Scale-Invariant Conditional VAE for Coarse-Grained Economic Time-Series Forecasting
Results show that replacing or augmenting the original training set with SI-CVAE–generated data yields consistent accuracy gains across multiple forecasting baselines, and that SI-CVAE attains higher synthetic-data quality than state-of-the-art generators on standard metrics.
Jian-Ping Zhu, Lei Wang, Yang Chen et al.
· 0 citations