Recently, Google has ramped up their efforts to tie clicks on ads to store traffic.  According to the company, On March 29, they’ve captured over four million store visits after users clicked on an ad, which is up from one billion a little less than a year ago, and is set to rapidly expand that number.

It was in September that Google extend the store visits measurement program to ads on the Display Network.  Google stated that it had statistically significant visibility into visits to 200 million stores globally.  They are now positioned, according to the company, to make store visits data available to thousands more advertisers, due to the advancements in several components of the measurement process.

Store visits are measured based on aggregated and anonymized data from users who decide to opt into Location History tracking on their phones, Google surveys and mapping technology.  (You can check out more information on how Google captures store visits data by seeing these two articles – Under The Hood: How Google AdWords Measures Store Visits and Google’s Surojit Chatterjee: Here’s Why You Should Trust AdWords Estimated Store Visits.)

According to Google, over the past month, it has shifted to using deep learning models that can train on larger data sets to increase accuracy in prioritizing location signals.  “This allows us to reliably measure more store visits in contexts that are typically tricky, such as in multi-story malls and dense geographies where many business locations are situated close to each other,” Kishore Kanakamedala, director of product management for online-to-offline solutions, wrote in Wednesday’s blog post.

There has been some recent improvements to mapping that includes a refresh of Google Earth and Google Street View images that allow users to get an up-to-date view of where buildings begin and end.  There is even a global effort effort to scan WiFi strength in more buildings to determine business boundaries.

Users were surveyed by Google in order to verify the locations they’ve visited and then reconciled the feedback against its predictions to continue training the models.  Not only that,  Google has teams that are conducting in-person audits and site visits, particularly in high store density areas which will help provide more data.

Google had even added store visits data to distance and location reports in AdWords back in November, which was meant to provide more detail on how far users were from a store location when they clicked on an ad, as well as what areas drove the highest volume of store visits, right down to the postal code.

Source –