- Related AI/ML Methods: Bagging Linear Fit Bootstrap, Ensemble Common & Complex Fit
- Related Traditional Methods: Nonparametric Bootstrap Simulation, Bootstrap Regression
This method computes a Bagging or Bootstrap Aggregation on your custom nonlinear fit model hundreds of times via resampled data to generate the best consensus forecasts. This approach is similar to the Bagging Linear Fit Bootstrap model described previously. The main difference is that the regression model is a customized nonlinear model that the user can enter. Again, do note the differences between bootstrap aggregation versus ensemble learning methods as described in the previous method.
As usual, the standard practice is to divide your data into training and testing sets. The training set (one dependent with one or more independent variables) is used to train the algorithm and obtain the best-fitting parameters. In this model, you can create your custom equations (Figure 9.56). Note that only one variable is allowed as the Training Dependent Variable, whereas multiple variables are allowed in the Training Independent Variables section, separated by a semicolon (;), and that basic mathematical functions can be used (e.g.,,,, +, -, /, *,,,). For instance, the training set’s dependent variable is and the independent variables are ,and so forth. You need to use the same functional form for the testing set’s independent variables as well (but with the same or different variables), otherwise, the model will not run properly. For example, the complementary testing independent variables set might be . Notice that the same functional form is used but applied to different variables. Applying it to the same variables would be the same as running a customized econometric model instead.
The algorithm also allows you to optionally enter known testing set dependent values. Sometimes these are known and sometimes they are unknown and are to be forecasted. If the values are unknown, simply leave the input empty or enter a 0 in the input if you wish to enter the next input, which is the forecast results save location in the data grid. 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:
Similar to the Bagging Linear model, the nonlinear fit model aggregation method is only interested in the average forecast prediction based on the testing variables.
Figure 9.56: AI/ML Nonlinear Fit Bootstrap Aggregation or Bagging