Google Maps has one of the most elaborate mapping databases with over 1 billion kilometres in more than 220 countries and territories around the world and the tech giant has been improving both the data and methods to use this data.
One of the biggest features is that it can calibrate the traffic you’ll meet on the way. Google has shed some light on the process that allows them to accurately detect the movement of traffic.
When a person uses Google Maps to navigate they are shown whether the traffic along their route is heavy or light, an estimated travel time, and the estimated time of arrival (ETA).
When people navigate with Google Maps, aggregate location data can be used to understand traffic conditions on roads all over the world. But while this information helps find current traffic estimates —whether or not a traffic jam will affect your drive right now—it doesn’t account for what traffic will look like 10, 20, or even 50 minutes into your journey.
To predict what traffic will look like in the near future, Google Maps analyzes historical traffic patterns for roads over time. The software then combines this database of historical traffic patterns with live traffic conditions, using machine learning to generate predictions based on both sets of data.
Since the start of the Covid-19 pandemic, traffic patterns around the globe have shifted dramatically. Google claims they saw up to a 50% decrease in worldwide traffic when lockdowns started in early 2020. Since then, parts of the world have reopened gradually, while others maintain restrictions.
To account for this sudden change, Google Maps recently updated their models to automatically prioritize historical traffic patterns from the last two to four weeks and deprioritizing patterns from any time before that.