# Two-Stage Framework for Seasonal Time Series Forecasting

arXiv: https://arxiv.org/abs/2103.02144 · HTML: https://mlsanity.com/paper/2103.02144/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 18 references that are in the map.
- First posted on arXiv 3 Mar 2021.

## Builds on (most cited first, 6 of 6)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Self-supervised Learning: Generative or Contrastive](https://mlsanity.com/paper/2006.08218/) (2020)
- [Time-Contrastive Networks: Self-Supervised Learning from Video](https://mlsanity.com/paper/1704.06888/) (2017)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigation](https://mlsanity.com/paper/1811.10092/) (2018)
- [RobustPeriod: Time-Frequency Mining for Robust Multiple Periodicity Detection](https://mlsanity.com/paper/2002.09535/) (2020)

## Built on by (most cited first, 1 of 1)

- [Robust Dominant Periodicity Detection for Time Series with Missing Data](https://mlsanity.com/paper/2303.03553/) (2023)

## Abstract (arXiv)

Seasonal time series Forecasting remains a challenging problem due to the long-term dependency from seasonality. In this paper, we propose a two-stage framework to forecast univariate seasonal time series. The first stage explicitly learns the long-range time series structure in a time window beyond the forecast horizon. By incorporating the learned long-range structure, the second stage can enhance the prediction accuracy in the forecast horizon. In both stages, we integrate the auto-regressive model with neural networks to capture both linear and non-linear characteristics in time series. Our framework achieves state-of-the-art performance on M4 Competition Hourly datasets. In particular, we show that incorporating the intermediate results generated in the first stage to existing forecast models can effectively enhance their prediction performance.