Foundations of Sequence-to-Sequence Modeling for Time Series

2018/05/09 by Vitaly Kuznetsov, Zelda Mariet, Kuznetsov, Vitaly +1
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Forecasting Techniques and Applications #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Stock Market Forecasting Methods #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.1805.03714

openalex publication_date 2018/05/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The availability of large amounts of time series data, paired with the performance of deep-learning algorithms on a broad class of problems, has recently led to significant interest in the use of sequence-to-sequence models for time series forecasting. We provide the first theoretical analysis of this time series forecasting framework. We include a comparison of sequence-to-sequence modeling to classical time series models, and as such our theory can serve as a quantitative guide for practitioners choosing between different modeling methodologies.

Citations

• Autoregressive Conditional Heteroscedasticity with Estimates of the Variance of United Kingdom Inflation
• Generalized autoregressive conditional heteroskedasticity
• Long Short-Term Memory
• Sequence to Sequence Learning with Neural Networks
• DeepAR: Probabilistic Forecasting with Autoregressive Recurrent Networks
• R2N2: Residual Recurrent Neural Networks for Multivariate Time Series Forecasting
• Long-term Forecasting using Higher Order Tensor RNNs

Related

• Time Series Analysis and Modeling to Forecast: a Survey
• Tailored Architectures for Time Series Forecasting: Evaluating Deep Learning Models on Gaussian Process-Generated Data
• Respecting Time Series Properties Makes Deep Time Series Forecasting Perfect
• Decomposing the Time Series Forecasting Pipeline: A Modular Approach for Time Series Representation, Information Extraction, and Projection
• Time Series Analysis: yesterday, today, tomorrow