About modelled online conversions

Modelled conversions use data that does not identify individual users to estimate conversions that Google is unable to observe directly. This can offer a more complete report of your conversions.

We model to recover slices of data where we know we can't observe ad attribution due to protecting user privacy or technical limitations. We do this to provide high quality measurement so that you accurately understand the impact of your marketing and maintain high quality bidding to prevent underbidding or overbidding.

When Google surfaces modelled conversions in Google Ads, we are predicting attributed conversions. In most cases, Google will receive ad interactions and online conversions but is missing the linkage between the two. The modelling that we perform is modelling whether a Google ad interaction led to the online conversion, not whether a conversion happened or not.

Without modelling, reported conversions would only reflect the observable portion of conversions rather than the true campaign performance.

How modelled online conversions work

In order to model for a non-observed slice of data, we try our best to use data from observable slices where we know behaviour is the same or very similar to the unobserved slice, or we have a good understanding of how they're different.

Example: Let’s say that you have a slice of conversions that are not observable on one browser type, but can be observed on other browser types. Our modelling will first understand the trends between users' behaviour (for example, conversion rates) across browser types. We then use our observable data from measurable browsers, together with any systematic biases, and incorporate other aggregate dimensions like device type, time of day, geographic location, operating system and more, to predict the likelihood of conversion events from ad interactions on the unobservable browser type.

Modelled conversions are reported with the same granularity as observed conversions. This includes dimensions such as conversion totals, attribution path and conversion values. In the 'Conversions' column, Google reports both modelled and observed conversions.

Note: Offline conversion imports and user accounts with very few weekly conversions currently may not incorporate certain types of modelling.

Benefits of modelled online conversions

  • Holistic measurement across all your ads traffic: Gain a more accurate picture of your advertising outcomes (ROI), and a complete picture of the conversion path across devices and channels resulting from ad interactions.
  • Efficient campaign optimisation: Modelled conversions help you optimise your campaigns more effectively and achieve better business results.
    • Privacy regulations and technology limitations mean that we lose observation for certain cohorts of users (for example, unconsented users, or users using particular device types or browsers). This means that our automated bidding algorithms will need to make optimisation decisions based on incomplete data, resulting in biased learning. As a result, automated bidding may deprioritise those cohorts since they have a lower reported performance, leading to overall poorer performance by the bidder. Modelling solves for these biases and corrects them in overall reporting to ensure that automated bidding has access to a more representative performance data. Learn more About automated bidding
  • Accurate privacy centric measurement: Modelled conversions use data that doesn't identify individual users to estimate conversions that Google is unable to observe directly. This can offer a more complete report of your conversions.This approach is in direct contrast with non privacy-safe tactics like fingerprinting, which relies on heuristics, such as IP address, and attempts to identify and track individual users. Google has a strict policy against utilising fingerprinting for ads personalisation, as it doesn't allow reasonable user control and transparency.

Google's conversion modelling approach

Google solutions work across a broad array of users allowing the accuracy of our conversion models to be validated across a large set of ad interactions and conversion actions through several key dimensions:

  • Scale: We have access to a magnitude and diversity of ad interactions across channels across various parts of the funnel. This provides us with comprehensive data around how different users react to different types of ads, regardless of where they are in the funnel and across all channels.
  • Accuracy: Our high signed-in user base allows our sophisticated modelling techniques to operate independent of cookies or other identifiers since we can infer a rich set of behavioural data across a representative set of opted-in users.
  • Coverage: Many websites use Google tags, which means that our conversion models are validated across a large set of different conversion actions. Conversion modelling uses data that doesn't identify the user in order to quantify conversions that Google is unable to observe directly. Our model is then trained uniquely on each advertiser, generating unique results.
  • Technical expertise: Google’s expertise in machine learning is a key capability allowing us to model with highest quality. We have mastered this throughout our measurement products that have employed modelling for years (Google Ads automated bidding and shop visits) as well as products beyond measurement (for example, driverless cars and YouTube recommendations).
  • Actionability: Google’s modelled conversions are surfaced in campaign reporting but are also tied to optimisation and bidding. This renders the data actionable as it works towards your business goals.

