Table 3.

Confusion matrix of neural network method with missing information imputation/indicator and local weather information (mean/confidence interval over 10-fold cross-validation).

	Real shows	Real no-shows
Predicted shows	35789.9 [36738.6, 36842.7]	1832.3 [1800.1,1874.2]
Predicted no-shows	1831.5 [1815.2,1875.6]	8999.9 [7967.7,9029.1]
Confusion matrix (row sum ratio/confidence interval over 10-fold cross-validation)
Predicted shows	0.95 [0.94,0.95]	0.05 [0.05,0.05]
Predicted no-shows	0.18 [0.18,0.19]	0.83 [0.81,0.83]