RouteTS framework forecasts time series by optimizing data domains

Researchers have introduced RouteTS, a novel framework for time series forecasting that addresses the limitations of existing methods by processing data in both the frequency and time domains. This approach partitions the frequency spectrum based on amplitude, assigning dominant frequencies to a frequency-domain predictor for preserving periodic structures and residual energy to a time-domain MLP for modeling local variations. Experiments show RouteTS achieves competitive accuracy and computational efficiency across various real-world datasets. AI

IMPACT Offers a principled solution for time series forecasting by optimizing computational domains for different data characteristics.

RANK_REASON The cluster contains a research paper detailing a new method for time series forecasting. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv stat.ML →

• arXiv
• multilayer perceptron
• RouteTS

• paper
• other

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →