks-and-mortar may not be competitive with Amazon?  What would you do if, as the author says, you have 3 or 10 but certainly not 20 years left?  Or is the author nuts?

Please leave a comment - tell us what you would do if you were CEO.

July 30, 2013

2000: The Internet Bubble Pops - And So Does A Career!

Top songs from the year that proved that the world would not end after the dire predictions of Y2K pundits:
  • "Breathe" - Faith Hill
  • "Smooth" - Santana, featuring Rob Thomas
  • "Say My Name" - Destiny's Child
  • "I Wanna Know" - Joe
  • "Everything You Want" - Vertical Horizon
Remember, during 1998, I sandbagged the plan for 1999.  Sandbagging led to record profit during 1999.

Because we had an approximate 20% merchandise productivity hit between 1997 and 1998, it became terribly hard to acquire new customers.  Not surprisingly, when existing customers like your product 20% less than in the past, new customer growth will drop by 20% as well. Well, it will actually drop by more than 20%, because you cannot circulate as deep because horrific merchandise productivity leads to highly unprofitable new customer acquisition activities.

Well, Eddie Bauer was owned by Spiegel.  And Spiegel was owned by Otto Versand.  And Otto Versand was not happy with my customer acquisition plans.  So my Inventory Director and I had to travel to Chicago (along with our SVP of Marketing) ... and the two of us (Inventory Director and I) had to defend our customer acquisition plans.  Heck, one might ask, "why would the inventory director have to defend customer acquisition plans?"  Well, maybe somebody learned that the two of us sandbagged 1999 and wanted us to account for our actions!

Mind you, nobody from the merchandising team had to go defend the merchandise productivity that led to a lousy customer acquisition plan.

Predictably, I was informed that our customer acquisition strategies were flawed.  My fault.

In early 2000, with the online channel surging north of $100,000,000, our catalog productivity crumbled further ... customers were switching from catalog shopping to online shopping (yes, I know, the catalog drives online performance, in some cases).  So we were called into another meeting, this time with the Executives from Spiegel, our parent company.  They were terribly unhappy with our customer acquisition strategies as well.  That's when I presented the results of forecasts ... forecasts that suggested that e-commerce was going to be the future of the business, and that we needed to focus on online marketing strategies to have a chance to grow.

That presentation didn't go well, either.

Merchandise productivity impacts everything.  Lousy merchandising productivity puts pressure on those who are responsible for other areas of the business.  And channel shift is an important topic (ask e-commerce folks serving a 22-39 year old customer ... a customer that is now fleeing traditional e-commerce).

Sandbagging was still a good idea - but it led to a set of consequences where the perception was that merchandising problems were "fixed", when in reality, we just set a really low plan and then crushed it via excellent management of expenses.

At some point, you realize you've taken a process as far as you can take it.

It was time for a change.

By March 1, I was working at Avenue A, an online advertising startup in Downtown Seattle ... armed with $2,000,000 of paper stock that would vest in 1-4 years.  I was part of the "new economy"!  I would help "monetize eyeballs".

By June 1, my paper stock was worthless.

The internet bubble had popped.

My career trajectory had popped.

Spiegel would go bankrupt a few years later, taking Eddie Bauer down with it.

Careers have peaks and valleys.  By Thanksgiving 2000, my career was not in a valley, it was in a Gorge!

And then ... serendipity happened ... as it does with most careers.  An opportunity presented itself.  By January 1, 2001, I'd be the new Vice President of Direct Marketing at Nordstrom. I spent six years as an analyst ... I spent six years going from Manager to Director to Vice President.  Your career will evolve unpredictably, no doubt about it.

It was a new opportunity, of course, that came with increased accountability.

July 29, 2013

1999: Sandbagging

Five popular songs from 1999:
  • "Believe" - Cher.
  • "No Scrubs" - TLC.
  • "Angel of Mine" - Monica.
  • "Heartbreak Hotel" - Whitney Houston.
  • "Hit Me Baby One More Time" - Brittney Spears.
Let's talk about the most valuable asset in your forecasting toolkit - the sandbag.

In auto racing, sandbagging happens when you purposely qualify slower than you normally could, because you know that the race organizers will put some of the slower cars in the front of the field, giving you, a fast car, an advantage when the race starts.  You don't drive as fast as you can, so that you protect your starting position when the big race starts (big-league racing starts the fast cars up front, avoiding the problem of sandbagging ... but your local Saturday Night track ... they have sandbagging).

The prevailing best practice at Eddie Bauer, when planning performance for the next year, was to apply "add on factors" to the plan.  Remember, 1997 was awful, and 1998 was a catastrophe.  So when you were planning 1999, you were strongly encouraged to apply "add on factors".  We'd sit in Executive Meetings, and our CEO would challenge each division to improve performance.
  • "Merchandising - how much are you willing to step up to the plate and commit to for 1999?  5%?  10%?  12%?

