AI RESEARCH
Don't Learn the Shape: Forecasting Periodic Time Series by Rank-1 Decomposition
arXiv CS.LG
•
ArXi:2605.07222v1 Announce Type: new How few parameters do we really need to forecast a periodic time series? An hourly electricity series, reshaped as a 24-row matrix with one column per day, is approximately rank-1: a daily shape modulated by a daily level (median centered rank-1 energy 0.82 on GIFT-Eval). Should we learn the shape? Smoothing, shrinkage, and low-rank fits all seem like obvious upgrades over the simple average of the last K=2 cycles.