SEOHow Is Automated Conversion Optimization Possible with Google?

How Is Automated Conversion Optimization Possible with Google?

Using the patent for "User Path Abandonment Analysis," this examines how Google processes data from user paths, AdWords Quality Score, and discusses the development of an automation system based on user behavior.

Last month, we looked at Google patent US 2015/0242512 A1 and Google personalization. Before that, we looked at one of its patents on the use of email to impact search rankings. Both of these patents focus on adjusting rankings for users based on behavior, but what happens after the user has clicked the search result and is now on your site?

A Google patent published on September 17, 2015 sheds light on some very interesting ideas addressing just this.

Google Patent US 2015/0262217 A1

Invented by Google’s Neil Hoyne, the patent is entitled, User Path Abandonment Analysis. However upon further digging, it covers far more than simple analysis of user paths. In fact, it lets us view some very interesting core areas of marketing today and into the future, including:

  1. Understanding a bit more of how AdWords Quality Score may work
  2. Understanding how Google will assess various attributes of a website to provide for better information back to the webmaster
  3. The development of a system which auto-adjusts based on user behavior

So the question may as well be, “How do they cover all this in a single patent?” It’s not so much that it’s covered, as it is applicable with each of these areas referenced in the following examples.

Let’s go through and break down the patent to understand how this occurs and see what’s coming soon to a website near you.

User Abandonment

The focus of the entire patent and related images revolves around methods for measuring user abandonment.

In fact, to make sure it covers pretty much everything other than “the user tripped into the bath with a blow dryer in hand,” it repeats specific elements multiple times with only minor adjustments to the technology or application involved.

We won’t get into each iteration, but here are some of the core references on the methods translated into layman’s terms.

From the Abstract:

“One method includes receiving user path data representing a plurality of user paths. The method further includes identifying a plurality of user paths ending with an abandonment event associated with a first resource. The method further includes determining a first abandonment metric indicating a first plurality of the identified user paths having a first condition of a characteristic. The method further includes determining a second abandonment metric indicating a second plurality of the identified user paths having a second condition of the characteristic. The method further includes determining whether the abandonment events associated with the first resource are at least partially related to the characteristic based on a comparison of the first abandonment metric and the second abandonment metric.”

Essentially, what it’s saying here is that the method is to measure one segment of user path data that leads to an abandonment. Further, the method requires the measuring of different segments of user path data, which leads to abandonment. With this data in hand, conclusions can be made involving where a problem may be.

For example, the measurement could be related to users entering on a specific page from different sources, like paid search versus organic search. In this example, if the abandonment rate on organic was high but the abandonment rate on paid was low, it could be determined that the page itself is not the problem, but rather the source. If the abandonment rate was high on both, it could be determined that the page itself is the issue.

Also, the patent includes purely on-site conditions. For instance, an image appears on a page with content from provider A and the same image appears with content from provider B. If the page has a higher abandonment rate for one than the other, it could be determined that the image only relates to one. But, if the image produces a high abandonment rate on both pages where a different image did not, one could determine that the image itself is poor or does not relate to the content of either page.

Now that we’ve got the Cliffs Notes down on the core method the patent outlines for using multiple conditions to determine the likelihood of a specific cause for a higher abandonment rates, it’s easy to see how all this relates to Quality Scoring in AdWords.

In this patent, there are multiple mentions of paid applications and the use of these measuring techniques to determine the performance of an ad. Think about AdWords ad groups and the scoring of each specific keyword, for example.

One of the interesting mentions in the patent is in Part 47 where it is written:

Save and publish“In another illustrative implementation, system 150 may determine that non-converting paths 165 with abandonment events associated with a cancellation page of a media service provider frequently include user interactions with at least four technical support webpages of the service provider prior to abandonment on the cancellation page. This may indicate that it is user dissatisfaction with the technical support pages, rather than the cancellation page, contributing to the abandonment events. In some such implementations, system 150 may provide a recommendation that the content provider consider revising the technical support section of its website.”

Note: The patent image that includes system 150 follows below.

Here we see the beginning of a larger point: the measurement and interpretation of common data characteristics to determine trends in abandonment provides greater detail regarding service and conversion loss.

Add to this multiple references to giving the content provider access to information regarding abandonment issues, and we can see that Google is giving website owners greater insight into their web traffic and abandonment points.

Section 54 Includes:

“This may help the content provider decide whether the resource should be modified for better interaction with the first device.”

What that example refers to is the idea of a user leaving a resource on one device, only to revisit said resource on another device at a later point in time, it serves to illustrate that Google is seeking to provide greater information to website owners. But that’s not the most interesting part, in my opinion.

In a short-but-sweet mention in Section 49, we read:

“In some implementations, system 150 may be configured to take one or more actions to reduce a likelihood of future abandonments (e.g., when system 150 determines that a series of similar interactions is likely at least partially responsible for abandonments). FIG. 4 illustrates a process 400 for reducing a likelihood of user abandonments according to an illustrative implementation. Abandonment analysis module 152 of system 150 may determine that the abandonment events are at least partially related to the series of similar user interactions based on a comparison of first abandonment metric 176 and second abandonment metric 178 (405).”

Now, let’s really think about what that means. To aid in this, here’s the image with the key reference points:

automation-patent

Basically, this patent says that the analysis system designed to determine the causes of abandonment (150) may be configured to take actions to reduce it. This may simply mean the pausing of a paid search keyword.

Personally, I find it exciting that the scope of the patent includes much more than this, as it can easily extend to content placement, layout changes, and so on.

One doesn’t have to think too long before seeing applications of this that Google itself would use. I’m imagining a world in which multiple layouts can be built into a site, and it’s set to test the various layouts against different traffic sources, user groups, or paths while automatically adjusting itself to display the best layout for the specific audience.

Conclusion

Patent US 215/0262217 A1 is definitely one of the more interesting patents to come out of Google in the past few months. It gives us interesting insight into the direction Google is looking regarding website data analysis, and how that data might be used to aid both its paid search department and website owners.

If this patent is any guide, it’s going to be a very fascinating few years ahead in analytics and conversion optimization.

Resources

The 2023 B2B Superpowers Index

whitepaper | Analytics The 2023 B2B Superpowers Index

8m
Data Analytics in Marketing

whitepaper | Analytics Data Analytics in Marketing

10m
The Third-Party Data Deprecation Playbook

whitepaper | Digital Marketing The Third-Party Data Deprecation Playbook

1y
Utilizing Email To Stop Fraud-eCommerce Client Fraud Case Study

whitepaper | Digital Marketing Utilizing Email To Stop Fraud-eCommerce Client Fraud Case Study

1y