# ARMA Block: A CNN-Based Autoregressive and Moving Average Module for Long-Term Time Series Forecasting

arXiv: https://arxiv.org/abs/2509.10324 · HTML: https://mlsanity.com/paper/2509.10324/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 13 references that are in the map.
- First posted on arXiv 12 Sep 2025.

## Builds on (most cited first, 9 of 9)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [Are Transformers Effective for Time Series Forecasting?](https://mlsanity.com/paper/2205.13504/) (2022)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks](https://mlsanity.com/paper/1703.07015/) (2017)
- [Time-MoE: Billion-Scale Time Series Foundation Models with Mixture of Experts](https://mlsanity.com/paper/2409.16040/) (2024)
- [How Much Position Information Do Convolutional Neural Networks Encode?](https://mlsanity.com/paper/2001.08248/) (2020)

## Abstract (arXiv)

This paper proposes a simple yet effective convolutional module for long-term time series forecasting. The proposed block, inspired by the Auto-Regressive Integrated Moving Average (ARIMA) model, consists of two convolutional components: one for capturing the trend (autoregression) and the other for refining local variations (moving average). Unlike conventional ARIMA, which requires iterative multi-step forecasting, the block directly performs multi-step forecasting, making it easily extendable to multivariate settings. Experiments on nine widely used benchmark datasets demonstrate that our method ARMA achieves competitive accuracy, particularly on datasets exhibiting strong trend variations, while maintaining architectural simplicity. Furthermore, analysis shows that the block inherently encodes absolute positional information, suggesting its potential as a lightweight replacement for positional embeddings in sequential models.