The merchandising team, sitting there, terrified, would pick 10%.  There's no reason for this 10% lift, other than they had to hit it or risk being fired.  Then the creative team would sign up for 4%, and the marketing team (me) had to sign up for something ... so I'd blurt out something like 2%.

Just like that, next year's plan was going to be 16% better than performance in 1998.  This allowed us to mail deeper (because the profit and loss statement looked better, even though it wasn't any better in reality), allowing the top-line forecast to grow, allowing us to acquire more customers, allowing the business to appear healthy.

It was all complete nonsense.

The Inventory Director and I concocted a plan, behind the scenes.  We'd tell our bosses what we were doing, of course, but that's it.

We would sandbag the plan.

In other words, if the demand plan called for a 16% productivity improvement, we'd plan a 0% productivity improvement behind the scenes.

This served two purposes.
  1. We would not over-circulate catalogs.
  2. We would not over-plan growth of the internet.
  3. We would not over-buy merchandise that caused us to have to include clearance catalogs in the plan ... clearance catalogs that would destroy profitability.
Productivity did not increase by 16% in 1999.  It increased by something like 2% or 3%.

But the sandbagging allowed us to have the most profitable year in the history of the Catalog/Internet division at Eddie Bauer ... that's a history that spanned more than fifty years.

Mind you, this record level of profitability, enjoyed by all employees, could not have happened if we had not sandbagged the plan, behind the scenes.  Had we signed up for a 16% increase in productivity, we would have had a ton of clearance activity, and profit would have been a disaster, and we'd have all been fired.

Two people - working together, coordinating inventory buys and circulation strategies - that's all it took for a $600,000,000 division to achieve record profitability.

The experts on Twitter would tell you that your highly coordinated and sophisticated omnichannel strategy is the gateway to riches.  Just be omnichannel, and just be excellent!

In-the-trenches workers will tell you that not making glaring mistakes, coupled with teamwork, yields record performance.

Sandbagging - if you are responsible for forecasting sales, make sure you sandbag a bit. You have a responsibility to protect your company from over-aggressive forecasts.

July 28, 2013

1998: Clearing Merchandise

Five popular songs from 1998:
  • "Too Close" - Next
  • "The Boy Is Mine" - Brandy and Monica
  • "You're Still The One" - Shania Twain
  • "Truly Madly Deeply" - Savage Garden
  • "How Do I Live" - LeAnn Rimes
At Eddie Bauer in 1998, the popular theme was "clearance".

Business was awful.  Simply awful. Comparable customers were spending 10% to 20% less in 1998 than in 1997 ... that came on top of 10% drops in Fall/Holiday 1997.

I was the newly appointed Director of Catalog Circulation ... in 1998, before the internet took over, that was one of the five most important jobs in any catalog division.  I determined the catalog budget for the year (a budget of more than a hundred million dollars a year - and yes, there were plenty of cooks in the kitchen who would override my decisions, but you get the drift).  My team determined who would receive catalogs, who would receive discounts and promotions.  I got to decide (yes, again, many cooks in the kitchen) if we added or dropped catalogs from the annual contact strategy.  My team forecasted the sales of every catalog, every customer segment, every promotion, every merchandise category in each catalog.

Remember, I had no prior experience in this area.

Well, that's not true.  I worked on countless circulation projects at Lands' End, and was responsible for the models that determined who received catalogs.  But honestly, that was all support work ... no real accountability to speak of.

Now ... accountability.  There is an enormous gulf between most jobs, and jobs that have true accountability.  Always seek the latter.

So when the Inventory Executive stopped by my office on Day 2 and said "I need you to add a clearance catalog to the contact strategy, and I need you to mail enough customers and pages to clear about $10,000,000 of excess inventory, and I need you to not screw up the buying rhythm of our full price customer base", I got that cold, clammy feeling that can only be experienced when enjoying the reality of true accountability.

I started where any analytics expert would start.  "Do we have any cannibalization tests, A/B tests designed to measure what happens when we add a clearance catalog?"  Heck, we had dozens of these tests at Lands' End.

"No, we don't execute tests like that at Eddie Bauer, we don't want to lose demand."

Oh.

So we had to add a clearance catalog in Spring, sandwiched between two existing catalogs. My job is to make this work for all parties involved.

I had to craft a scenario that looked something like this:


We were never going to hit the original plan - business was off by 20%, and would continue to be off for another year.  So I had to show what the plan looked like when down 20% to plan (that's the middle column).  As you can see, profit dropped from $4.4 million to $3.5 million just because business stunk ... and we'd lose about $9,000,000 in demand ... hence the reason for having to clear $10,000,000 via a clearance catalog (with 20% off and free shipping and discounted prices ... a modern wonderland).

In the Clearance Scenario, I pulled 10% of the demand out of the February and March catalogs, because some customers would eschew those full-price mailings to instead shop in the Clearance catalog.  Then I forecast a whopping $10,000,000 in the Clearance catalog.

You run the profit and loss statement ... and then you get a sick feeling in your stomach.

