Compare the performance of multiple Machine Learning and Regression models by producing a table of metrics from each model. The metrics are computed based on each model's training data. Optionally a filter specifying evaluation data (usually a testing sample independent of the training sample) may also be provided. The models may either be existing already or created for comparison.
Requirements
A Q project with multiple machine learning models that you want to compare.
Method
Usage
To compare machine learning models:
1. Select Create > Classifier > Compare Models.
2. Under Inputs > Existing or new models select whether you would like to compare existing models or create multiple new models for comparison.
- If your working with Existing models then under Inputs > EXISTING MODELS > Input models select the models you want to compare.
- If your selection is to work with New models then under Inputs > COMMON INPUTS select your Outcome and Predictor(s) variables. For New models you should also select which MODEL X > Algorithm to use for each of the models to compare.
Example
Options
Existing or new models - Choose to use existing machine learning models or create new models to compare.
Existing models
Input models - At least 2 existing machine learning models.
Ensemble - Whether to create an ensemble model by combining the predictions of the underlying models.
New models
Outcome - The variable to be predicted by the predictor variables.
Predictors - The variable(s) to predict the Outcome.
Missing data See Missing Data Options.
Variable names Displays variable names in the output.
Random seed - Seed used to initialize the (pseudo) random number generator for the model fitting algorithm.
Ensemble - Whether to create an ensemble model by combining the predictions of the underlying models.
Evaluation filter - Select a filter to apply to the models.
Models - For each model, select a machine learning algorithm and the desired settings for each model. See for more details.
For model-specific options see Classification And Regression Trees (CART), Linear Discriminant Analysis, Random Forest, Support Vector Machine, Deep Learning, Gradient Boosting or Regression.