Table 2 Hyperparameters optimized for the LightGBM model using a subset of 26 features with PSO.

From: An integrated approach of feature selection and machine learning for early detection of breast cancer

Hyperparameter

Range

PSO

learning_rate

0.01–0.3

0.27

max_depth

1–10

10

num_leaves

2–100

100

n_estimators

1–1000

1000

max_bin

10–300

264

min_child_samples

1–50

1

colsample_bytree

0.5–1

0.5

subsample

0.5–1

0.6

subsample_freq

0–80

80

reg_alpha

0–1

0

reg_lambda

0–1

1

min_split_gain

0–1

0

Back to article page