See, you had no choice ... you had to clear the merchandise that wasn't going to sell, merchandise that was overbought.  You can't just let it sit there ... well, I suppose you could burn it, but then you're losing an incremental $5,000,000 instead of the $2,100,000 profit hit the clearance book would cause.

Here's a little hint, folks.  CFOs do not like situations where you add $3,000,000 in ad cost and you lower profitability by $2,100,000.  They really, really, really don't like those situations.  No amount of pithy advice from the experts on Twitter ("a social brand is a successful brand" ... "don't own your own product, avoid proprietary products") can help deal with having to clear $10,000,000 of merchandise in the next 1-2 months.

But that's the reality of a business in free fall.

And after having the Executive team yell at you about how rotten business is and how rotten your clearance plan is, you get busy trying to fix 1999 while burying the carcass of a 1998 that had just started.

That's my advice to you, dear e-commerce mavens operating in a modern world.  You have to do two things at once.  You have to deal with the reality of your current year, and at the same time, you have to make sure that next year is going to exceed expectations.  Online, the same things happen that happened in the old-school catalog world ... when you ramp up your clearance section, your full price section takes a hit.  Plan this accurately, get through the pain of clearing out the junk, and move on to planning the next year.

July 25, 2013

1997: Career Inflection Point

Five popular songs from 1997:
  • "Candle in the Wind" - Elton John
  • "Foolish Games" - Jewel
  • "I'll Be Missing You" - Puff Daddy & Faith Evans
  • "Un-Break My Heart" - Toni Braxton
  • "Can't Nobody Hold Me Down" - Puff Daddy
Let's skip methodology for a day, and talk about the inflection points that impact a career.

It's been my experience that a series of circumstances arise, at a point in time ... and if you capitalize on the circumstances at that specific point in time, your career moves in a positive direction.

Here's the org structure at Eddie Bauer, in January 1997.
  • CEO
  • EVP of Global Brand Development, and a President of Catalog reporting to the CEO ... 2 important individuals, no doubt.
  • SVP of Marketing reporting to the EVP of Global Brand Development.
  • DVP of Research, DVP of Retail Marketing, Director of Catalog Circulation reporting to the SVP of Marketing.
  • Then me ... Manager of Analytical Services.
That's when a series of circumstances presented themselves to me, the humble little Manager of Analytical Services at a $1.5 billion dollar apparel monster.

Event:  In late January 1997, the DVP of Retail Marketing was fired (or so claimed the prevailing gossip of the time ... and here's a tip, and I know it is hard ... try to stay above the gossip, folks).

Event:  In February 1997, during my performance review, I told my boss that I wanted to become the next Director of Catalog Circulation.  To this day, I have no idea why I put this down on paper.  It wasn't the logical career path for somebody like me ... in fact, the logical career path was to move to the vendor side of the industry.  The current Director of Catalog Circulation was generally well liked, knowledgeable beyond reason, and certainly not going anywhere.  So maybe I didn't think there was a risk involved in proposing my future career path.

Event:  In December 1997, the incumbent Director of Catalog Circulation decided to scale back work hours.

Event:  In December 1997, I was named the next Director of Catalog Circulation.  Sixteen perfectly qualified catalog circulation experts were passed over, some with excellent training and comparable career goals.

Event:  In January 1998, the President of Catalog either quit or was fired.

Event:  In January 1998, a team of six folks, called the "Catalog Business Team", was put in place to fix catalog performance, replacing the President of Catalog.  This team had a matrixed org structure, reporting to the CEO and individual department heads.

In other words, in twelve months, I went from being a lowly Analytics Manager at a $1.5 billion dollar business to having a matrixed org relationship with the CEO of a $1.5 billion dollar business.  Accountability was about to become the theme of 1998 ... real accountability ... it was no longer acceptable to call out problems, I had to actually DO something about problems!

Three years later, I'd be Vice President of Direct Marketing at Nordstrom, a $7 billion dollar retail giant.  In just 36 months, I went from being a lowly Analytics Manager to a Vice President.

There are a handful of inflection points in any career.  You have to sense when a career inflection point presents itself, and you have to RUN through the door when it is opened.

And you have to be really, really LUCKY ... I was lucky.  Luck plays an enormous role, folks. Career paths are like a tournament bracket ... too few championship spots for too many people.  Take advantage of luck / serendipity ... be ready when it graces you.

July 24, 2013

1996: Matched Market Testing of TV Ads

Here's five popular songs from 1996:
  • "Macarena", by Los Del Rio.
  • "One Sweet Day", by Mariah Carey.
  • "Because You Loved Me", by Celine Dion.
  • "Nobody Knows", by Tony Rich Project.
  • "Always Be My Baby", by Mariah Carey.
While listening to those songs in 1996 at Eddie Bauer, I analyzed the performance of Television Ads.  Here's a ad from 1999, just so you can get a hint of the theme of the content (click here please).

Somehow, a little analytics manager like me recommended a matched market test.  We'd air the commercials in Seattle, but not Portland ... Salt Lake City, but not Boise ... Los Angeles, but not San Francisco ... Phoenix, but not San Diego.

