Recent forecasts predict that the amount of cellular data traffic will significantly increase within the next few years. The reason for this trend is on the one hand the high growth rate of mobile Internet users and on the other hand the growing popularity of high bandwidth streaming applications. Given the fact that cellular networks (e.g. UMTS) have only limited capacity, the existing network infrastructure will soon reach its limits. As a result, the concept of traffic offloading attracts more and more attention in research since it aims at the reduction of cellular traffic by shifting it to local-area networks like Wifi. One particular form of traffic offloading is known as opportunistic traffic offloading and follows the basic idea to shift traffic from the cellular network to the level of inter-device communication of mobile devices. To perform opportunistic traffic offloading in an efficient way, assumptions about the prospective inter-device connectivity of the mobile devices have to be made. In general, the more inter-device connections are possible the more traffic can be offloaded. To utilize this fact, we developed the TOMP system. TOMP is the first opportunistic traffic offloading system that uses movement predictions of mobile users to analyze the prospective inter-device connectivity. In this paper we propose three different metrics for analyzing movement predictions and present an algorithm, which uses these metrics to utilize an efficient opportunistic traffic offloading. To evaluate TOMP, we show by simulation that we can save up to 40% of cellular messages in comparison to a typical cellular network.