Deep autoregressive models with spectral attention

Moreno-Pino, Fernando; Olmos, Pablo M.; Artés‐Rodríguez, Antonio

doi:10.1016/j.patcog.2022.109014

Cited by 6 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the inherent unpredictability in financial time series, researchers have turned to decomposition techniques to reveal more detailed information at varying frequency levels [5] for betterinformed portfolio management [2,29] and risk modeling [3]. Recent works have explored time series forecasting or classification with frequency representation combined with deep learning [20,23,40,43]. In our work, we used the wavelet transform as a time-frequency representation of the time series.…”

Section: Visual Time Series Forecastingmentioning

confidence: 99%

From Pixels to Predictions: Spectrogram and Vision Transformer for Better Time Series Forecasting

Zeng,

Kaur,

Siddagangappa

et al. 2023

4th ACM International Conference on AI in Finance

View full text Add to dashboard Cite

Time series forecasting plays a crucial role in decision-making across various domains, but it presents significant challenges. Recent studies have explored image-driven approaches using computer vision models to address these challenges, often employing lineplots as the visual representation of time series data. In this paper, we propose a novel approach that uses time-frequency spectrograms as the visual representation of time series data. We introduce the use of a vision transformer for multimodal learning, showcasing the advantages of our approach across diverse datasets from different domains. To evaluate its effectiveness, we compare our method against statistical baselines (EMA and ARIMA), a state-of-the-art deep learning-based approach (DeepAR), other visual representations of time series data (lineplot images), and an ablation study on using only the time series as input. Our experiments demonstrate the benefits of utilizing spectrograms as a visual representation for time series data, along with the advantages of employing a vision transformer for simultaneous learning in both the time and frequency domains.

show abstract