Pre-training a transformer on the TSX index reduces binary cross-entropy loss on individual stocks from 0.69 to 0.64 and yields lower MSE than LSTM or XGBoost in regression, though ensembles achieve higher average daily returns.
[Under double blind review] PromptCast: A new prompt - based learning paradigm for time series forecasting,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
q-fin.ST 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Index to Equity: Pre-Training Transformers for Stock Return Prediction
Pre-training a transformer on the TSX index reduces binary cross-entropy loss on individual stocks from 0.69 to 0.64 and yields lower MSE than LSTM or XGBoost in regression, though ensembles achieve higher average daily returns.