Skip to main content
Financial Innovation

Table 2 Prediction performance of empirical methods in test sample

From: Machine learning approach to drivers of bank lending: evidence from an emerging economy

Methods

MSE

MAPE

R-squared

Panel OLS Regression

1.928

0.067

0.385

Tree Regression

3.292

0.082

0.430

Bagging

2.091

0.065

0.504

Boosting

1.732

0.061

0.588

Random Forest

1.534

0.061

0.617

Xgboost

1.715

1.911

0.611

Extra-Trees

1.753

0.067

0.566

  1. Bold values represent that random forest model provides the best out-of-sample performance
Back to article page