GPS technology has become an essential part of any travel and, with the development of smartphone technology, it has become accessible to a larger number of users. The development of technology over time has also enabled easier access to different information which can influence travel, and users of these applications have become more connected than ever before. All of this has resulted in one simple fact - existing GPS applications have become obsolete. For this reason, we have set the goal of developing the next generation of GPS applications, which will make significant use of a social component, as well as learning about its users’ interests in order to improve the user experience. The system is designed to use different methods of machine learning, which have to be optimized for use on mobile platforms. We have also developed a functional prototype, which has demonstrated that the existing methods can be used to improve the user experience of GPS mobile applications.