“Every month, more than a billion users come to Google Play to download apps for their mobile devices. While some are looking for specific apps, like Snapchat, others come with only a broad notion of what they are interested in, like ‘horror games’ or ‘selfie apps,’” Google wrote in its blog post. “These broad searches by topic represent nearly half of the queries in Play Store, so it’s critical to find the most relevant apps.”
So to help you find the most relevant apps, Google “trained a neural network to learn how language was used to describe apps.” This, the search engine says, ought to make it easier for folks to find relevant apps, even if they don’t know exactly what they’re looking for.
“We built a Skip-gram model, where the neural network attempts to predict the words around a given word, for example ‘share’ given ‘photo,'” the company explained. So ostensibly, if you look for “selfie,” you’ll be greeted with apps like Snapchat or Instagram.
While Google notes that employing artificial intelligence has certainly helped to provide better results to users, the team is continuously exploring a range of methods to constantly improve the system. And soon, the company hopes to “personalize the app discovery experience for users.” So although there’s not yet your own customized map for navigating the Google Play Store, this might just be the closest thing to it … for now.
