A Deep Structural Model for Analyzing Correlated Multivariate Time Series

Multivariate time series are routinely encountered in real-world applications, and in many cases, these time series are strongly correlated. In this paper, we present a deep learning structural time series model which can (i) handle correlated multivariate time series input, and (ii) forecast the targeted temporal sequence by explicitly learning/extracting the trend, seasonality, and event components. The trend is learned via a 1D and 2D temporal CNN and LSTM hierarchical neural net. The CNN-LSTM architecture can (i) seamlessly leverage the dependency among multiple correlated time series in a natural way, (ii) extract the weighted differencing feature for better trend learning, and (iii) memorize the long-term sequential pattern. The seasonality component is approximated via a non-liner function of a set of Fourier terms, and the event components are learned by a simple linear function of regressor encoding the event dates. We compare our model with several state-of-the-art methods through a comprehensive set of experiments on a variety of time series data sets, such as forecasts of Amazon AWS Simple Storage Service (S3) and Elastic Compute Cloud (EC2) billings, and the closing prices for corporate stocks in the same category.

[1]  Yoshua Bengio,et al.  On the Properties of Neural Machine Translation: Encoder–Decoder Approaches , 2014, SSST@EMNLP.

[2]  Alexander M. Rush,et al.  Character-Aware Neural Language Models , 2015, AAAI.

[3]  Salim Lahmiri,et al.  Minute-ahead stock price forecasting based on singular spectrum analysis and support vector regression , 2018, Appl. Math. Comput..

[4]  Eric R. Ziegel,et al.  Analysis of Financial Time Series , 2002, Technometrics.

[5]  Guoqiang Peter Zhang,et al.  Time series forecasting using a hybrid ARIMA and neural network model , 2003, Neurocomputing.

[6]  Andrea Fumi,et al.  Fourier Analysis for Demand Forecasting in a Fashion Company , 2013 .

[7]  Benjamin Letham,et al.  Forecasting at Scale , 2018, PeerJ Prepr..

[8]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[9]  Beveridge-Nelson-Stock-Watson Decomposition,et al.  Structural Time Series Models , 2004 .

[10]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[11]  K. Hipel,et al.  Time series modelling of water resources and environmental systems , 1994 .

[12]  Steven L. Scott,et al.  Inferring causal impact using Bayesian structural time-series models , 2015, 1506.00356.

[13]  Sepp Hochreiter,et al.  The Vanishing Gradient Problem During Learning Recurrent Neural Nets and Problem Solutions , 1998, Int. J. Uncertain. Fuzziness Knowl. Based Syst..

[14]  Trevor Darrell,et al.  Long-term recurrent convolutional networks for visual recognition and description , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  A. Harvey,et al.  Estimation Procedures for Structural Time Series Models , 1990 .

[16]  Josh Patterson,et al.  Deep Learning: A Practitioner's Approach , 2017 .

[17]  P. Young,et al.  Time series analysis, forecasting and control , 1972, IEEE Transactions on Automatic Control.

[18]  Jonathan D. Cryer,et al.  Time Series Analysis , 1986 .

[19]  Ping-Feng Pai,et al.  A hybrid ARIMA and support vector machines model in stock price forecasting , 2005 .