Hidformer matches classic neural network baselines on 128-day stock close price forecasts for six large-cap stocks, with no clear advantage after accounting for evaluation flaws.
MIT Press (2016)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CE 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Hidformer: Transformer-Style Neural Network in Stock Price Forecasting
Hidformer matches classic neural network baselines on 128-day stock close price forecasts for six large-cap stocks, with no clear advantage after accounting for evaluation flaws.