After a half year of commercials, we ran the numbers.  The commercials were responsible for something like a 4% increase in comp store sales.  But the profit and loss statement didn't look too good.


In other words, we had a 100% ad to sales ratio ... and we needed to see a 30% ad to sales ratio to generate profit.

This analysis drew criticism from all fronts.
  • Finance said I was overestimating the performance of the TV ads, that I couldn't possibly, with any precision, used matched market testing to show that we even generated $15,000,000.
  • Creative / Branding said that I couldn't possibly, with any precision, understand the long-term branding impact of the commercials - they said I was only measuring the short-term impact, which, in their minds, was completely meaningless.
This was the first time I employed what I call the "Switzerland Approach".  In other words, I chose to be neutral.  No attachment to the commercials, zero!  I didn't care if the commercials worked or did not work, I only cared in the profit number at the bottom of the profit and loss statement.

After a year of using the "Switzerland Approach", I was overwhelmed with "business". Everybody wanted to learn something about customer behavior, because the outcomes I sold were neutral, and without emotion.

That's the lesson of this blog post (and the 1993 - 1996 timeframe in general).  Try to be Switzerland.  Let the customer do the talking!  Sell the message, not the ideology.

July 23, 2013

1995: The Grass Isn't Always Greener

Five popular songs in 1995 include:
  • "Gansta's Paradise" - Coolio
  • "Waterfalls" - TLC
  • "Creep" - TLC
  • "Kiss From A Rose" - Seal
  • "On Bended Knee" - Boyz II Men
Nice run from Boyz II Men, huh?

Imagine, for a moment.  In late 1994, you're sitting in a board room, sharing customer data with Executives, data that shows the company is between five and ten million dollars less profitable than everybody perceives it to be.  You're using high-speed mainframe computers to do your analysis, and you are actually using a personal computer (pretty forward for 1994, folks) to create Powerpoint-style presentations.  You have seven years of customer history at your disposal.  Using a combination of SPSS and Easytrieve Plus, you can analyzing anything you want.  You can answer any question you want to answer.  You're a manager, with your own office with a door.  You've re-built a new department, and now supervise a team of eight individuals, up from one at the start of the year.

But the work you're doing isn't fun, anymore.  You took sides in 1994, and now you don't get to analyze half the business in 1995.

It was time to move on.

I blew the whole thing up and move west, to a major competitor - Eddie Bauer.  Eddie Bauer was a company 50% bigger than Lands' End.  300+ US-based stores.  An internet business that, in 1995, was generating about five orders a day, which was industry-leading at the time!

Armed with a healthy pay raise, I arrived for my first day at Eddie Bauer, in late 1995.

I was given a desk in the hallway.

There was no customer database in-house.  Spiegel, the parent company, held three years of Eddie Bauer customer data, data that could only be accessed with in-depth knowledge of COBOL.

Yes.  COBOL.  The ancient language that was nearly responsible for the collapse of society in 1999 (Y2K).

Remember a few days ago when I implored you to learn coding skills?

I spent the next two weeks learning COBOL.  And wondering if I made a big mistake in changing jobs.

I spent the two weeks after that getting the OKs necessary to buy a copy of SAS, answering questions like "why do you need software that costs $2,000 - we already have a customer report called Vital Signs?"

Four weeks later, I was compiling COBOL programs.  Soon, I'd be learning things about customer behavior that Vital Signs was unable to reveal.

I'll say this again.  Learn how to write code.  It's the most important skill an aspiring analyst can possess.

July 22, 2013

1994: Testing And Consequences

Here's five popular songs from 1994 ... enjoy 'em all!
  • "The Sign" - Ace of Base
  • "I Swear" - All 4 One
  • "I'll Make Love To You" - Boyz II Men
  • "The Power Of Love" - Celine Dion
  • "Hero" - Mariah Carey
Recall the big 2^7 factorial test we designed at Lands' End in 1993?  Well, after twelve months, the test yielded fascinating results.  More important, however, would be the process to learn how to communicate the results.

You may have noticed ... sometimes, I can have a sharp tongue.  My boss noticed this, way back in 1994, and decided to enroll me in Dale Carnegie training.  Folks, this is about the best class you can take.  I learned how to sell ... not vacuum cleaners, but how to sell data.

Armed with this new knowledge, the knowledge of how to sell, I put together a presentation with the findings of the test.  I knew that a team of Executives were meeting on October 21, so I scheduled a meeting to discuss the findings with my department heads on October 20 (coincidence ... I think not ... that was part of Dale Carnegie training).

With the exception of the Kids business, every business unit tested generated between 50% and 75% incremental sales, based on the outcome of the year-long holdout test.  In other words, if you stopped mailing catalogs in that business unit, between 25% and 50% of the sales would still happen ... between 50% and 75% of the sales would disappear.

On the surface, that sounds like a good thing ... 50% to 76% of the sales were actually caused by catalogs.

But then you ask your finance friends to run a profit and loss statement for you.

