App recommendation is now widely used to select apps for production and life. Nevertheless, current methods excel in improving retrieval efficiency and reducing information overload in the app field, they often prioritize accuracy without sufficiently considering potential information leakage during the recommendation process. Such an oversight compromises user information security, making the process unreliable. That is, it cannot effectively recommend the apps to users when preserving user’s privacy. Thus, we introduce APP-Rec, which incorporates package recommendation and differential privacy techniques. Not only does this approach enhance the accuracy of recommendations, but it also ensures the privacy of user preferences. Integrating this method into mobile and industrial app stores can potentially elevate users’ and employees’ satisfaction, paving the way for greater convenience in daily life and better industrial productivity.

With the prosperity of the mobile Internet, the abundance of data makes it difficult for users to choose their favorite app. Thus, mobile app recommendation as an emerging topic attracts lots of attention. However, existing methods for app recommendation rarely consider recommendation accuracy under the privacy representation of user preferences. To address this problem, we propose a privacy-aware app package recommendation method named APP-Rec. Specifically, in this method: 1) treat an app and its associated heterogeneous entities (APP-Rec considers not only the apps themselves but also a variety of related factors—collectively referred to as heterogeneous entities, such as app category and app neighbors) as an app package and extract comprehensive features from the app package using an intrapackage attention network and an interpackage attention network to improve app recommendation; and 2) design a privacy module utilizing Laplace noise to achieve privacy preservation of user prefer...