Model performance across different evaluation scopes
| Model | MAE | MSE | R2 |
|---|---|---|---|
| Linear Regression | 3687.64 | 75,236,811.98 | 0.465 |
| Random Forest | 3474.73 | 70,883,256.96 | 0.497 |
| ARIMA | 26.34 | 1296.29 | −0.259 |
| LSTM (Maize) | 15.36 | 364.62 | 0.640 |
| LSTM (Rice) | 11,893.29 | 153,813,836.48 | −0.039 |
| Model | MAE | MSE | |
|---|---|---|---|
| Linear Regression | 3687.64 | 75,236,811.98 | 0.465 |
| Random Forest | 3474.73 | 70,883,256.96 | 0.497 |
| ARIMA | 26.34 | 1296.29 | −0.259 |
| LSTM (Maize) | 15.36 | 364.62 | 0.640 |
| LSTM (Rice) | 11,893.29 | 153,813,836.48 | −0.039 |
Note(s): Linear Regression and Random Forest were evaluated on the full multi-commodity dataset, whereas ARIMA and LSTM models were evaluated on selected commodity-level series. Accordingly, metric values should be interpreted within their respective evaluation contexts and are not directly comparable across all models
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.