Table 3:
Comparison of Forecast Performance Based on Empirical Data (N = 402)
| Null Model | ZIMLP | RS-ZIMLP | |||||||
|---|---|---|---|---|---|---|---|---|---|
| Mean | SD | 95% CI | Mean | SD | 95% CI | Mean | SD | 95% CI | |
| ACC* | 0.87 | - | - | 0.84 | 0.01 | [0.83, 0.85] | 0.91 | 0.00 | [0.90, 0.92] |
| recall* | 0.00 | - | - | 0.73 | 0.02 | [0.70, 0.75] | 0.77 | 0.03 | [0.72, 0.82] |
| precision* | - | - | - | 0.46 | 0.01 | [0.44, 0.48] | 0.71 | 0.02 | [0.68, 0.75] |
| AUC | - | - | - | 0.90 | 0.00 | [0.89, 0.91] | 0.93 | 0.01 | [0.92, 0.94] |
| MAE | 1.57 | - | - | 1.72 | 2.31 | [1.39, 4.13] | 1.27 | 1.21 | [0.96, 3.40] |
| RMSE | 5.82 | - | - | 5.11 | 9.17 | [3.24, 34.67] | 4.53 | 9.97 | [2.85, 40.45] |
Note. The forecast performance was evaluated based on all participants (N = 402) in the empirical study. The calculation of ACC, recall, and precision was based on a threshold of 0.3 for both ZIMLP and RS-ZIMLP models. The Mean, SD, and 95% CI represented the means, standard deviations, and 95% credible intervals of the posterior distributions of these measures.