ARMA Block: A CNN-Based Autoregressive and Moving Average Module for Long-Term Time Series Forecasting
This work addresses forecasting challenges in time series analysis with a simple, extendable module, though it is incremental as it builds on ARIMA and CNN concepts.
The paper tackles long-term time series forecasting by proposing a CNN-based ARMA block that directly performs multi-step forecasting, achieving competitive accuracy on nine benchmark datasets, especially those with strong trend variations.
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.