There are a lot of signs that trade and retail media networks (RMNs) are converging. This is driven on the one hand because retail media and trade are increasingly financed from the same source: sales co-op funds. On the other hand, they are both converging on the lower funnel – the first moment of truth. Why would tactics so close to the point of purchase be so hard to measure?
To make sense of this and to understand why retail media ROAS is so hard to measure, we have to look at the simple formula: ROAS = Contribution/Media Cost. When evaluating the profitability of retail media, there are problems with both the numerator and the denominator. The cost (denominator) is often higher for the same service (programmatic or social) if you buy it through the retailer versus buying directly. As a client-side friend put it:
“CPMs for RMNs are (basically) made up. They’ll charge you $18.00 CPMs for a Facebook buy that is completely disconnected to the actual CPMs in the auction. They just pocket all the overage and margin.”
On the other side of the table, an industry consultant reported a Walmart executive saying:
“I’m glad that Walmart connect generates such high margin income for us to offset losses in other parts of the business.”
What is happening in practice is that the RMN costs are being bundled together with other fees as a cost of doing business with the retailer. So, in truth, there are other goodies hidden in the RMN cost such as slotting fees, preferred display locations, etc.
The other problematic part of the ROAS equation is in the numerator – the contribution or lift from media. With most performance media, the drivers of contribution are audience reach and frequency, sometimes at DMA level. With RMNs the media is driving offline sales within the retailer’s marketing area. It is also focused on specific UPCs. This specificity is a two-edged sword: it makes the impact easier to derive because it is so specific, but it also reduces its scope. In fact, only the biggest retailers (e.g., Amazon, Walmart, Kroger, Target, Best Buy, Instacart) have the scale to drive enough traffic to read.
The current practice for deriving the effect of retail media is to treat it just like any other performance media variable in a marketing mix model without paying attention to details of tactic, geography, or the mix of online/offline sales channels.
With all that in mind, here are of the top considerations to improve the quality of the estimate of lift (the numerator of ROAS):
- If the retailer is one of the top RMNs (excluding Amazon), then it makes sense to derive the retail media impact on sales within the trade RMAs. This requires access to chain or RMA-level data.
- If the RMN advertising is for specific UPCs or sub-brands, it makes sense to estimate the sales impact at least at the sub-brand level. Because RMN data moves through media systems, it is not easy to obtain UPC-specific data. Text processing is usually required to infer the sub-brand from various identifying strings.
- Since all these sales impacts are proportional to size of retailer marketing areas and of the sub-brand, a multiplicative marketing mix model will provide much better results than an additive model, since its effects are automatically scaled. This is similar to the way that multiplicative models are more accurate for trade promotions.
- The impact of adstock/saturation must differ by tactic. Onsite search is lower funnel and short-acting whereas offsite media can be much longer-acting.
- There are many types of impacts on sales to consider, including both direct and halo. This table shows the relationship between the type of media (onsite vs offsite) and the sales impact as we move from the most direct (onsite search driving online sales) to the most attenuated (offsite media driving sales in the same high-intent lookalike target anywhere).
| Media Type | Direct | Halo | Secondary Halo |
| Onsite | Online (DTC) | Offline sales of same retailer | Offline and online sales of other retailers (informational search) |
| Offsite/in-App | Offline and online sales of all retailers |
Using advanced modeling systems such as Robust Hierarchical Bayes that take geography and UPC into account, we can accurately track the effectiveness of RMNs (the lift per impression). DTC (onsite search/display driving online sales) has the most direct attribution path. Offsite targeting is usually less effective although there are exceptions. The ROAS depends on transparency in media costs – which at the present time is caught up in the vendor-buyer negotiation and escapes rationalization.
If you would like to discuss how our approach to Robust Hierarchical Bayes can help you better measure your Retail Media investment (and your marketing mix performance as a whole), schedule a call with the i4i Team.
