Predict Real-Time
Predict real-time output value by changing the input value.
Predict real-time output values by changing the input values using the What-If analysis method.
-
Click Next to view the Model Quality values.
The Model Quality and Predict values are displayed..
-
Click next to Model
Quality to view its values.
The model field prediction values are displayed.
-
Click Scalar to view the details.
In model quality, a measure of ML model, R2, is displayed for train, cross-validation and test data. The closer it is to 1.0; the better the model is in predicting the known data points. R-square values in the Test column are better indications of the ML model quality but in the absence of a separate test data; R-Square values in the cross-validation column can be used as cross-validation provides a form of testing in the absence of a separate test data. Before you proceed with predict study or optimization; you should make sure that the R-square values in test or cross-validation are within acceptable ranges (i.e., greater than 0.7).
-
Click Predict to view the predict real-time output
values.
The output values are displayed.
-
Click in the output to display the
curve.
The curve for the output is displayed.
-
Click View to view the predicted model preview.
The Info panel is displayed with the predicted model preview.
-
Click Generate Preview in the Info panel.
The predicted model preview will be generated and displayed.
-
Click Save to save the predicted model.
The save dialog box is displayed.
-
Enter the file name of the predicted model preview and click
Save.
The predicted model is saved in the Altair One Drive location. By default, a folder predicted is created under the Study folder name. You can change the folder name by navigating the Altair One drive location.
-
Slide or double click and edit the values of trained model input value in the
Predict panel to generate a new predicted
model.
-
Click Predict to get the updated predict real-time
output values.
Note: Generate multiple prediction model files by changing the input values and save them to compare the predicted model files.