Seasonal Encoder-Decoder Architecture for Forecasting

2022/07/08 by Avinash Achar, Achar, Avinash, Soumen Pachal +1
Computer Science · Decision Sciences · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural Networks and Applications #Stock Market Forecasting Methods #Time Series Analysis and Forecasting

paper · pdf · doi:10.48550/arxiv.2207.04113

openalex publication_date 2022/07/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Deep learning (DL) in general and Recurrent neural networks (RNNs) in particular have seen high success levels in sequence based applications. This paper pertains to RNNs for time series modelling and forecasting. We propose a novel RNN architecture capturing (stochastic) seasonal correlations intelligently while capable of accurate multi-step forecasting. It is motivated from the well-known encoder-decoder (ED) architecture and multiplicative seasonal auto-regressive model. It incorporates multi-step (multi-target) learning even in the presence (or absence) of exogenous inputs. It can be employed on single or multiple sequence data. For the multiple sequence case, we also propose a novel greedy recursive procedure to build (one or more) predictive models across sequences when per-sequence data is less. We demonstrate via extensive experiments the utility of our proposed architecture both in single sequence and multiple sequence scenarios.

Related

• Randomized Neural Networks for Forecasting Time Series with Multiple\n Seasonality
• A Policy Gradient-Based Sequence-to-Sequence Method for Time Series Prediction
• Recurrent Neural Networks for Forecasting Time Series with Multiple Seasonality: A Comparative Study
• CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting
• Ensembles of Randomized NNs for Pattern-based Time Series Forecasting