Researchers have introduced McWC, a novel model designed for long-term time series forecasting that addresses limitations in existing methods. McWC separately models cyclicity, trend, and crucially, inter-channel correlations, which are often overlooked. The model employs a multi-layer cyclicity construction module, a multi-layer perceptron for inter-channel correlations, and a multi-level wavelet decomposition module for frequency information. Experiments on six real-world datasets show that McWC achieves state-of-the-art performance with improved computational efficiency and historical information extraction capabilities. AI
RANK_REASON The cluster contains a research paper detailing a new model for time series forecasting. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →