Pre-trained RNN models with global self-attention or sliding-window sparse attention deliver the highest value-weighted Sortino ratios (2.0 and 1.80) in a COVID-era backtest of 420 large-cap US stocks.
Available at SSRN 4999011 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
baseline 1
citation-polarity summary
fields
q-fin.PR 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
unclear 1representative citing papers
citing papers explorer
-
Is attention truly all we need? An empirical study of asset pricing in pretrained RNN sparse and global attention models
Pre-trained RNN models with global self-attention or sliding-window sparse attention deliver the highest value-weighted Sortino ratios (2.0 and 1.80) in a COVID-era backtest of 420 large-cap US stocks.