Oh oh.

The outcome was very similar to the profit and loss statement at the start of this post.  When 65% of the sales are incremental, it means that you're not running a 10% pre-tax profit business ... you're actually running an UNPROFITABLE business!!

Well, the presentation went well - my department head decided that the Executive Team should see the results of the test - and they were, coincidentally, meeting the very next day!

Here's a little hint for you testing advocates out there who think the secret to success in life is in testing everything under the sun and then sharing the results with Execs who will quickly and nimbly change course based on the genius of your findings ... GMs who earn $125,000 annual bonuses for generating 10% pre-tax profit do not like Managers (I was promoted from Analyst to Manager in 1994) who demonstrate that they are actually costing the company a fortune ... regardless how well you communicate results.

Repeat:  GMs who earn $125,000 annual bonuses for generating 10% pre-tax profit do not like Managers who demonstrate that they are actually costing the company a fortune ... regardless how well you communicate results.

The most spirited meeting I have ever been in happened in 1994 - my job was to share the profit and loss statement for each business - pre-incremental sales and post-incremental sales.  The room divided in half - you were either on the side of incremental sales, or you were on the side of finance reporting.

Now, I have no idea what happened behind the scenes in the five weeks after this meeting was held.

But within five weeks, the CEO, an advocate of the findings of the test, was fired.  He was replaced by the GM of one of the business units that was, after measuring incremental sales, actually unprofitable.  Within nine weeks, I would be re-org'd out of my new Manager job, I'd lose my staff, and I'd have half of my responsibilities taken away.  I'd also report to a new Director, a person who had no marketing experience whatsoever (yes, companies promote people with no experience ... wait until I get to my summary of the year that was 1998).

What did I learn?

Never - ever - ever - take a passionate, partisan side.  Business is not Fox News or MSNBC, though too often, we treat it that way. See, I moved all-in on the side of incremental sales, alienating half of the company in the process.  I should have moved all-in on explaining customer behavior.  

I sided with ideology.

Don't side with ideology.

Side with customer behavior.

Make sure that what you learn about the customer is separate from what you believe your company should do.

July 21, 2013

1993: Testing As A Strategic Weapon

Five popular songs from 1993:
  • "I Will Always Love You" - Whitney Houston
  • "Whoomp, There It Is" - Tag Team
  • "I Can Help Falling In Love With You" - UB40
  • "That's The Way Love Goes" - Janet Jackson
  • "Freak Me" - Silk
I'd guess this happens at your business as well as at Lands' End, way back in 1993.  You have a merchandising team that must increase sales, or they get fired.  Yup, merchants have a fun job, with much more pressure than the average employee. 

So your merchandising team introduces a new product line.  And the numbers look great. Woo-hoo!

Except for one little problem.

The merchants responsible for the existing product lines are experiencing flat sales, or are experiencing sales declines.  Well, this can't be their fault, can it?

At Lands' End, there were two camps in 1993:
  • Camp #1 = The core business was the engine behind the entire company, without it, everything fails.  New business units were stealing demand from the core business.
  • Camp #2 = New business units were the growth engine of the company, without them, the business would experience flat or declining sales.
Here's a little hint - it is very tough to use existing data to prove that camp #1 or camp #2 is right. You need a test.

Why set up a test?  Well, we had all of these bizarre, circular arguments.  For instance, a customer might purchase from the core catalog in January, then purchase from a Home catalog in October.  The core business folks would argue that the October order cannibalized a core business order - the Home team (Home merchandise, pillows, comforters) would argue that without the October Home order, the customer would lapse and become unproductive.  The arguments would simply swirl around, without resolution - and no amount of data pro/con would change any viewpoint.  It was almost like a religion - folks had faith - and you couldn't use facts to change faith.  You needed a test.

What did we design, at Lands' End, to answer this question?
  • Step 1 = Every customer number ending in "3" would be included in our test.
  • Step 2 = We randomly created 1/0 flags ... for each business unit.  If the customer received a "1", the customer could be mailed catalogs if eligible.  If a customer received a "0", the customer would be suppressed from receiving catalogs from that business unit for the next twelve months.
Yes ... twelve months.

Almost nobody has the courage to execute a test of this magnitude.  Would you have the courage to not send an email to a customer for a year, to prove that email marketing truly worked?

Almost everybody should have the courage to execute a test of this magnitude.  How else are you going to accurately measure the impact of a business unit without withholding the business unit from customers?

Testing is a strategic weapon.  Stop testing nonsense (i.e. large orange button vs. small green button ... or 30% off plus free shipping vs. free shipping plus 30% off).  Test something that actually matters to your business!  In 1993 at Lands' End, we implemented a year-long test.

And I've got a feeling that, in 1994, what we learned would cause problems!

July 19, 2013

New Channel: Clarity.fm

We're going to try something new for a few months.

If you're not interested in a $16,000, month-long analytics project, but would instead like to spend $200 for a half-hour of ad-hoc consulting, why not give Clarity.fm a try?

