November 30, 2010

Hashtag Analytics: Part 5 = All We Need Is Love

In prior posts, we learned that #blogchat participants who only participated in one of the previous four weeks had low "engagement rates" (engagement = probability of participating in the following week):

We can mine the information, and see if there are participants who will engage again!

Let's look at re-engagement rates among those with only one week of participation, by number of tweets:
Ok, now we're getting somewhere!  Engagement rates go sky-high if the person tweets at least two or more messages.

But what about those folks who only tweet one time?  Is there anything within that audience that can be mined?

I want you to look at the line that says "re-tweet".

If the person issues one tweet, and only participates once over a four week stretch, and that one tweet is a "re-tweet" of information tweeted by somebody else, then the person has a very low engagement rate.  And that is a sad thing, because the person who issued the original tweet benefits from having a first-time user re-tweet his/her message.

But the person issuing the re-tweet?  They are the least likely to re-engage.

Except for one little thing!

Look at the last two lines in the table ... here, I split the re-tweet line into those who were "acknowledged" for the re-tweet, and those who weren't?

What do you see?

If the person was acknowledged, the person has a 62% chance of re-engaging.

If the person was not acknowledged, the person has a 6% change of re-engaging.

What a finding!

If you are participating in #blogchat, and you are lucky enough to have somebody re-tweet your message, and you find out that you don't know who this person is, then do something simple.
  • Thank the person for re-tweeting your message!
The data strongly suggests that a simple act of kindness dramatically increases engagement rates among first-time participants.

That's an important finding!

Dear Catalog CEOs: Groupon / Google / Co-Ops / List Rental

First of all, if Google gets Groupon for $5 billion or $6 billion, I'd offer kudos to Groupon.  They are the smartest marketers in the room, you cannot deny that. 

Talk about monetization.  At 13,000,000 subscribers and a $6 billion dollar sale price, you're looking at $461 per e-mail address.  You are able to milk your e-mail subscriber list for, what, $0.15 per e-mail message, at 100 message per year, $15 per year, total?

Talk about monetization.  How does a start-up convince established businesses to give a $50 item to the customer for $25, and then convince the established business to give half of what's left (though I'm told that big brands cut better deals than this) to Groupon for access to their list of discount-craving fans?  How does a start-up convince an established business to accept $12.50 instead of $50.00?

Do you ever think about this?


Let's pretend that you, the Catalog CEO, took this idea to Abacus, or Experian, or Millard, or ALC, Merit Direct, Belardi/Ostroy, or any other catalog vendor.  Let's pretend that you told them to start a new division ... one where they recruit e-mail addresses, then they partner with catalog brands to offer fabulous discounts and promotions that are made available only to those on the e-mail list.

What would Executive leadership at Abacus, Experian, Millard, ALC, Merit Direct, Belardi/Ostroy, or any other catalog vendor say to you?

"You're nuts."

"E-mail addresses don't work as well as a physical name/address, we all know that."

"Who in their right mind would go for that type of revenue split when we sell you viable names for just $0.06 or $0.13 each?"

"We've got this new model for business names where the second name at a business works 14% better than a new name at a new business, and you can take that to the bank!"

"Your target customer won't sign up for those type of e-mail promotions, she wants a physical catalog in the mail."

"We tried e-mail list building back in 2001 and it didn't work."

And that would be that.

We need some encouragement!


Abacus/Experian/Millard/ALC/Merit Direct/Belardi-Ostroy/Other Co-Ops ... you are list organizations, right?  You work with my Catalog CEO clients, you sell them access to your lists, right?

Groupon sells my Catalog CEO clients access to their list, right?


So how is Groupon any different than you? They are your number one competitor, they are you!  They figured out a different way to monetize a list, to the tune of a potential sale price of $6,000,000,000.


Abacus/Experian/Millard/ALC/Merit Direct/Belardi-Ostroy/Other Co-Ops, would Google buy your business for $6,000,000,000?

Remember, Groupon does the same thing you do, they sell access to a list.

