Table 11 Model performance comparison (Mean ± SD across 3 CV Folds).

From: Forecasting cashew production in India using a hybrid machine learning framework with STL decomposition, ensemble methods, and global trade network analysis

Model

MAE (MT)

RMSE (MT)

MAPE (%)

\(R^2\)

Gradient boosting (Winner)

14.40 ± 11.11

45.77 ± 35.21

3.60 ± 2.29

0.988 ± 0.016

Random forest

51.11 ± 47.56

189.18 ± 168.84

11.29 ± 1.67

0.871 ± 0.120

ElasticNet (Failed)

244.83 ± 163.04

643.29 ± 674.11

426.50 ± 273.35

-0.433 ± 0.958

Ridge (Failed)

253.15 ± 185.87

659.87 ± 701.48

431.62 ± 317.07

-0.452 ± 0.989

Back to article page