Postcodes: A Simple Solution to Measuring Your Advertising ROI

One of the hottest trends in ad performance measurement, especially as privacy concerns kill user-level online tracking, is geographic incrementalism experiments. These experiments are cost-effective, simple, and reliable when done correctly.

Geomedia experiments typically use large marketing areas, such as Nielsen’s Designated Market Areas (DMAs). Unlike traditional matched market testing, this modern approach randomly assigns DMAs, ideally all 210, to test and control groups. In this way, advertisers with first-party data can measure real sales lift internally, without external services. In the absence of internal sales data, third-party panels such as those from Circan and NielsenIQ offer alternatives that are consistent with this type of test design.

High-quality, randomized controlled trials (RCTs) – similar to clinical trials in medicine – are the best source of evidence for cause and effect relationships, including the effect of advertising on sales.

Statistical models, including synthetic users, AI, machine learning, attribution, all sorts of quasi-experiments, and other observational methods are faster, more expensive, and less transparent forms of correlation—not causality measurement. They can be effective in defining a target audience, but they are not good for quantifying ROI.

But imagine the possibility of conducting geographic experiments using postal codes instead of DMAs.

Targeting by postal codes

The advantage of DMAs is that they are universally compatible with all media types. Postcodes, on the other hand, present a challenge for digital media experimentation. Online postcode targeting often relies on IP address inference, which is unreliable and increasingly privacy-intrusive. Geolocation signals from mobile devices also pass postcodes into user profiles, which is bad for experimentation because a single device/account can be tagged with multiple postcodes based on where the user has recently visited.

The key to the reliability of this type of geographic experiment is to ensure that the zip codes used for random media exposures match the zip codes in which recipients receive their bills, as recorded in the company’s CRM databases. Each device and user should be covered by only one zip code: their home zip code.

To implement this technique, media companies can take two groundbreaking steps:

1. Use basic postcode targeting:
   Major players like Google and Meta already collect extensive user data, often adding multiple zip codes to a single device. For experiments, these companies should offer a “base” zip code targeting option based on a user’s profile or the most commonly viewed zip code for their devices.
2. Implementation of anonymous registration using postal codes:
   Publishers should require registration to access most free content, offering an “anonymous” account type that doesn’t require an email address. Users would have to provide a username, password, and home ZIP code, allowing publishers to improve audience profiles while preserving user anonymity.