STF-RNN: Space Time Features-based Recurrent Neural Network for predicting people next location

摘要: This paper proposes a novel model called Space Time Features-based Recurrent Neural Network (STF-RNN) for predicting people next movement based on mobility patterns obtained from GPS devices logs. Two main features are involved in operations, namely, the space which is extracted collected data and also time associated timestamps. The internal representation of automatically proposed rather than relying handcraft representation. enables to discover useful knowledge about behaviour more efficient way. Due ability RNN structure represent sequences, it utilized order keep track user history. These tracks help meaningful dependencies as consequence, enhancing performance. results show that STF-RNN provides good improvements people's location compared with state-of-the-art models when applied large real life dataset Geo-life project.