Calculating Incremental Response

When measuring the effectiveness of a promotion, the focus should always be on the incremental order activity that is generated by the promotion. The overall order activity during the promotion's "response window" is irrelevant. For example:

Assume that a catalog mailing is followed two and a half weeks later by a re-mail of the same catalog with a cover change. How many of the orders that were received subsequent to the second catalog's in-home date were the result of the second catalog? How many would have occurred even if the second catalog had never been mailed? And, for those catalogers with an ecommerce site, how many orders would have come in if neither the first nor the second catalog had been sent?

Baseline Order Activity

Catalogers implicitly acknowledge the existence of "baseline" order activity when they say that a re-mail "cuts off the tail" of an initial catalog's "promotional curve." However, just about everyone is struggling with how to quantify the exact amount of cannibalization that re-mails have on their initial drops; and, with how to determine the amount of order activity that ecommerce sites are responsible for.

Without knowing the level of baseline order activity, it is impossible to determine the amount of incremental purchases generated by a second catalog; or, for that matter, by the first catalog compared with self-generated ecommerce activity. Without this understanding, it is impossible to measure the effectiveness of a promotion.

The calculation of incremental effects is a very difficult challenge in today's world of overlapping promotions and channels. Besides re-mails on top of initial drops, and mailings on top of self-generated ecommerce activity, there exist:

  • General catalogs interspersed with specialty catalogs and event or merchandise-specific direct mail pieces.
  • Email blasts in conjunction with direct mail.
  • In B-to-B, the interactions of direct channels with field sales force activity.
  • For catalogers with brick-and-mortar retail, the resulting complex interaction of in-store purchase activity with direct mail and ecommerce.

In sum, today's catalogers operate in environments that are nothing short of analytically noxious.

The Retail Analogy

Savvy retailers have known for years about baseline purchase activity as a result of:

  • Free Standing Inserts ("FSI's"), which is what falls out of everyone's newspapers on Sunday mornings.
  • Run on Press ("ROP"), which is the advertising in the main body of newspapers and magazines.
  • Television and radio spots.
  • The powerful intrinsic advertising that takes place every time a prospect or customer walks or drives by a retail location.

These retailers understand that just a fraction of the store traffic that occurs within the response window of a direct promotion is the result of that promotion. They recognize that there is not a guaranteed stimulus/response relationship between a direct promotion and a subsequent purchase. They have learned that direct promotions are diluted and sometimes even overwhelmed by the vast ocean of ongoing mass promotional stimuli.

This lack of guaranteed stimulus/response relationship between direct promotions and subsequent purchase activity is even true when a response device is included. It is a recognized phenomenon that a significant chunk of customers who take advantage of response devices would have made a purchase anyway.

Today's catalogers find themselves in the same sorts of "open loop" environments as retailers. This is because the advent of multi-channel marketing, and especially the rise of the Web, makes it easy for customers "and, to a lesser extent, prospects "to generate order activity on their own, regardless of how often they are promoted.

Match-Back Processing is Not the Solution

When it comes to promotional measurement, catalogers have not kept up with the times. They continue to employ the old school tool of "match-back processing." Match-back processing, in turn, is driven by business rules to allocate order information and generate campaign reports. For example, the following is the rules hierarchy employed by one cataloger:

  • Responders who, during the process of ordering, are tied to an existing and unique customer ID.
  • Responders whose order has a source code that agrees with the piece they were mailed.
  • Responders who, during the process of ordering, are identified by unique customer ID, but whose order shows a source code different from the piece they were actually mailed.
  • Responders who are matched to their orders by name and address but not unique customer ID, and whose order source code agrees with the source code under which they were mailed.
  • Responders who match by name and address, with source codes on their order that do not agree with what they were sent.
  • Orders with a current source code that cannot be matched back to a mailed name and address record; that is, "pass-along."

Unfortunately, this approach does nothing to address the issue of measuring incremental performance in today's multi-channel world of overlapping promotions.

One cataloger recently learned this first-hand. It had tested radically new creative and initial results were extremely encouraging. However, just to make sure, the cataloger decided to track customer behavior beyond the normal response window. To the cataloger's astonishment and dismay, it discovered that nine months subsequent to the test window just about all of the new treatment's advantage over the tried-and-true promotional package had dissipated! What had happened is that the apparently-successful test treatment had shifted demand forward; that is, pulled order activity into the normal response window that would have occurred anyway in the more distant future.

The Solution

Nevertheless, the cataloger had inadvertently begun down the path towards accurately measuring incremental performance in today's multi-channel world of overlapping promotions. This is because the cataloger had stumbled upon the fact what is required is a "Longitudinal Analytical Framework" to support the continuous creation of knowledge.

The first, "base" component of such as framework is a robust repository of complete customer history, including:

  • Unabridged, atomic-level order and item "demand" transactions; and, when appropriate, post-demand transactions such as returns, exchanges and allowances.
  • All promotional contacts, including mail, email and phone.
  • Scrupulously de-duped individual-level data that is properly linked to the household-level. And, likewise for B-to-B, individual-level data accurately linked to the site level, and the site-level data to the company level.
  • The ability to easily recreate past-point-in-time customer views, model scores/segment definitions and business rules, and "time-0 snapshots" for predictive modeling and cohort analysis.

This can be defined as a "marketing database." However, it is much more than what most catalogers refer to as their "marketing database." For example, one of the leading operational systems advertises add-on marketing database capabilities. However, among other deficiencies, this database offering fails to scrupulously de-dupe customers and inquiries, does not support individual-to-household and individual-to-site-to-company-level linkages, and does not maintain complete promotion history. As for other leading service company solutions, some routinely roll off order, item and promotional data after specified time periods such as twenty-four or thirty-six months. And, most product and service solutions do not include point-in-time capabilities.

The second component of a Longitudinal Analytical Framework is the implementation and subsequent analysis of continuous waves of across-time test treatments, in order to fully understand the complex interactions of channels and promotions. All ongoing analysis takes place within the robust repository of complete customer history.

With such an approach, the devil is in the details and the analytical challenges are very significant. However, the payoff is that true insight can be gained into the behavior of customers and prospects, and into the accurate measurement of incremental response to promotional activity. And, as a result, the holy grail of contact optimization becomes achievable.