In other words, the key to success is out there, just waiting to be implemented.  Any one of our catalog vendors could have attempted the Groupon model before Groupon attempted it, and would have had an enormous head start, having already built a list of a hundred million names and addresses.  And the idea is completely congruent with the mission of a list rental organization like Millard, or a co-op like Abacus ... it's the same thing, with a different monetization structure.


This brings me to you, the Catalog CEO.  The future is out there, just waiting for us to capitalize on it.  All of the good ideas are out there already.  We have the ability to make magical things happen.  Our ability to make magical things happen decreases when we look within the same box of toys for our answers.  We have to be willing to take risks, measured risks.  Sometimes, we have to be willing to set aside our pre-conceived notions of "what will work".  Sometimes, we have to trust the 29 year old marketing analyst, giving her a chance to implement something that we strongly believe won't work.  When her idea doesn't work, we mentor her with compassion.  When her idea does work, we give her more responsibility.

Do not let some rogue startup take something that you invented, put a modern twist on it, monetize it differently, then run you out of business with a mashup of your business model and their idea.

November 29, 2010

Hashtag Analytics: Part 4 = One Week

We continue our analysis of the #blogchat community by looking at a segmentation scheme that includes recency (weeks since last participation) and weeks (number of weeks participated during past four weeks).

Last week, we looked at "Mega Participants", those with recency = 1 and weeks > 2.  Their engagement rate (probability of participating next week) was about 70%.


Now take a look at every row in the table where users only participated in one week.

What do you see?


Well, you see low engagement rates, don't you?

In other words, if the participant participates in only one week, regardless of recency, that person has a low chance of participating in the following week.


So that's not a good thing (though #blogchat data is so directionally similar to what classic direct marketers see in their RFM analytics that it is frightening).

What would any good direct marketer do when faced with an unresponsive audience?


Yup, that's right, they'd mine the data for the subset of participants who do want to participate again.

So we'll do that tomorrow!

November 28, 2010

The Perfect Gift For Cyber Monday: Hillstrom's 2011 Almanac

Are you looking to buy something that provides hundreds of thousands (or millions) of dollars of profit opportunity?

And are you looking to buy it at full price, eschewing the free shipping and 40% off Cyber Monday offers that destroy corporate profitability?

Then Hillstrom's 2011 Almanac is for you!  You get one tip per day, 365 in all, tips that can be used to improve business performance tomorrow!




Knowledge you'll gain?  Priceless!

And if you aren't going to buy it, at least tweet about it to your followers!!

Dear Catalog CEOs: Lifetime Value of a New Item

Dear Catalog CEOs:


You occasionally ask me to analyze the merchandise life cycle.  In other words, you want to know what the lifetime value is of a new product, and you want to know what impact new product development has on the growth potential of your business.


A new product faces a daunting challenge.  In one instance, I demonstrated to a CEO that a new product has an 8% chance of surviving five years after introduction.  For this business, here's what the life cycle looks like:


In other words, a new item is expected to generate $8,000 total demand in the year it is introduced (known as the 'stub year', or 'year zero').  In the next ten years, the item will achieve a total of $35,000 demand ... or $35,000 - $8,000 = $27,000 of future demand.


The marketing literature is littered with lifetime value stories ... newly acquired customers generate $17 of lifetime value, for instance.


You'll be hard pressed to find a single story in the marketing literature about the lifetime value of a product.


It turns out that knowing the lifetime value of a new item is one of the key metrics to determine the success of your business.  Your product assortment is being transformed each year in a highly Darwinistic process of survival.  

In this case, only 8% of new items survive five years.  This means that your merchants are in a constant hunt for the 'next big thing'.  Your merchants must identify 100 new products, expecting only 8 of the items to still be offered five years later.  

Imagine what happens if your merchants fail to identify new products that meet acceptable productivity levels?


Yes, when you fail to identify great new items, your business struggles in the future.

We'll address that topic next week.

Chasing Returns

The topic is "Chasing Returns", inspired by a blog post that I read this morning.  The article talks about chasing returns in a market that one does not understand.

This weekend, we deal with Black Friday and Cyber Monday.  These are discount and promotion oriented events cheered on by the media, by trade organizations, and by marketers with a lust for driving sales increases without regard for generating gross margin.