Examples of available modelling for online conversions

Some of the most important conversion modelling efforts we have available are:

Modelling for third-party cookie limitations

Some browsers (for example, Safari and Firefox) don't allow conversion measurement using third-party cookies. If you rely on third-party cookies for conversion measurement, you will experience conversion modelling in line with your websites’ traffic on those browsers (desktop and mobile). Learn how to improve modelling by upgrading to the global site tag

Modelling for first-party cookie limitations

Some browsers (for example, Safari) limit the amount of time that first-party cookies are allowed. You will experience conversion modelling in line with your share of latent conversions beyond that window. Learn how to improve modelling by using enhanced conversions

Modelling for EU cookie consent limitations

Regulations in some countries require that advertisers obtain consent for use of cookies related to advertising activities. Advertisers who have adopted consent mode will experience conversion modelling in line with their unconsented users. Conversions are modelled for unconsented users.

Impact of iOS 14

Apple’s App Tracking Transparency (ATT) policywill require developers to ask for permission when they use certain information from other companies’ apps and websites for advertising purposes. Google won't use information (such as IDFA) that falls under the ATT policy. In line with this, conversions whose ads originate on ATT impacted traffic will experience modelling. Make sure that your website can accept arbitrary URL parameters for the best modelling.

Cross-device conversions

When a user starts their journey on one device with an ad interaction, and completes the conversion on another, it may not be possible to attribute the conversion to the ad interaction. Google observes data from the large number of signed-in users on Google properties to extrapolate similar behaviour across all users. All cross-device conversions are modelled.

Note: The share of these conversions that can be recovered via Google Ads depends on the amount of observable data that we have for each situation and the representativeness of that observable data (for instance, how realistically it resembles the entire user base of a particular advertiser). Recovery rates vary, depending on the problem that we’re addressing. The more observable data, the better the model quality. Learn how you can improve upon this by implementing the global site tagconsent mode, and enhanced conversions.

Principles of online conversion modelling

Constant quality improvement

Like all other products, our data scientists continuously make algorithm improvements to increase accuracy and scale of modelling. We regularly introduce new products to give us new sources of observable data, which fine tune our modelling (for example, enhanced conversions and consent mode can give us more observed data).

Sophisticated techniques on checking for accuracy

We use techniques like holdback validation to check the accuracy of our modelling (for example, we hold back a portion of observed conversions and model for that slice). Then we compare the modelled results to the actual observed conversions that we held back, and measure inaccuracies and biases and continuously tune our models. Similar methods are broadly used in machine learning.

Rigorous thresholds for reporting

We only include modelled conversions in our reporting when we have high confidence that conversions actually occurred as a result of ad interactions. We avoid systematically reporting more conversions than reality and always aim to minimise over-reporting. This means that for some users, we don’t observe enough conversions on a regular basis to be able to confidently model. In these cases, we do not report any modelled conversions.

Each gap is addressed via a unique modelling methodology

Because we identify different gaps in measurement and different types of observable data are needed and available, we have different types of models for different types of gaps. We also use techniques that eliminate double-counting across various types of models. We know that conversion rates vary significantly by advertising channel, and as a result, we build separate models for each channel and ad interaction type (impressions vs. clicks).

The outcome of each model is unique to your business and user behaviour

Once a general modelling algorithm is determined to address a specific observation gap, we apply that algorithm to each advertiser’s data separately and arrive at unique results that reflect unique user behaviour and conversion rates for that advertiser. For example, if your users have a very high tendency to start their journey on one device and convert on another device, there will be a higher than average cross-device modelled conversions reported for you.

Strict policy against fingerprinting

Fingerprinting technologies typically rely on heuristics such as IP addresses that identify users across various touch points and devices and generate a 'fingerprint ID' to identify the user across future interactions. We are not generating such IDs or attempting to identify individual users because it doesn't allow reasonable user control and transparency nor do we let others bring fingerprinting data into our advertising products. Instead, we're aggregating data such as historical conversion rates, device type, time of day and geo to predict the likelihood of conversion event across the set of users who viewed or clicked on an ad.

Communicating significant modelling changes

We constantly run experiments before rolling out any modelling changes, and if we detect a significant reporting and bidding impact, we communicate accordingly.

Automatic integration

Where we can accurately do so, Google will use available data to provide integrated conversion modelling in your conversion reporting and optimisation. In some cases, such as when conversions can't be observed for a set of users that haven't consented to cookies, we'll need data about your consent rates so that we can provide conversion modelling.

Related links

Was this helpful?
How can we improve it?

Need more help?

Sign in for additional support options to quickly solve your issue

Clear search
Close search
Google apps
Main menu
Search Help Centre