Deep Neural Networks For Online Trend Prediction

Recent studies show that Deep Neural Networks can be highly effective for trend prediction applications. These studies, however, typically focus on offline applications. In this study we explore deep neural networks (DNNs) for trend prediction in online streaming applications. We reformulate the trend prediction problem for streaming applications, and present an efficient algorithm for online trend segmentation and updating, which predicts the time for the current trend to change and the slope of the next trend. Four DNNs, i.e. LSTMs, CNNs, BiLSTMs and TCNs, are implemented and evaluated across four different datasets using walk-forward validation. The recurrent DNN models, specifically the BiLSTM, outperform the other DNNs. The findings suggest that DNNs can be effectively used for online trend prediction in real-time applications.