One of my favorite stories came a few years ago, on Cyber Monday.  A business leader told me that he saw Cyber Monday promotions from his competitors in his e-mail inbox at 7:00am, then told the e-mail marketing manager to hold the delivery of the e-mail campaign for an hour so that the promotion could be changed, from 25% off plus free shipping, to 35% off plus free shipping.  I asked the business leader why the change was made?  The business leader replied ... "Because we had to remain competitive!"

This is an example of chasing returns in a market that one does not understand.

You don't do things because a trade organization cheer leads an event that gives attention to the trade organization.



You don't do things because a competitor does them.  When you are at Six Flags and your child wants cotton candy and already had cotton candy, you don't look around at your competitors (other parents) and then say, "Ok, not only do you get cotton candy, but you get a double-sized cotton candy because I've got to remain competitive" ... do you?

You do things because you thoroughly understand both the short-term and long-term consequences of your decision.


The short-term consequences are easy to understand, you run a promotion, and sales increase by 46%.  This is "chasing returns", you see sales increase, so you discount more often, with bigger and better promotions.

If you can answer the following set of questions, then you're free to run whatever promotions you want.
  1. If you did not run one single promotion for six months, how would company profitability change?  In other words, do you know if customers will purchase at the same rates, over time, if you do not run a single promotion?
  2. If a customer purchases using a promotion, will the customer purchase at full-price in the future, or have you trained the customer to purchase when you offer promotions?
  3. Does the impact of promotions "sustain" over time?  In other words, if you offer 20% off plus free shipping and you get a 30% sales lift, will you get a 30% sales lift when you offer the same promotion next year at this time, or will you have to increase the percentage off in order to obtain the same lift?
  4. Does your promotion cannibalize sales from surrounding days?  In other words, do you lose full-price sales in the first fifteen days of November because the customer knows you'll offer promotions on Black Friday and Cyber Monday?
If you can answer each question, based on prior test results, then run whatever promotion you want.

If you cannot answer each question, then you are chasing returns.  And we all know how well that worked for the financial industry and for the sale price of the homes we live in.

November 25, 2010

Hashtag Analytics: Part 3 = Recency + Weeks

You thoroughly enjoyed the first two parts of our series ... among the most popular posts written this year.

So we'll continue.

In this case, I segment the user base by recency (weeks since last tweet) and weeks (number of weeks user participated in last four weeks).

"Engage" represents the percentage of the audience in each segment that participated in last week captured in my dataset.

What do you see?

Clearly, there are users that are highly "engaged".  In particular, there are two segments of users that are highly engaged.
  • Recency = 1 Week, Participated in 3 of Past 4 Weeks.
  • Recency = 1 Week, Participated in 4 of Past 4 Weeks.
This is going to be the criteria I use for what I call a "Mega Participant".  A Mega Participant is a participant who participated last week and participated in three of the past four #blogchat events.

In subsequent posts, we'll learn that these individuals are highly valuable, in terms of keeping the #blogchat community moving forward.


Notice, however, that "engagement" rates are not spectacularly high for other users.  I analyzed prior weeks (because there are different topics on different weeks each month) ... the same trend repeats, over and over and over again.


Also notice that prior Mega Participants only account for 9.6% of all participants in the week being analyzed.


In other words, the #blogchat ecosystem is a dynamic ecosystem, with users moving in and out every week.  And when that happens, recruiting new participants is of paramount importance!

November 24, 2010

Hillstrom's 2011 Almanac: PRINT VERSION IS AVAILABLE!!!

Take advantage of Black Friday by picking up your copy of Hillstrom's 2011 Almanac!!

The print version of the book is now available on Amazon.com!!!!  Click here to take a peek, and to buy the book on Amazon.  The print price is $14.95.


A digital version is available for $7.95.
Three samples are available for your browsing pleasure.
You get 365 tips to improve your marketing, analytics, and leadership programs, one tip per day for each day during 2011.  How do you beat that?


Purchase the print version today, and you'll have your book in time for the all-important Cyber Monday e-commerce holiday.  And Hillstrom's 2011 Almanac makes a perfect stocking stuffer!

