How do you generate probabilistic attribution scores, and how do you ensure accuracy?
We start with raw event data: impressions (ads we’ve served) and conversions (events passed to us via tags on the marketer’s website or via the marketer’s conversion API). Suppose there is no deterministic link between the two events. In that case, we feed the events and any related data into our model, which estimates the probability that the impression was from the same person who converted.
We train our models using probabilistic events combined with deterministic data (which more accurately determine which events are for the same user). We can train our models on this subset of data and then score them on the larger, complete set of events. In this way, our models expand our knowledge of the small set of deterministic events into probabilistic scores on the larger set of events.
To ensure accuracy, we measure our performance in several ways, including using holdout data from the training set and comparing our results with third-party attribution solutions. Our customers have run many cookieless campaigns with us, and those with their own measurement solutions report that our measurement aligns with theirs.
Do you have thresholds to ensure you only attribute conversions with a confidence level above a certain threshold?
From running many tests, we have found that using all conversion scores together yields the most accurate results (rather than discarding information from lower-scoring conversions). We retain all conversion scores to inform our attributions. While some individual conversions may have lower likelihood scores, aggregated totals are highly predictive; evaluating the total sum of your conversion probabilities across cookieless conversions allows us to achieve a high level of confidence overall. Keep in mind that a low-scoring conversion will contribute only a small amount to the total; e.g., an attributed conversion with 50% of conversions correctly attributed will contribute only 0.5 conversions to the total.
In many cases, our attribution assigns a conversion likelihood score of 0 (for example, when impressions and conversions occur in different countries). We will not count any attribution signal with a score of 0.
How do you validate that attribution results are correct/accurate?
When we train our cookieless identity models, we test them on a known dataset. We can validate this using deterministic IDs, such as email-based IDs. In addition, while third-party cookies exist, we can also test our measurement against what third-party cookies report on some media.
Can you provide a match rate between users visiting a client website or digital destination and being visible to Quantcast across the open web?
This is simply the ratio of cookieless to everything for the internet at large.
Over half the internet is now cookieless. Even though Chrome is rolling out very slowly, we already see significant Chrome traffic without third-party cookies, driven by users’ individual choices. For a particular client, the opportunity will vary a bit depending on the client’s target audience: for example, a client selling Apple software will have a much higher percentage of cookieless users than someone targeting Windows users.
Do you report on individual conversions?
We do not report on individual conversions; we report the aggregate counts in Report Builder.
We take the probability/score for each conversion into account when reporting. For example, if we say that we think there were five possible conversions with probabilities: 0.3, 0.5, 0.6, 0.8, and 0.9, then we would report three conversions (3 ~= 3.1 = 0.3+0.5+0.6+0.8+0.9)
Why does Quantcast not use thresholds (i.e., only counting attribution above a certain percentage of confidence)?
We believe a system that does not rely on thresholds is more accurate. Each time you apply a threshold (e.g., 75% likelihood), you remove data that informs modeling. The more you remove, the more data you end up with that you cannot use. When you model and use thresholds, your results are not as good as when you model and use all of the resulting data.
An example best explains this. If you are targeting females, and models result in three outcomes—a score of 74% likelihood that your target is female, a score of 76%, and a score of 95%—thresholding above 75% would mean that the score of 74% would get a no-bid, and you would bid the same for 76% likelihood and 95%. Without thresholding, you would bid highest for 95%, lower for 76%, and still lower for 74%.
How does audience targeting work in a cookie-less environment?
Quantcast is not reliant on third-party cookies. The platform was built to work in cookie-less environments like Safari and Firefox and uses a multi-signal, probabilistic approach to identify and target users. This involves using its first-party tag data, contextual signals, and other identifiers to create a comprehensive view of user behavior, thereby expanding audience reach and often resulting in lower CPMs.