quantlab.model.predefined

Modules

catboost_model	Qlib's CatBoost benchmark model.
double_ensemble	Qlib's DoubleEnsemble benchmark model.
gats	GATs: Qlib's graph attention model over one bar's cross-section.
lgbm	Qlib's LightGBM benchmark model.
linear	Qlib's linear benchmark model.
master	MASTER: a market-guided transformer over one bar's cross-section.
membership_mask	Mask a predictor's predictions with an index's point-in-time membership.
mlp	Qlib's MLP benchmark model.
model_ensemble	Model ensembles: models of any classes over any factors, combined into one prediction.
realmlp	RealMLP regression head backed by pytabkit.
recorded	Serve a recorded backtest run's predictions instead of predicting them again.
rnn	Qlib's recurrent benchmark models: LSTM, GRU and ALSTM.
seed_ensemble	Seed ensembles: one model config trained under several random seeds.
smoothed	Smooth a predictor's predictions in time, causally.
tcn	Qlib's TCN benchmark model: a temporal convolutional network.
transformer	Qlib's Transformer and Localformer benchmark models.
xgb	XGBoost regression head for the tree-model layer.
xgb_td	XGBoost regression head with pytabkit's tuned defaults.