Think Globally, Act Locally: A Deep Neural Network Approach to High-Dimensional Time Series Forecasting

05/09/2019
by   Rajat Sen, et al.
0

Forecasting high-dimensional time series plays a crucial role in many applications such as demand forecasting and financial predictions. Modern real-world datasets can have millions of correlated time-series that evolve together, i.e they are extremely high dimensional (one dimension for each individual time-series). Thus there is need for exploiting these global patterns and coupling them with local calibration for better prediction. However, most recent deep learning approaches in the literature are one-dimensional, i.e, even though they are trained on the whole dataset, during prediction, the future forecast for a single dimension mainly depends on past values from the same dimension. In this paper, we seek to correct this deficiency and propose DeepGLO, a deep forecasting model which thinks globally and acts locally. In particular, DeepGLO is a hybrid model that combines a global matrix factorization model regularized by a temporal deep network with a local deep temporal model that captures patterns specific to each dimension. The global and local models are combined via a data-driven attention mechanism for each dimension. The proposed deep architecture used is a variation of temporal convolution termed as leveled network which can be trained effectively on high-dimensional but diverse time series, where different time series can have vastly different scales, without a priori normalization or rescaling. Empirical results demonstrate that DeepGLO outperforms state-of-the-art approaches on various datasets; for example, we see more than 30 in WAPE over other methods on a real-world dataset that contains more than 100K-dimensional time series.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/28/2015

High-dimensional Time Series Prediction with Missing Values

High-dimensional time series prediction is needed in applications as div...
research
11/09/2021

Learning from Multiple Time Series: A Deep Disentangled Approach to Diversified Time Series Forecasting

Time series forecasting is a significant problem in many applications, e...
research
07/13/2021

Deep Autoregressive Models with Spectral Attention

Time series forecasting is an important problem across many domains, pla...
research
12/15/2021

Optimal Latent Space Forecasting for Large Collections of Short Time Series Using Temporal Matrix Factorization

In the context of time series forecasting, it is a common practice to ev...
research
11/22/2019

Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values

Multivariate time series (MTS) forecasting is widely used in various dom...
research
06/24/2019

Streaming Adaptation of Deep Forecasting Models using Adaptive Recurrent Units

We present ARU, an Adaptive Recurrent Unit for streaming adaptation of d...
research
09/30/2021

PIETS: Parallelised Irregularity Encoders for Forecasting with Heterogeneous Time-Series

Heterogeneity and irregularity of multi-source data sets present a signi...

Please sign up or login with your details

Forgot password? Click here to reset