A Transformer-GRU hybrid is benchmarked for daily Bitcoin and Ethereum price prediction and beats four baselines on error metrics, but the Bitcoin gain over BiGRU is not significant and the architecture is not novel.
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
REJECT 1representative citing papers
citing papers explorer
-
A Novel Hybrid Approach Using an Attention-Based Transformer + GRU Model for Predicting Cryptocurrency Prices
A Transformer-GRU hybrid is benchmarked for daily Bitcoin and Ethereum price prediction and beats four baselines on error metrics, but the Bitcoin gain over BiGRU is not significant and the architecture is not novel.