Hands-On Machine Learning for Algorithmic Trading

Gradient-boosting machine

For illustration purposes, we also train a LightGBM gradient-boosting tree ensemble with default settings and the multiclass objective:

param = {'objective':'multiclass', 'num_class': 5}booster = lgb.train(params=param,                    train_set=lgb_train,                    num_boost_round=500,                    early_stopping_rounds=20,                    valid_sets=[lgb_train, lgb_test])

The basic settings do not improve on multinomial logistic regression, but further parameter tuning remains an unused option:

y_pred_class = booster.predict(test_dtm_numeric.astype(float))accuracy_score(test.stars, y_pred_class.argmax(1) + 1)0.738665855696524