One of the latest models introduced to help advertisers gain a better understanding of attribution is Google Data-driven.
What is the Google Data-Driven Model?
Unlike rule-based models, Data-driven attribution uses machine learning to evaluate all the converting and non-converting paths across your AdWords account and identifies the proper credit for each interaction.
The model considers:
- Number of ad interactions
- Order of exposure
- Ad creative
- Other factors to determine which keywords and clicks are the most effective at driving results
This is Google’s attempt to build an attribution measurement that can be applied to campaigns and immediately start providing actionable data.
In other words, Data-driven looks at all the clicks on your search ads, then it compares the click paths of customers who convert vs. the click path of customers who don’t.
The model identifies patterns of clicks that lead to conversions and then they basically overlay that onto your campaigns and tell you how valuable your campaigns are based on this wide array of search behavior.
IMPORTANT: Google’s data-driven model does not take into account clicks from other channels such as Facebook or Amazon. This is for AdWords data ONLY. Click here to learn more about “Google Attribution” (which is Google’s latest solution to better understand attribution across ALL channels).
How Google Data-driven Model Works
If you’re feeling confused, let’s use the example Google provides on how Data-driven works:
You own a tour company in New York City, and you use conversion tracking to track when customers purchase tickets on your website. In particular, you have one conversion action to track purchases of a bike tour in Brooklyn.
Customers often click a few of your ads before deciding to purchase a ticket.
Your data-driven attribution model finds that customers who click your “Bike tour New York” ad first, and then later click “Bike tour Brooklyn waterfront,” are more likely to purchase a ticket than users who only click on “Bike tour Brooklyn waterfront.”
So the model redistributes credit in favor of the “Bike tour New York” ad and its associated keywords, ad groups, and campaigns.
Now, when you look at your reports, you have more complete information about which ads are most valuable to your business.
Our Experts Test The Google Data-Driven Model:
Kate Lynch, Retail Search Manager at CPC Strategy manages advertising efforts for a shoe retailer. In May 2017, she decided to switch the account over from “Last Click” attribution to the new “Data-driven” model.
Prop-Tip: Keep in mind, the data driven model does require some time to ramp up. So, even though Kate switched to the new model in May – she didn’t see any real impact on the account until September 2017.
Starting in September and through to February 2018, Kate noticed that her non branded campaigns were having a significant impact on getting customers to convert.
Previously, using the “Last Click” model – she couldn’t see this data and overall it looks like her non-branded campaigns were not performing well.
“With the new Data-Driven model, we definitely saw a lift in our non branded performance,” she said.
In fact, the top 3 campaigns (based on spend and best selling items) were all non-branded campaigns.
“It was beneficial for us to know that those non-branded campaigns had impacted our customers and assisted in getting them to eventually convert.”
As a result, Kate shifted budget to increase spend on her non-branded campaigns 171%. Conversions increased 173% and revenue increased 180%.
“Overall, we discovered that those non branded campaigns were having a positive effect on our conversions. If I didn’t implemented the Data-driven model, I would not have known that.”
“Ultimately, I decided it was in the best interest of the client to stay on the Data-driven model because it’s able to give credit to the all the AdWords campaigns that are leading to conversions – not just the last ad they click on before converting.”
Data Requirements for Google’s Data-driven Model:
Keep in mind, Data-driven attribution requires a certain amount of data to create a precise model for how your conversions should be attributed. Because of this, not all advertisers will see an option for data-driven attribution.
As a general guideline, for this model to be available, an account must have:
- At least 15,000 clicks, and
- At least 600 conversions within 30 days
How long does it take to Google to collect data?
Google will start preparing a data-driven model from the moment you receive the minimum necessary attribution data.
Once they have collected sufficient data for the model for 30 consecutive days, you will see the data in AdWords. If you don’t have enough data, you won’t see an option to use data-driven attribution.
Pro-tip: Because eligibility for data-driven attribution is determined by the data for each conversion action, you may see data-driven attribution for some of your website and Google Analytics conversion actions, and not for others.
Do I have to maintain these data thresholds?
Once you’re using data-driven attribution, you won’t be able to continue using this model if your data drops below 10,000 clicks for the account or 400 conversions for the conversion action within 30 days.
According to Google, you will receive an alert when your data drops below this level, and, after 30 days of continued low data, your conversion action will be switched to a linear attribution model.
Pro-Tip: In our experience using Data-driven, Google did not notify us when our data dropped below the requirement. It also automatically defaulted the account to another model (example, “Linear”).
If the decrease in data is unexpected, you may want to check your conversion tracking tag, the status on your “Conversion actions” page, your conversion action settings, and other account settings to make sure everything is working properly.
Additional Attribution Models Available
If data-driven attribution isn’t available to you, AdWords does offer other attribution models that don’t have data requirements.
To help explain how each model works, we’ve included the example below:
Selena finds teeki.com (a yoga apparel company) by clicking one of it’s AdWords ads. She returns one week later by clicking over from Facebook. That same day, she comes back a third time via one of Teeki’s email campaigns, and a few hours later, she returns again directly and buys a pair of floral yoga pants.
- Last AdWords Click attribution model: In this case, the first and only click to the Paid Search channel —would receive 100% of the credit for the sale.
- First Click attribution model: The first touchpoint—in this case, the Paid Search channel—would receive 100% of the credit for the sale.
- Linear attribution model: Each touchpoint in the conversion path—in this case the Paid Search, Social Network, Email, and Direct channels—would share equal credit (25% each) for the sale.
- Time Decay attribution model: In this case the touchpoints closest in time to the sale or conversion get most of the credit. In this particular sale, the Direct and Email channels would receive the most credit because the customer interacted with them within a few hours of conversion. The Social Network channel would receive less credit than either the Direct orEmail channels. Since the Paid Search interaction occurred one week earlier, this channel would receive significantly less credit.
- Position Based attribution model: 40% credit is assigned to each the first and last interaction, and the remaining 20% credit is distributed evenly to the middle interactions. In this example, the Paid Search and Direct channels would each receive 40% credit, while the Social Network and Email channels would each receive 10% credit.
For more on Google’s data-driven model, email [email protected]