November 23, 2010

Hashtag Analytics: Part 2 = Engagement

Today, we're going to explore a few introductory metrics, metrics that help us understand how the #blogchat community behaves.

I created a variable called "Engage".  This variable has a 1/0 value, a "1" if the user issued at least one tweet within the #blogchat community for the week ending November 11, 0 otherwise.

I then summarized activity for the prior four weeks, weeks ending November 4, October 28, October 21, and October 14.  I created two new variables, and transformed the remaining eight variables.
  • New Variable = Recency ... defined as "weeks since last participation."  This variable can have a value of 1, 2, 3, or 4 ... one means the user last participated one week ago, four means that the user last participated four weeks ago.
  • New Variable = Weeks ... a sum of the number of times the user participated in the last four weeks.  This variable can have a value of 1, 2, 3, or 4 ... four means that the user participated in each of the past four weeks, one means that the user only participated in one of the past four weeks.
  • Statement, Re-Tweet, Amplify, Converse, Link, Tweets, RT, and ANSW are all "averaged" for the four weeks.  In other words, if a user participated in each of the four weeks, and had 2 statements, 9 statements, 4 statements, and 17 statements, I calculate an average ... 8 statements per week.  This process is repeated for each variable.
At this point, I have a dataset with eleven variables.
  • Engage:  Did user engage the week of November 11 (1/0)?
  • Recency:  Weeks since last participation (through November 4).
  • Weeks:  Number of times user participated in past four weeks.
  • Tweets:  Average number of tweets per week.
  • Statements:  Average number of statements per week.
  • Re-Tweets:  Average number of times re-tweeting other comments per week.
  • Amplify:  Average number of times amplifying the comments of others, per week.
  • Converse:  Average number of times conversing with others, per week.
  • Links:  Average number of links mentioned, per week.
  • RT:  Average number of times re-tweeted by others, per week.
  • ANSW:  Average number of times answered by others, per week.
Finally, I transformed the last two variables, into 1/0 indicators.
  • RT:  1 if user was ever re-tweeted, 0 otherwise.
  • ANSW:  1 if user was ever answered, 0 otherwise.
This dataset provides us with a rich set of community dynamics, dynamics that can be analyzed in many interesting ways.

For instance, I measured "engagement", the percentage of users who participated the week ending November 11, based on "recency", the number of weeks since the user last participated.  Take a look at the findings:


Recency Users Engage Totals % Totals
1 496 38.7% 192 16.7%
2 530 17.7% 94 8.2%
3 342 11.7% 40 3.5%
4 206 9.7% 20 1.7%
99 807 100.0% 807 70.0%



1,153

Take a look at the first row.  Users who last participated the week ending November 4 had a 38.7% chance of engaging (i.e. issuing at least one tweet with the #blogchat hashtag) during the week ending November 11.  496 users had a 38.7% engagement rate, yielding 192 users who participated during the week ending November 11.


This is a pretty low rate.  And look what happens as participation becomes more "distant" ... 17.7% of those who last participated two weeks ago engaged ... 11.7% of those who last participated three weeks ago engaged ... and 9.7% of those who last participated four weeks ago engaged.


In other words, it is really important to keep the user "engaged".  If the user takes a week off, or two weeks off, the user becomes less and less likely to engage in the future.


Look at the column labeled totals.  This is the number of users by segment.  In total, there were 1,153 users who participated in #blogchat during the week ending November 11.  Most important, 807 of the 1,153 users, 70% in total, had not participated in the past four weeks.


This is sooooooooo important.  The success of the #blogchat event for the week ending November 11 was largely due to the fact that 70% of those who tweeted something had not tweeted anything in the prior four weeks!


In Direct Marketing, we know that New Customer Acquisition means EVERYTHING.


In Social Media Communities, we have the first piece of evidence that New User Acquisition means A LOT!


Tomorrow, we'll continue to analyze engagement rates across various segments.

Hillstrom's 2011 Almanac: Digital Versions Are Available!!

Are you looking for the perfect Cyber Monday gift?

How about Hillstrom's 2011 Almanac?

You get 365 practical tips for improving business tomorrow morning, I mean, how do you beat that?

