Monday Musings

Life is hard enough ... so on Monday we pursue a different vector:

Grocer H-E-B performed simulations prior to the outbreak, leaving them better prepared for everything that has happened since (click here). Enjoy the oral history style of storytelling.

Dinner with the Gaffigans (click here).

Medical masks are one of Animal Crossing's hottest looks (click here).

Kringle from O&H Danish Bakery in Racine ... perfect for our trying times (click here).

Stay tuned until at least the twenty-nine second mark of the video (click here).

Christmas Clicks

I recently built a QuickScore model (click here) ... in the email portion of the model I predicted who would be most likely to click through an email campaign in the next month.

That's where the fun started:

• Customers who clicked through email campaigns between Thanksgiving and Christmas were less likely to click through a campaign in Spring ... the variable possessed a negative coefficient.

Oh.

There is so darn much good stuff to research in email click-through activity ... and almost all of it has been ignored by an industry lusting over vanity metrics. The secrets to File Power are just lying there, waiting to be discovered. Go discover how your customers actually behave as long as you are trapped at home.

Sales Impact

I ran a Twitter poll to understand how much sales have been impacted in the past few weeks:

• 10% = > 5% Sales Gain.
• 18% = -5% to +5% (i.e. Flat Sales).
• 16% = -5% to -25% (Significant Sales Decline).
• 56% = -25% or Worse Sales Decline (i.e. Catastrophe).

As you can see, about 1 in 4 Twitter readers are not seeing a sales impact, with about 1 in 10 seeing healthy sales gains.

For the 3 in 4 seeing a significant sales decline, this is the time to measure File Power. This is the time to forecast the impact of reduced File Power on the future health of the business.

For those seeing sales gains, thank your lucky stars, for you have been blessed.

Hillstrom's QuickScores

Hillstrom's QuickScores

For the duration of our virus-induced quarantine and likely well into 2021, we will have no choice but to either rebuild businesses or capitalize on a virus-induced bump in sales, with most of us in the former category. Email marketing will be one of the key drivers that restore File Power to our businesses, given the low cost and high relevancy of the channel.

Hillstrom's QuickScores addresses a targeted approach to restoring File Power, Sales, and Profit. Based on a proprietary weighting strategy that evaluates when historical purchases happened and how much was spent (by marketing channel), you will receive the following QuickScores.

• Email QuickScore:  A score that you can use for targeting purposes ... each customer ranked from highest to lowest based on the probability of purchasing via an email campaign. You'll know exactly who to target for loyalty programs, for activation programs, for reactivation programs.
• Catalog QuickScore:  For catalogers, a score that will tell you who is most likely to purchase solely because of catalog mailings. Historical purchases across channels are weighted appropriately so that you are not wasting one penny of the money your brand allocates to marketing purposes.
• Merchandise QuickScore:  Based on weighted historical transactions you will know, by customer, the Primary Merchandise Category and the Secondary Merchandise Category preferred by the customer. Used in combination with the Email QuickScore, you will be able to target the specific merchandise category that causes the customer to be most likely to purchase from an Email Marketing campaign. The scores can also be used to personalize your home page / landing pages.
• Brand QuickScore:  An overall ranking of customers from best to worst based on Brand Loyalty.

Project Cost = $8,000.

Project Turnaround = Approximately One Week.

Project Deliverable = Email QuickScore, Catalog QuickScore (if you are a catalog brand), Merchandise QuickScore, and Brand QuickScore ... you will receive pseudo-code that allows you to score your own file on a weekly / daily / hourly basis. If needed, you can send me transactions once a month and I will score your file for you and send the records back to you. If your company needs that during this challenging time, I'll do it at no cost.

Let's get busy building this infrastructure into your database now ... so that when life returns to normal you are ready to capitalize on myriad opportunities.

Test Panels and Attribution

I recently read an article from a vendor ... the vendor described their multi-touch attribution routine for catalog brands.

If you don't execute four-panel tests between catalog marketing and email marketing, multi-touch attribution routines are hopelessly flawed.

Yes, they're hopelessly flawed.

Your four-panel test gives you all of the information you need to assign weights to transactions.

Look at the email portion of the table.

• 9% of mail/phone/fax demand is attributed to email marketing.
• 98% of email demand is attributed to email marketing / almost all of it is caused by email marketing.
• 12% of search demand is attributed to email marketing.
• 11% of online marketing demand is attributed to email marketing.
• 5% of in-store retail sales are attributed to email marketing.
• 6% of all other online sales are attributed to email marketing.

That's it ... you've got it ... you executed holdout groups, and you know the exact percentage of sales that should be attributed to email. No need for AI or algorithms. You have the facts.

Look at the catalog portion of the table.

• 93% of mail/phone/fax demand is attributed to catalog marketing.
• -23% of email demand is attributed to catalog marketing. Catalogs cannibalize email, and if you take catalogs away email does much better ... so you need to subtract email demand from the catalog total to account for the corrosive impact of catalogs.
• 32% of search demand is attributed to catalog marketing.
• 25% of online marketing demand is attributed to catalog marketing.
• 8% of in-store retail sales are attributed to catalog marketing.
• 53% of all other online sales are attributed to catalog marketing.

You've got it ... you take your matchback algorithm, you apply the percentages by channel, and you know exactly what the contribution of catalogs are to your bottom line. Run a p&l by segment and you are done.

If you execute test panels, you know the truth.

I'm been writing this blog for nearly fifteen years. I've been advocating this style of testing the entire time. Get busy learning the truth about your business.

BREAKING NEWS

Your life is hard enough right now ... so click on this link and watch penguins explore Shedd's Aquarium and enjoy ninety seconds of peace.

P.S.:  This link gets you to the Brown Bear Cam at Brooks Falls in Alaska. Most of the videos now are "best of" videos from last summer ... but come July/September you'll want to watch the action live.

P.P.S.:  This "dog in training" failed.

P.P.P.S.:  This goat had to "shake it off".

The Math Behind Business Coming Back

Let's say that this virus issue causes your business to lose 40% of your top-line volume for two months ... and this is possible, especially if you are retail brand.

While devastating for two months, there is math that offers subsequent hope.

I first saw this working at Lands' End in 1991 - 1992. With business not spectacular, we had huge gluts of customers who did not repurchase when business was bad. When business returned to normal we actually experienced gains in 1993 simply because larger gluts of customers repurchased at the same rate they were expected to repurchase at, causing a modest sales rebound.

In the example above, business is down 40% for months 1-2, when the customer has a recency of 1 month or 2 months. You lose 48 purchasers in the first month. You lose 32 purchasers in the second month ... you are 80 customers behind after two months.

This leaves you with a glut of 792 non-purchasers entering month three under normal conditions ... under crisis conditions, you have 872 non-purchasers. Even with normal repurchase patterns over the next ten months you have more customers in your cohort, causing more repurchasers.

• After Two Months you are down 80 repurchasers.
• After Twelve Months you are down 51 repurchasers.

In other words, you regain 37% of the customers you lost during the two-month catastrophe.

Many customers come back ... as long as merchandise productivity returns to normal.

That's the key to this ... merchandise productivity must return to normal.