Table 8.
Comparative performance of GBM, random forest, and deep neural network in the analysis of combined training dataset of all states of India
| Approach | Performance measures of random forest and deep neural network and GBM models | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Active cases modeling | Recovered cases modeling | |||||||||
| R2 | MSE | RMSE | MAE | MRD | R2 | MSE | RMSE | MAE | MRD | |
| Random forest | 0.59 | 136,919.20 | 370.02 | 187.02 | 136,919.20 | 0.33 | 6607.79 | 81.28 | 39.39 | 6607.79 |
| Deep neural network | 0.22 | 264,411.60 | 514.20 | 275.35 | 116,327.90 | 0.02 | 9628.01 | 98.12 | 42.31 | 3395.10 |
| Gradient boosting machine | 0.99 | 3075.37 | 55.46 | 35.89 | −2846.53 | 0.99 | 94.35 | 9.71 | 6.63 | −357.78 |
Note: R2 (coefficient of determination), MSE (mean square error), RMSE (root mean square error), MAE (mean average error), and MRD (mean residual deviance)