And this isn't going to cost you the $750,000 you'll spend with your favorite Management Consulting firm.  You'll pay a far more reasonable price for great information!

The book is now available in two digital formats.


The Kindle version is available for $7.95 as well.  Let me know if you cannot download it, the book appears to be ready for distribution.

The print version, via Amazon.com, will be available in the next 2-7 days, and will cost you just $14.95.

The print version, via Createspace, is now available for $14.95.  Personally, I'd hold out for the release of the Amazon version, as you are likely to receive it faster (and you can add an item and get free shipping).

It's time to get your 2011 Almanac, be ready for 2011 with 365 marketing, analytics, and leadership tips!

November 22, 2010

Hashtag Analytics: Part 1 = Data Acquisition

We're going to try something new here, something that is trendy in analytics these days.

We're going to analyze hashtag behavior on Twitter.

Our analysis will focus on the #blogchat community, a Sunday evening social media discussion hosted by Mack Collier on Twitter.  Every Sunday night, this community discusses various topics of interest to their community.  Folks communicate via the #blogchat hashtag, so that everybody can follow what folks are saying about each other.

I collected data from about eighteen weeks of #blogchat events.  After analyzing the behavior of the community, I reduced the dataset to five weeks of behavior.  I used four weeks as the segmentation period, with one week as a prediction period.  Later in the analysis period, we'll review eight weeks of data, using four weeks to predict the next four weeks.

Allow me to explain the variables I am tracking in my dataset.

The first variable is called "statement".  Here's what a statement looks like:
  • MineThatData:  I am really looking forward to #blogchat tonight!
In other words, the individual is communicating a statement to the entire audience.


The second variable is called "re-tweet".  This is a huge form of social currency.  The person issuing the re-tweet is giving another individual credit for saying something clever, or is trying to gain attention in some way.
  • MineThatData:  RT @mackcollier Bloggers really do a nice job of sharing interesting topics #blogchat.
The third variable is called "amplify".  This happens when a user adds to the statement offered by another individual.
  • MineThatData:  And they have unique opinions. RT @mackcollier Bloggers really do a nice job of sharing interesting topics #blogchat.
The fourth variable is called "converse".  Here, one user is having a conversation with another user.
  • MineThatData: @mackcollier Don't you think that bloggers could do a better job of being objective? #blogchat
The fifth variable is called "link".  Often, when a person makes a statement, the person links to another article to back up the statement.
  • MineThatData: We covered this topic on my blog last month:  http://bit.ly/dk928d #blogchat
We sum each tweet a user issues, and create a sixth variable, called "tweets".

The first set of variables describe the actions a user might partake in.

The next two variables are very important.  These two variables account for feedback from other users in the community.


The seventh variable is called "RT".  Each time a user is "re-tweeted", I tally one for the user in the "RT" column.  In my earlier example, @minethatdata gets a value of "1" in the "re-tweet" variable.  @mackcollier gets a value of "1" in the "RT" variable, because his statement is re-tweeted.
  • MineThatData:  RT @mackcollier Bloggers really do a nice job of sharing interesting topics #blogchat.
The eighth variable is called "ANSW".  This is an important variable, because it means that the user is engaged in a conversation, and that the other person in the conversation elected to answer the user.  In our earlier example, @minethatdata gets a value of "1" in the "converse" variable, while @mackcollier gets a value of "1" in the "ANSW" variable.
  • MineThatData: @mackcollier Don't you think that bloggers could do a better job of being objective? #blogchat
My dataset is generated on a weekly basis.  Each week, I categorize all activity in the #blogchat community, for each user participating in the #blogchat community.

Let's assume that a user, called @user, issued the following tweets.
  • @user:  @person But don't you think that brands should be "all-in" in Social Media? #blogchat 
  • @user:  If big brands don't join the conversation, they're finished. #blogchat
  • @user:  What do you think are the three most important things a large brand should do first? #blogchat.
  • @user:  @person This link is very helpful. http://bit.ly/dkeo229kf #blogchat. 
If this is all of the activity I can find for @user, then @user has the following profile for this week:
  • Statement = 2.
  • Re-Tweet = 0.
  • Amplify = 0.
  • Converse = 2.
  • Link = 2.
  • Tweets = 4.
  • RT = 0.
  • ANSW = 0.
The data set has one row per @user / week combination.

