This algorithm computes thousands of possible nonlinear and interaction models (suitable for cross-sectional data for pattern recognition); it calibrates the best model with the training dataset and forecasts outcomes using the testing dataset. In other words, it performs an ensemble learning approach (Figure 9.67).
Simply enter the variables you need to classify and enter the number of clusters desired. For instance, the required model inputs look like the following:
Figure 9.67: AI/ML Ensemble Learning Common Fit
The sample results illustrate the ensemble algorithm where over 1,593 combinations of linear, nonlinear, interacting, and mixed models were tested, and the 10 best models are shown. The models are selected based on the independent variables’ p-values ≤ 0.10 and ranked by Adjusted R-squares. A stricter p-value can be entered if required.
