Most Popular Blog Post Of 2017 (So Far)

When combining readership and "viral" components and pickup by trade journalists and "life of the article", this is the most popular blog post I've written in 2017 ... by an order of magnitude (click here).

If you need that kind of help ... email me (kevinh@minethatdata.com).

P.S.: This article is in second place ... notice a theme? (click here).

How Many New Customers Are Needed?

This was our forecast.

This is the forecast required to grow the business by 5% per year, for each of the next five years.

Holy Cow!

Compared to today, we need +13% / +25% / +34% / +42% / +50% increases in new customers over the next five years, if we want the business to grow by 5% per year.

So this business is just moving customers around low-value segments ... the business needs to dramatically ramp-up customer acquisition just to achieve tepid growth.

Do you know how many new customers you need to simply achieve tepid growth?

No?

Give me a holler (kevinh@minethatdata.com), and we'll figure it out together.


"Forecasting outcomes are the sum of all analytics and marketing knowledge possessed by your company."

20 Volunteers Needed To Test A Revised/New Business Simulation!!!!

Show of hands ... who would like to volunteer to test their business chops?

I've created a new version of the simulation performed at the VT/NH Group in March. I'm looking to take this simulation "on the road" ... to your company ... potentially holding day-long sessions to teach the simulation and to teach how Analysts might better work with Executives.

Here's what I am thinking.

1. The first 20 volunteers get to participate ... email me (kevinh@minethatdata.com) with your intent to participate.
2. The competition will take place May 8 - May 12.
3. Each morning, you (the participant) will submit your business plan to me via email.
4. Around noon (Pacific Time), the simulation will "crunch the numbers".
5. Each afternoon (Pacific Time), you (the participant) will learn how you are performing against your peers.
6. The next morning, you will submit a new business plan for the following year.
7. The participant with the highest company valuation after five years will be declared "the winner", and will earn unrelenting and unending praise from the business community.

Each participant will earn a coveted MineThatData PickAxe ... how about that?!

What levers will you be able to pull?

• Amount of Investment in Online Advertising.
• Amount of Investment in Offline Advertising.
• Discounting Strategy.
• Shipping Cost Strategy.
• Price of Widgets.
• Price of Bidgets.
• Price of Tidgets.
• % of Your Merchandise Assortment That Will Be "New" Each Year.
• Brand-Marketing Strategy vs. Technology-Centric Strategy, Determining The Appropriate "Mix" of Both.

Who wants to participate? Send me an email (kevinh@minethatdata.com) ... this should only take a few minutes of your time and you might end up being the overall winner!!

When Low-Value Counts Hold While High-Value Counts Are Flat ...

Here is the evolution of file counts ...

Here is the evolution of rebuy rates.

The evolution of file counts coupled with rebuy rates yield the following five-year forecast.

The forecast isn't very positive, is it?

Movement in the file happens among low-value customers.

Notice, however, that there is growth among high-value customers (red in the rebuy graph). And the forecast shows that demand per buyer will increase, and average order values will increase. Clearly, this company is trying to squeeze as much out of good customers as possible.

But not enough to offset weakness among lower-value segments.

More on the topic tomorrow.


"Forecasting outcomes are the sum of all analytics and marketing knowledge possessed by your company."

Are Business Shifts Positive?

Recall how our customer file evolved over the past six years.

There are a reasonably constant number of customers at X = -1 / Y = 0.5. These customers buy about 1.3 times a year, and only buy from the primary product category - generally buying via email marketing.

There are a reasonably constant number of customers at X = -0.5 / Y = -1.2.  These customers buy only one (inexpensive) item from the primary category via online. This probably isn't a segment that has a high repurchase rate.

I created a GIF of repurchase rates over the past five years. How does this GIF compare to the GIF above (if you cannot see the GIFs, please visit http://blog.minethatdata.com)?

Notice that the largest file count areas have poor repurchase rates.

High repurchase rate cohorts are reasonably consistent over time ... customers around X = -0.25 / Y = -0.5 tend to have the highest repurchase rates. Who are these customers?

• They order about three times per year.
• 80% of their dollars come from the primary product category.
• Nearly all of their dollars are online - only 15% come from online marketing channels.

So the most loyal customers purchase every four months ... generally buying from the most popular product category ... and they're so loyal that they don't need marketing to drive their purchases.

This creates interesting challenges, when looking to the future. File growth generally comes from low-repurchase segments. We need to see if "some" of these customers will migrate to high value in the future, don't we? Let's take a look at that tomorrow.


"Forecasting outcomes are the sum of all analytics and marketing knowledge possessed by your company."

When Business Shifts

It's hard to have a good forecasting algorithm if you don't know what happened in the past.

Everybody has different ways of approaching the topic. I like to use a Principal Components Analysis ... creating two "factors" ... each factor is then "segmented" into seven different classifications that yield 7*7 = 49 customer segments. By tracking the change in file counts and rebuy rates by segment, I can quickly see how a business is "evolving" ... and then I am better able to create a forecast that shows where the business is going.

Let's take a look at where a business has been over the past six years.

Each image below shows how the file evolved over the past six years ... red = many customers ... blue = small numbers of customers.

