Skip to main content
Financial Innovation

Table 10 XGBoost best parameter setting

From: Predicting cash holdings using supervised machine learning algorithms

Colsample by tree

0.5

0.6

0.7

0.8

0.9

1

n estimators

500

600

700

   

Gamma

0

1

    

Max depth

3

4

5

   

Reg lambda

1

1.5

    

Eta

0.01

0.05

0.1

   
  1. The hyperparameter values displayed in bold are the best settings that provide the maximum R2. The optimal hyperparameter setting is obtained by assigning the following values: colsample by tree = 1, n estimators = 700, gamma = 1, max tree depth = 4, reg lambda i = 1.5, and eta = 0.1
Back to article page