2026
Scale-Invariant Conditional VAE for Coarse-Grained Economic Time-Series Forecasting
IJCAI 2026
Coarse-grained time series (CGTS) are critical for business and macroeconomic analysis. However, CGTS are typically updated infrequently and contain few observations, so model-centric training on raw data is prone to overfitting and degraded forecast accuracy. To address this, we propose SI-CVAE, a