Measure conversions more accurately with first-party data
Once you’ve established a first-party data foundation from practices like sitewide tagging, it can enable your measurement solutions to work together and provide you with the most comprehensive reporting possible.
For example, enhanced conversions allow site tags to use consented, user-provided data to give you a more accurate view of how people convert after engaging with your ads.
Here’s how it works
By sending hashed user-provided data from your website to Google, which is then matched to signed-in Google accounts, conversions can be attributed to ads in a privacy-safe way.
This, in turn, provides more observable data to strengthen conversion modeling, gives you the comprehensive data you need to measure conversion lift and helps you better optimize campaigns with Smart Bidding.
This enabled them to measure conversions that would otherwise not have been captured, improving return on ad spend (ROAS) with a recorded sales uplift of 8.6% in Search and 31% in YouTube.
Fill measurement gaps
Online clothing retailer MandM Direct wanted to explore privacy-safe techniques for preserving campaign measurement. They started by implementing sitewide tagging on 100% of their website and adopting Google’s new analytics platform, Google Analytics 4. Next, they strengthened the accuracy and comprehensiveness of these tools by adopting enhanced conversions and using Consent Mode so their site tags could rely on conversion modeling when users didn’t consent to cookies.
Implementing enhanced conversions helped MandM report 3% and 20% more conversions on Search and YouTube respectively — along with a 15% increase on top of that by using Consent Mode.
Rely on machine learning to fill gaps in the customer journey and unlock insights
Even when you’ve built a strong base of observable measurement, gaps in the customer journey might occur when people move across devices and from online-to-offline, not to mention browser restrictions and varying consent choices.
That’s where machine learning can step in to fill measurement gaps. Take conversion modeling which has been, and will continue to be a key feature in Google’s measurement solutions. Modeling uses observable signals to help depict a more complete picture of your performance in a privacy-safe way. And because each advertiser’s customer set can behave distinctly, there isn’t a one-size-fits-all model.
Here’s how it works for each advertiser
We separate ad interactions into two groups: one where we can observe the link between an ad interaction and conversion, and one where we cannot observe the link.
We divide the observed group into subgroups that share non-sensitive characteristics like: device type, browser, country, conversion type, etc.
Within each of these subgroups, we calculate conversion rates.
Next, we take the ad interactions and conversions that are missing a link, and assign them to one of the existing subgroups based on shared characteristics.
For example: subgroup 1 may all be in France, use Chrome as their browser, and are on an iPhone. We see in the “unobserved” group similar characteristics in the ad interaction and conversion data, except for one of these dimensions which is the one we are trying to predict against (for example browser type). So, we align these groups appropriately based on their similarities.
Using the known conversion rates from the observed population and machine learning, we can model which unlinked ad interactions belong to which unlinked conversions.
Note: Our data scientists continuously make improvements to the algorithm for accuracy and scale. Additionally, we proactively test and validate models using techniques like holdback validation to improve accuracy. This allows us to regularly measure biases and inaccuracies to continuously tune our models.
Once the ad interactions and conversions have the appropriate links between them, we aggregate them and surface them in your reporting. We only include modeled data in reporting when we have high confidence that conversions actually occurred as a result of ad interactions. This rigor ensures that we avoid systematically over-reporting.
Gain more insights from your first-party data
Modeling can also set your campaigns up for success by enabling products like Smart Bidding in Google Ads to work better because of access to more complete information - all with user privacy at the forefront.
In addition to more complete conversion measurement and optimization, modeling can also help you learn new customer insights from your behavioral analytics data. For example, Google Analytics 4 uses advanced machine learning models to surface customer insights from your first-party data - across both app and website - and use those insights to improve your marketing.
Then data-driven attribution in Google Ads can take your analysis a step further by using advanced machine learning to determine how each marketing touchpoint contributed to a conversion, all while respecting user privacy. Like all of Google’s measurement solutions, we respect people’s decisions about how their data should be used in the attribution process, and have strict policies against covert techniques, like fingerprinting, that can compromise user privacy.
To help all advertisers take advantage of better attribution in today’s changing privacy landscape, data-driven attribution is now the default attribution model for all new conversion actions in Google Ads.
Check out what the future looks like
Chrome’s Privacy Sandbox aims to develop new technologies to help you get the reporting and insights you need without having to track individuals across the Internet.
For instance, instead of measuring what people do on the Internet in a way that could identify them, they can be kept anonymous by putting limits on data when their actions are reported and adding random data (noise) into the report.
Here’s how it could work
A web browser will match a conversion that happens on an advertiser’s website with an ad that was clicked or viewed on the web. The browser will only report information in a way that doesn’t expose people’s identities—for example, aggregating the data and limiting the amount of information shared about each conversion.
The Privacy Sandbox technologies will work along with capabilities like first-party data and machine learning to power Google’s measurement solutions.
Explore the series
Chapter 2: Ensure your measurement remains accurate and actionable.