Here's my presence on Clarity.fm ... https://clarity.fm/#/minethatdata.

You arrange a call, I take the call, and we go from there.

I know, I know, many of you will say "well, I can just pick up the phone and call you, so why wouldn't I do that?"  You can, do that if you like!

But if you like a different approach, and based on the feedback out on Twitter, there's a segment of the population that likes this approach, give Clarity.fm a try. https://clarity.fm/#/minethatdata

July 17, 2013

1992: Returns Matter

Here's five popular songs from 1992:

  • "I Will Always Love You" - Whitney Houston
  • "Smells Like Teen Spirit" - Nirvanna
  • "End of the Road" - Boyz II Men
  • "Rhythm is a Dancer" - Snap!
  • "To Be With You" - Mr. Big
Returns kill e-commerce, catalog, and retail brands.  Imagine working at Zappos, where +/- a third of all shoes are returned!?  That's a big number.

A big, fat, unprofitable number.

Returns hurt us at Lands' End, back in 1992.  My boss, and my Director, wanted me to do something about it.

What can a lowly statistical analyst do about it?

Simple.

Do not market to customers who return A LOT of merchandise!

How?

The Hyperbolic Tangent Function (click here, geeky followers)!

Now, you never, EVER, share the details of the math you use with folks at a Director level and above.  It's just not good practice.

But the geeky math makes all the difference in the world.

To over-simply the issue, the math suggested that customers who return at least 67% of their merchandise over at least three purchases should not be mailed catalogs.  Why?  Well, these customers were predicted to have at least a 50% future return rate, making all of their future purchases unprofitable.

You are not under any obligation to mail customers who, or will be, unprofitable.

This yielded another $700,000 in incremental, annual profit ... on top of the $1,000,000 in incremental, annual profit generated by the statistical models that I used to select customers for catalog mailings.

Yes, my work was starting to be noticed.  In a company of 5,000 employees, I was responsible for $1,700,000 of annual profit - greatly overshadowing the $29,600 annual salary I was being paid (about $50,000 in current dollars).

All analysts, early in a career, must find ways to get noticed.  3-D color contour plots make a difference.  Profit makes a much bigger difference.

If you work for a catalog brand, e-commerce brand, or retail brand, you are under NO OBLIGATION to send catalogs or email campaigns to customers who return a lot of merchandise.  Why would you purposely cause your company to be less profitable?

I'm waiting for your answer ...

Stop emailing customers who return the majority of the merchandise they purchase.  Quantify the impact on annual profit.  Your career, and the profitability of your company, depends upon you making smart decisions.

July 16, 2013

1991: Statistical Models

Songs that were popular in 1991:

  • "Everything I Do" - Bryan Adams
  • "Black or White" - Michael Jackson
  • "Joyride" - Roxette (we're seeing a lot of Roxette, don't you think?  I bet that ends, soon.)
  • "Wind of Change" - Scorpions
  • "Losing My Religion" - REM
One of the great illusions of "statistical modeling", or as it is popularly known today as "Big Data", is that most techniques, regardless how different they are, do the exact same thing.

If you work at a large company, like Lands' End, statistical modeling means everything.  I created a model in 1991 that increased the productivity of catalogs by about 1%.  This increase resulted in a million dollars of incremental profit - generated by me, a lowly statistical analyst known for producing 3-D contour plots.

You get noticed as a 25 year old analyst when you produce a million dollars of profit all on your own.

But the attention isn't deserved, honestly.

Here's the thing.  If a model is built responsibly, then 97% of the names of responsibly built model #1 will be the same as the names of responsibly built model #2.

So when your vendor has a "Big Data" solution for you - please keep in mind that 97% of the names are going to be identical to the names selected by your current methodology.

Identical.

The argument, then, is about the effectiveness of the 3% of names that are different.

At Lands' End, in 1991, I picked names, 3% different than the names previously selected, names that were fundamentally better.  This was a crucial step in earning credibility among Management.

If you work for a large company, this opportunity exists for each and every one of you - those working for catalog marketers, those working for email marketers, those working in the retargeting industry.  Take advantage of the opportunity presented to you!

July 15, 2013

1990: Heat Map Derivation

Five popular songs from 1990:
  • "Nothing Compares 2 U" - Sinead O'Connor
  • "Vogue" - Madonna
  • "Ice Ice Baby" - Vanilla Ice
  • "U Can't Touch This" - MC Hammer
  • "It Must Have Been Love" - Roxette
Back in 1990, you didn't have a tool like Crazy Egg to help you visualize things.  You had to write code.

Yes, I know.  Technology makes things easier for folks, giving more people access to information.  It's all good.  I get it.  But this is my blog, and I have a point to make!

There is something critically important about being able to write code.  You are empowered to produce elegant work when you write code ... you are forced to do utilitarian (still highly important) work when you don't write code.

In 1990, I worked with several analytics co-workers.

Each and every one of my co-workers were smarter, more talented, and more recognized than I was.

It is not good to be at the bottom of the analyst ladder.

