Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks

Abstract

Multivariate time series forecasting is an important machine learning problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation. Temporal data arise in these real-world applications often involves a mixture of long-term and short-term patterns, for which traditional approaches such as Autoregressive models and Gaussian Process may fail. In this paper, we proposed a novel deep learning framework, namely Long- and Short-term Time-series network (LSTNet), to address this open challenge. LSTNet uses the Convolution Neural Network (CNN) and the Recurrent Neural Network (RNN) to extract short-term local dependency patterns among variables and to discover long-term patterns for time series trends. Furthermore, we leverage traditional autoregressive model to tackle the scale insensitive problem of the neural network model. In our evaluation on real-world data with complex mixtures of repetitive patterns, LSTNet achieved significant performance improvements over that of several state-of-the-art baseline methods. All the data and experiment codes are available online.

Accepted by SIGIR 2018

References in corpus (5)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Learning to Diagnose with LSTM Recurrent Neural Networks
• Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables
• Recurrent Neural Networks for Multivariate Time Series with Missing Values
• Estimating Structured Vector Autoregressive Model

Cited by in corpus (13)

• A Survey on Anomaly Detection for Technical Systems using LSTM Networks
• Exploring Interpretable LSTM Neural Networks over Multi-Variable Data
• A Memory-Network Based Solution for Multivariate Time-Series Forecasting
• R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting
• Multi-variable LSTM neural network for autoregressive exogenous model
• A Time-Temperature Dataset for the Strawberry Cold Chain Across Multiple Shipments and Locations
• Autoregressive Convolutional Recurrent Neural Network for Univariate and Multivariate Time Series Prediction
• seq2graph: Discovering Dynamic Dependencies from Multivariate Time Series with Multi-level Attention
• AutoAI-TS: AutoAI for Time Series Forecasting
• There is no Artificial General Intelligence
• The Effectiveness of Discretization in Forecasting: An Empirical Study on Neural Time Series Models
• Towards Better Forecasting by Fusing Near and Distant Future Visions
• Stanza: A Nonlinear State Space Model for Probabilistic Inference in Non-Stationary Time Series