And when you have data formatted in this manner, you can make magic happen!  Tomorrow, we begin to explore the magic behind the #blogchat community. 

November 21, 2010

Dear Catalog CEOs: Future Content

Dear Catalog CEOs:

In 2009, this series was the most popular series of posts I wrote.

In the first third of 2010, this series was about "average", in terms of readership.
In the past three months, this series is well below "average", in terms of readership.

We're at an interesting crossroads.  Your industry trade journals have abandoned you, shifting focus to multi-channel (whatever that is), then e-commerce, and now social/mobile.  Your conferences have been terminated due to low attendance and poor content.

I understand that readership of this series may be at or above average among Catalog Executives, but is being abandoned by remaining (the vast majority) of blog subscribers.

So if this is the case, I need your help.
  1. Use the comments section (go ahead an be "anonymous" for the purpose of this exercise) to describe what you think has been lacking, in terms of content, in the past three months.
  2. What are you reading in the trade journals that you find interesting?
  3. What do you want for me to write about that would be interesting and useful to your business?
It would be very helpful to receive a few comments from you, industry leaders whom this series is tailored to.


Based on your feedback, I will tailor the content to your interests, as long as it is congruent with my knowledge base.  Without feedback, I'm left to consider topics that are of interest to the overall audience, so please offer feedback (e-mail address is kevinh@minethatdata.com).

November 17, 2010

Hillstrom's 2011 Almanac ... Sample #3

Here's a third sample from the upcoming book "Hillstrom's 2011 Almanac".


July 3

You’ll never read about boring marketing tactics!

Nobody wants to read about how Blair Corporation increased sales by 3% by doing a better job of placing catalogs in outgoing package shipments.

Lots of people want to read about how virtual currency will change the way users play games on Facebook, regardless whether any real currency changes hands or not.

In no way is virtual currency unimportant.  It’s certainly important!

But it is just as important that you execute a boring tactic that generates real sales, and real profit, regardless whether anybody in the vendor community actually talks about the boring tactic or not!

November 16, 2010

Hillstrom's 2011 Almanac ... Sample #2

Here's another sample from the upcoming book "Hillstrom's 2011 Almanac."

May 17

Now that you have the trade area for each store, record the information in your customer database.

Migrate the following segmentation attributes to your web analytics platform:
  • Visitors who do not live in a store trade area.
  • Visitors who live in one retail store trade area.
  • Visitors who live in zip codes that are part of 2+ store trade areas.
Analyze the living daylights out of this.  Customers/visitors who are saturated by retail stores behave different than do customers/visitors who do not live near a retail store.

November 15, 2010

Hillstrom's 2011 Almanac ... Sample #1

Here's a sample tidbit/observation from the new book, available soon:

May 3

If you want to measure the incremental value that Facebook delivers to your business, give regression analysis a try.
Pull purchase data for all customers who placed at least one order in the past twelve months ending March 31.  Here are the variables.
  • Recency, Months Since Last Purchase.
  • Number of Orders, Past 12 Months.
  • Number of Orders, 13+ Months Ago.
  • Number of Channels Purchased From.
  • Number of Merchandise Divisions Purchased From.
  • 1 if Customer is a Facebook Fan, 0 Otherwise.
Pull demand spent by customers in this audience during April.  Run a Regression Analysis.
  • April Demand is the Dependent Variable.
  • The Variables above are Independent Variables.
Look at the coefficient for being a Facebook Fan.
  • If is isn't significant, then being a Fan results in no incremental value.
  • If the coefficient is negative, then being a Facebook fan hurt the business.
  • If the coefficient is positive, then multiply the value of the coefficient by the number of customers who are a Facebook Fan.  This multiplication yields the incremental dollar value provided by Facebook. 
    • Example:  Coefficient = $0.50.  Customers = 1,000.  Incremental Value = $0.50 * 1,000 = $500.

What Happens At Different Life Stages?

One of the first analyses I run in a Merchandise Dynamics project is the Life Stage Analysis. Specifically, I want to know what customers do...