There are two trends you should pay attention to.

1. Lower-Right corner changes in file counts.
2. Upper-Right corner changes in file counts.

In the lower-right corner of the image, counts have been on the decline over time ... but in the past year, there is a significant increase in counts. I looked at the attributes comprising customers in this corner of the graph. What did I learn?

• Far lower right count declines are from customers who purchased one time per year, online-only, buying product not in the primary product category for this company.
• Upper right corner count declines are from customers who purchased one time per year, phone-only, buying product not in the primary product category for this company.

In other words, this is a company that appears to have greatly cut back on marketing of supporting product categories ... and customers simply disappeared instead of buying from the primary product category.

But then something changes in the past year ... around X = 1 / Y = -0.8 we see a significant increase in customer counts. What describes this segment?

• Customers who buy 1.5 times per year.
• Their purchases are split between the primary product category and the second-most popular product category.

This company changed strategy ... and is actively cross-shopping customers between the two most important product categories.

On Monday, I'll share rebuy rates across time ... and if you like geeky GIFs, here is a GIF of how file counts evolved over time.

"Forecasting outcomes are the sum of all analytics and marketing knowledge possessed by your company."

Sure The Catalog Co-Ops Appear To Be Dying - But What Does It Mean?

When I attend a catalog-centric conference, a theme emerges (this has happened each of the past three years).

• The catalog co-ops are dying.
• What do I do about it? I need new customers!

It's common to see 10% to 15% annual performance declines over each of the past three years.

It is also common for a cataloger to generate 60% of their new customers from catalog co-ops.

So what does it mean to the future health of a catalog business when catalog co-op performance falls off of a cliff?

Let's run an example ... say your business retains 37% of last year's customer file, so you need 63 new + reactivated buyers. You get 53 new buyers and 10 reactivated buyers, for a total of 63. If this is true, then your customer file remains flat each and every year. Your business isn't growing, but you aren't dying either. Every year, you have 100 buyers.

Ok, now let's drop the quantity of co-op sourced buyers (say 30 of the 53 new buyers) by 15% per year, each year, for the next five years.

2017:

• 100 Buyers * 0.37 Rebuy Rate = 37 Retained Buyers.
• 10 Reactivated Buyers + 37 Retained Buyers = 47 Retained/Reactivated Buyers.
• 23 New Online Buyers + 30*0.85 = 26 New Catalog Buyers = 49 New Buyers.
• Total File = 47 + 49 = 96 Buyers.

Do you see what is coming? No? Let's keep running our forecast out for four more years.

2018:

• 96 Buyers * 0.37 Rebuy Rate = 36 Retained Buyers.
• 10 Reactivated Buyers + 36 Retained Buyers = 46 Retained/Reactivated Buyers.
• 23 New Online Buyers + 30*0.85*0.85 = 22 New Catalog Buyers = 45 New Buyers.
• Total File = 46 + 45 = 91 Buyers.

2019:

• 91 Buyers * 0.37 Rebuy Rate = 34 Retained Buyers.
• 10 Reactivated Buyers + 34 Retained Buyers = 44 Retained/Reactivated Buyers.
• 23 New Online Buyers + 30*0.85*0.85*0.85 = 18 New Catalog Buyers = 41 New Buyers.
• Total File = 44 + 41 = 85 Buyers.

2020:

• 85 Buyers * 0.37 Rebuy Rate = 31 Retained Buyers.
• 10 Reactivated Buyers + 31 Retained Buyers = 41 Retained/Reactivated Buyers.
• 23 New Online Buyers + 30*0.85*0.85*0.85*0.85 = 16 New Catalog Buyers = 39 New Buyers.
• Total File = 41 + 39 = 80 Buyers.

2021:

• 80 Buyers * 0.37 Rebuy Rate = 30 Retained Buyers.
• 10 Reactivated Buyers + 30 Retained Buyers = 40 Retained/Reactivated Buyers.
• 23 New Online Buyers + 30*0.85*0.85*0.85*0.85*0.85 = 13 New Catalog Buyers = 36 New Buyers.
• Total File = 40 + 36 = 76 Buyers.

Oh. My. Goodness.

If the co-ops are able to properly help you, you have 100 customers five years from now.

If the co-ops continue to erode at a 15% rate per year, you have 76 customers five years from now.

If I told you that your customer file would be 24% smaller five years from now because of the performance of the co-ops, would you do something about it?

• Would you call every co-op into your office and demand better performance?
• Would you start trying every trick in the book to find new customers?
• Would you start building better relationships with Google and/or Facebook?
• Would you share the findings with your Executive Team?
• Would you teach every employee at your company what is happening, and then ask every employee for ideas to help reverse the trend?
• Would you create an incentive structure to reward every employee who reverses this trend?  15% spot bonuses?  Promotions?

You'd do something, right?

That's why we have to forecast what the future looks like.

Let me know if you need forecasting scenarios run for your business (kevinh@minethatdata.com). We need to see what tepid co-op performance is doing to the future health of our businesses, right?


"Forecasting outcomes are the sum of all analytics and marketing knowledge possessed by your company."