Model evaluation
Use these stored procedures to evaluate the performance of your model by comparing
predictions to the true values. Build confusion matrices, and evaluate metrics such as accuracy,
precision, recall, mean absolute error, and mean squared error.
IDAX.CMATRIX_STATS - Calculate classification quality factors from a confusion matrix
Use this stored procedure to calculate and to show different classification quality factors from a confusion matrix. Classification quality factors are, for example, the true positive rate for each predicted class, the false positive rate for each predicted class, the positive predictive value for each predicted class, the F-measure for each predicted class, correctly and incorrectly classified predictions, prediction accuracy, and weighted prediction accuracy.
IDAX.CONFUSION_MATRIX - Build a confusion matrix
Use this stored procedure to build a confusion matrix for classification predictions. The calculation is based on the comparison of the predictions that are made when a classification model is applied on data, and on the real values for this data.
IDAX.MAE - Calculate the mean absolute error of regression predictions
Use this stored procedure to calculate the mean absolute error of regression predictions. For the calculation, the predictions that are made when a regression model is applied on data are compared to the real values of this data.
IDAX.MSE - Calculate the mean squared error of regression predictions
Use this stored procedure to calculate the mean squared error of regression predictions. For the calculation, the predictions that are made when a regression model is applied on data are compared to the real values of this data.