So I had to do something different.  I had to do something to get noticed.

I decided to write code - I created a 3-D color contour plot (color was rare in 1990, FYI) using an HP7475a plotter.  The map illustrated corn or sorghum hybrid yields in, say, Iowa, via color, in 3-D format --- it looked a little something like this:


Instead of the graph looking like this - imagine state boundaries instead of the N/S and E/W axis on this graph.  Make sense?  I know, it's geeky.

This graph got attention.  In fact, I was able to submit to the 1990 SUGI conference in Nashville, and present the methodology as a poster.

Click below to see the actual paper/poster and associated SAS code (which should still work, FYI). http://www.sascommunity.org/sugi/SUGI90/Sugi-90-195%20Hillstrom.pdf

When I applied for a job at Lands' End, in late September 1990, I provided a copy of the code, and a sample graph ... "Number of Junebugs Killed Daily on Wisconsin Highways".  Though the folks at Lands' End had already chosen a candidate for a Statistical Analyst position, the graph got their attention ... enabling me to earn the opportunity to be hired at Lands' End.

If I don't take the initiative and write the code, I don't get invited to present the poster at SUGI 1990.  And if I don't get invited to present the poster at SUGI 1990, I don't get hired by Lands' End.  And if I don't get hired by the good folks at Lands' End, I don't get the opportunity to share information with you.

It is SOOOOO important to possess the skills to write just a little bit of code.  So many analysts - maybe more than half these days, are web analysts who are not required to write code.  This means that so many of today's analysts can only do what software developers want the analyst to do.

My entire career was launched by the ability to write code that created a 3-D contour plot.

Learn to write code.  Your future career path depends upon it.

July 14, 2013

1989: Identifying Interesting Opportunities

Popular songs in 1989 include:

  • "Like A Prayer - Madonna".
  • "Eternal Flame - Bangles".
  • "Another Day In Paradise - Phil Collins".
  • "The Look - Roxette".
  • "Love Shack - B52s".
We did some interesting things at the Garst Seed Company.

If I remember this correctly, one of our researchers wanted hybrids that yielded well, and dried down quickly.  The hybrid could be harvested faster than normal, helping the farmer achieve high yields when the growing season was shortened by bad weather.

The analysis was quite simple - but elegant - fit a line through a relationship between yield and days to dry down.  Any hybrid that was "below the line" in the graph above and had a high yield (> 120 bushels per acre) was a hybrid that would be "fast tracked".  The researcher wrote a paper, and invented a simple but effective methodology, and I got to do the actual work for the researcher.  All in all, it was a lot of fun!

You can have fun, too.

In e-commerce, the methodology above works for analyzing conversion rates.  Plot conversion rates on the x-axis, plot profit per conversion on the y-axis.  You want to explore scenarios where you have high conversion rates and high profit per conversion.

So much of what we're doing in 2013 is not new - it's a derivation of stuff done long ago, applied to a modern situation.  Borrow what has been done, twist it to apply to modern situations, and identify and interesting opportunity!

July 10, 2013

1988: Deer Romping

Top Selling Song of 1988 = Faith, by George Michael.

Ya gotta have faith!

Sometimes, however, it was hard to have faith in the data.

In the autumn of 1988, at the Garst Seed Company, we were analyzing the annual "harvest". Each research plot was harvested, yields were recorded, and data was sent to a twenty-three year old analyst named Kevin Hillstrom.

Research plots were in grids.  I analyzed each cell in the grid - a cell represented a corn or sorghum hybrid, the number represented the yield of the hybrid.

Look in the top half of the table.  See the red numbers?  Those "yields" don't look right, do they?

Turns out that a deer "romped" through those plots, ruining the experiment.  Yields are 70% too low!

These experiments were expensive to conduct, and took six months from planting to harvest to complete.  You couldn't just say that the experiment was wasted, you had to do something with the data.

We used a method called "GLM", or "Generalized Linear Models" ... to correct for cases where deer romped through and destroyed our experiment.  By adjusting for the rows and columns in the field (and by planting a second or third "rep" ... an identical but re-randomized test), we could predict (values in blue above) what "should" have happened.

This allowed us to save the company a fortune ... we used good data to predict what should have happened.

These days, you go out on Twitter, and you'd swear that folks just invented A/B tests.  Well, the good folks at Kansas State and Iowa State University were executing and analyzing randomized plots, using GLM to adjust for outliers ... as far back as the 1940s ... which means these methods were being used long before that!

We have the same problems today in e-commerce ... how do you measure conversion rate when the email marketing team adds/removes campaigns from the schedule?  Or how do you measure conversion rate when you toss a bunch of sloppy brand advertising on the home page, foregoing revenue generated by top-selling items that were previously sold on the home page?

You use this procedure, this "GLM" procedure, to predict "what should have happened".  Heck, you don't even have to get that fancy ... just eyeball the results, it's better than using sloppy, bad data, isn't it?

July 09, 2013

25 Years

There should be some kind of award for being gainfully employed for the past twenty five years.

