HAELT, a hybrid ResNet-attention-LSTM-Transformer ensemble, reports the highest F1 (0.6421) for hourly AAPL price direction on one 242-sample test set, but with AUC 0.554 below logistic regression.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HAELT: A Hybrid Attentive Ensemble Learning Transformer Framework for High-Frequency Stock Price Forecasting
HAELT, a hybrid ResNet-attention-LSTM-Transformer ensemble, reports the highest F1 (0.6421) for hourly AAPL price direction on one 242-sample test set, but with AUC 0.554 below logistic regression.