How one of America’s largest consumer goods advertisers rebuilt its programmatic buying around verified human attention and recovered a substantial share of its media budget in the process.
On the surface, Georgia-Pacific’s programmatic buys looked healthy. Reported viewability was strong. Standard verification tools returned low fraud flags. Every dashboard said the media was working.
Internal scrutiny told a different story. A persistent disconnect between media quality metrics and actual sales impact pointed to a familiar but well-hidden problem: non-human traffic and low-quality impressions were inflating performance reports without moving a single case of product off the shelf. Impressions were likely inflating performance reports.
Georgia-Pacific brought programmatic operations in-house, consolidated on a single DSP, and benchmarked its buying against the ANA Programmatic Transparency Initiative. Working with Yahoo, the team traced spend back through the supply chain rather than accepting the summary reports at face value.
The forensic analysis found that a meaningful portion of spend was tied to impression types and supply paths that did not correlate with incremental sales, despite appearing clean in legacy reports. Three problems stood out:
• Over-reliance on generic third-party audience segments.
• Heavy exposure to lower-quality open-exchange environments.
• Traffic patterns that delivered cheap CPMs but not verified, viewable, human impressions in premium contexts.
That evidence drove three decisions: a systematic cull of low-value exchanges, a sharp reduction in third-party data partners, and a pivot toward retailer first-party data such as Kroger Precision Marketing audiences, where impressions could be tied directly to verified purchase behaviour.
Exact fraud percentages were not disclosed. What is clear is the scale of the reallocation. Georgia-Pacific moved a substantial share of its budget away from low-quality and potentially fraudulent inventory and into tightly curated, high-viewability, high-human-traffic supply. Media productivity moved into the top quartile of its category, and the pool of suspect impressions shrank significantly.
Verified human reach increased as the team prioritised premium placements, transaction-backed retailer audiences, and AI optimisation via Yahoo’s Blueprint Performance, focusing on the impressions most likely to drive incremental sales rather than superficial reach.
In practical terms, the forensic, in-house approach allowed Georgia-Pacific to recover a large portion of previously underperforming spend, functionally in the tens of percentage points of its programmatic budget, by cutting out wasteful, low-quality paths and reinvesting in demonstrably effective, human-verified media.
| Metric | Before Forensic Audit | After Forensic Optimisation |
|---|---|---|
|
Reported impressions |
High |
Lower (non-human removed) |
|
Nominal CPM |
Lower |
Slightly higher |
|
Cost per real human reached
(hCPM) |
High (hidden) |
Significantly lower |
|
Performance stability |
Variable |
Consistent |
|
Budget recovered |
0% |
20-60% |
When fraud is removed, you are not paying less to reach fewer people. You are paying less to reach the same real people because you have stopped sending your ads to unverified or scam sites.
