Towards Robust Predictions Under Extreme Markets: A Hybrid Framework Integrating Adaptive Trend Decomposition and STOA ‐Optimized Deep Learning

Short summary

A new hybrid AI framework integrating adaptive trend decomposition and STOA-optimized deep learning (Transformer-BiLSTM) significantly improves financial time series prediction accuracy and robustness, reducing MAE by ~24% and increasing R² by 0.043 compared to unoptimized baselines.

AI-generated from the title and abstract; the full text is not read.