Google has made several changes in the Play Store recently so it can improve the overall experience of browsing through the store for an app or game while keeping users safe from bad apps at the same time. Like many other Google apps, artificial intelligence (AI) is at the heart of it. We take a look at some of the ways in which Play Store has changed for the better in the last few months.

Malware attacks on Android devices continue to be a major concern for Google. Behind most of these attacks is a bad app astutely hiding among good apps which makes detecting them hard. Google has found a new way to tackle them and its powered by AI. Dubbed as Play protect, this new security tool examines privacy and security signals for every app on the Play Store to detect potentially harmful signals on time. For this, it uses deep learning to identify and create peer groups of apps with similar functionality. The peer groups are based on not only the categories they belong to, but also on the apps’ metadata, description, user metrics and number of downloads.

So during their daily scans, if the tool comes across an app asking for a permission which its peer apps don’t have, it will be immediately red flagged.

If you go to categories such as Trending or Top apps in Play store, you will find the most bizarre results at the top of the page. Apps replete with advertisements, frequent crashes and published by anonymous sources often show ahead of reliable apps. To curb such apps, Google will use AI to improve the search and discovery algorithm in the Play Store. The company will now include app quality signals in the ranking algorithms. To create those signals, it will take into account factors such as performance data, user engagement and user ratings of every app on the Play Store. This means users will get to see quality apps ahead of some random or poorly developed app.

According to Google, most people do not use specific app names while browsing through the store. The keywords punched into the search bar are often random, suggesting that people are looking for a wider variety of options. To ensure they would get to see a wider array of apps, Google has deployed an AI-based neural network which tries to predict words around a given word. For example, if you search for a photo, it will also look for apps which allow sharing of photos. So you won’t just get photo editing apps but photo sharing apps as well.

The post Artificial intelligence is making Google Play Store better appeared first on Artificial Intelligence.

Google has released some details from the Security and Privacy team about how Google Play is being curated, and machine learning plays a big part.

Google has two basic goals for applications in the Play Store: safety and exposure. The Security and Privacy team wants to weed out apps with malware, but they’re also concerned about applications that ask for broad permissions that might not be needed. In turn, when good apps that follow good practices are found, the team wants them to be featured in the Play Store.

One of the ways they do this is by using what is called “peer groups”. Applications with similar capabilities are grouped together. Apps like Spotify and Pandora (for example) are different from each other, but they have the same basic functions and are designed to stream music to your Android using details from your account with each service. The same goes for Twitter and Facebook or apps like coloring books. When they do the same basic things, they get lumped together. This makes it easier to study what the apps are doing, how they are doing it, and if they should be doing it at all.

They are then analyzed to see what they request from your device when it comes to personal data. Ideally, every app in a peer group will request the same types of information and have a good reason to do so. But sometimes, one will be an outlier. Google gives the example of a coloring book app that requests fine location details through GPS. Other coloring book apps don’t do this, so one that does would be subject to further review by the Security and Privacy team.

There are too many apps in Google Play for humans to do this effectively, so Google has employed some machine learning techniques to automate much of the process. Deep learning algorithms study the language in the app, data about what the app does and how it does is analyzed by computer, and the peer groups themselves are built by these machines based on things like app metadata and text descriptions as well as metrics like user installs.

Google does plenty to keep malware from getting on your phone through Google Play, but this is also to educate developers about the complex (very) permission model Android uses. this is a pretty cool way to use computers that help users and developers, and it’s great that Google is willing to share some information about how it’s being done.

The post Google is using deep learning and data analysis to curate the Play Store appeared first on Artificial Intelligence.