But there isn't.  Instead, you get to read another in a long line of blog posts.

After graduating from the University of Wisconsin with a BS in Statistics, I started my first day of work at the Garst Seed Company, in Slater, Iowa, on July 15, 1988.  Next week, it's the twenty-five year anniversary of the magical moment when I put down the Des Moines Register, entered the corporate campus of the Garst Seed Company, and emerged nine hours later with a 1,200 page SAS manual in hand.

In the next seven weeks, we'll explore marketing and analytical topics from 1988 to 2013.  All examples will be tied to current issues, so no need to fret about blog posts focusing on the best ways to avoid SB37 errors in JCL code on a mainframe computer.

July 08, 2013

Barnes & Noble

Multichannel / Omnichannel experts tout the "bricks 'n clicks" advantage.

But then we read about Barnes & Noble (click here for a link to an article about losses in the Nook Division - losses offsetting in-store profit).

Let's think about this for a moment.

  • Experts say Omnichannel / Multichannel > Single Channel.
  • B&N will reduce stores by a third in upcoming years.
  • B&N will pull back on digital tablets.
  • B&N has every advantage over Amazon, according to omnichannel experts.
  • Amazon is not pulling back, are they?
At some point, we have to concede that the whole multichannel / omnichannel thing is designed to generate page views, to sell vendor solutions, to sell research reports, and to generate Management Consulting engagements.

Do what is right for your business, not what is right for somebody to generate more page views.

July 07, 2013

Dear Catalog CEOs: A Business Bubbling Under The Core Business

Dear Catalog CEOs:

Here's an interesting quote ... I heard it recently from one of your peers.  I had not heard a true catalog executive offer this previously.  It marks a shift in thinking.
  • "We were told we had to align all of our channels.  Yet last week, we're looking at merchandise reporting, and we can see the proof in the pudding.  We have online items that are fundamentally different than our core catalog items.  They sell reasonably well, and with minimal ad cost, they're very profitable.  But more important, this tells me that we're serving different customers.  We can no longer think about the catalog as the center of the ecosystem.  We have different customers.  Older customers and younger customers.  We need to meet all of their needs.  The catalog can't accomplish our goals anymore.  This will disrupt our entire organization, how we do things."
I'm going to stop right there.  Take a moment, and let the paragraph sink in.  I'll be back in a moment.

...

...

...

I'm back.

This was one of your peers, not me, saying this.

It may just be that you have a new business, bubbling under the surface of your core business.  If you look at the data the right way, you'll see this.  The future is staring you right in the face.

Now that you are back from a weekend of enjoying fireworks, spend a little time thinking about the quote, thinking about what it means for your organization.

July 02, 2013

July 4

I'll be back on July 8 with scintillating facts that have the potential to revolutionize your business.

Until then, take a break, and celebrate the outcome of the Revolutionary War ... explode a few devices (safely, of course).  Spend a day at the beach.  Grill brat patties over an open flame.  Enjoy a cold drink.

Or experience a summer sunset.  Your choice!


July 01, 2013

Two Items

You have two items:
  • Item #1 was promoted in your catalog, generating $10,000 in demand and $1,000 profit.  Not bad!
  • Item #2 was not featured in your catalog.  It generated $3,500 in demand and $1,700 profit.
Which item do you prefer?

Most of you prefer item #1, don't you?

"It sold more!".

"We captured market share!".

"Businesses grow or they die."

There are reasons for favoring item #1.  At a $25 price point, it means you sold 400 units, most likely to about 350 customers.  For item #2, you most likely sold 140 units to maybe 125 customers.  Item #1 gives you what I call "file power".  I'm a big advocate of file power.  I'll take an incremental customer over an incremental dollar of net sales any day of the week.  In this case, you get both - incremental customers and incremental sales.  Incremental customers are good, because they pay us back in the next 1-3 years.  Ask Amazon how they feel about incremental customers.

There are reasons for favoring item #2.  Two big reasons.  First, you didn't have to spend ad dollars to generate the sales.  Sales that are generated by brand loyalty are more valuable than sales generated by advertising.  You get to save the ad dollars, and possibly do something else with them that will generate sales.  Second, you generated more profit.  Now, I get it, nobody looks at profit anymore.  It's only the most important metric in your whole business, it's the metric that allows us to earn a salary.  Without profit (or cash), you're sunk.  This item generates more profit/cash than the first item.  Therefore, in many ways, it is more valuable.  The incremental profit increase allows us to invest in advertising, buildings, new businesses, new items, salary increases, bonuses, you name it.  Business leaders that prefer item #2 and reinvest profit/cash in new activities tend to find a path to the future faster than those who are cash strapped due to a 30% ad-to-sales ratio.

Each item possesses strengths.

Which strength do you favor?

The strength you favor says a lot about the type of business you desire to create.

Items That Appear In Multi-Item Orders

In a typical Life Stage Analysis within a Merchandise Dynamics project, it is common to see exaggerated trends when comparing first-time buy...