This project explores Attention-Based Transformer Encoders to develop robust buy/sell classification models for financial time series. It addresses market non-stationarity and noise by combining De Prado-inspired preprocessing with a hybrid Transformer-LSTM architecture.
pytorch time-series-classification transformer-lstm optuna-optimization triple-barrier-method de-prado-inspired purged-k-fold-cross-validation
-
Updated
Oct 18, 2025 - Jupyter Notebook