Analysis Type

Specifies the operation mode of the tool. The tool can be run to train a model to only assess performance, or train a model and predict to features. Prediction types are as follows:

• Fit a model to assess model performance—A model will be fit and applied to the input data. Use this option to assess the accuracy of your model before generating predictions on a new dataset or understand relationships and drivers of your predicted variable. The output of this option will be a feature service of your fitted data and model diagnostics.
• Fit a model and predict values— Predictions or classifications will be generated for input features and prediction features. Explanatory variables must be provided for both the prediction features and the features to be predicted. The output of this option will be a feature service of your model fitted to your input data, a feature service of predicted values and model diagnostics.

Fit a model to assess model performance

Use this mode if you want to fit a model, and investigate the fit.

With this choice the model will be trained using an input layer. Use this option to assess the accuracy of your model before generating predictions on a new dataset. This option will output model diagnostics apply the model to your training data.

Fit a model and predict values

Use this mode if you want to fit a model, and apply the model to the dataset to generate predictions.

Predictions or classifications will be generated for features. The output of this option will be a feature service, model diagnostics, and an optional table of variable importance.

Choose a layer to generate a model from

The layer containing point, line, area, or tabular features that contain the dependent and explanatory variables.

In addition to choosing a layer from your map, you can choose Choose Analysis Layer at the bottom of the drop-down list to browse to your contents for a big data file share dataset or feature layer.

Choose the field to model

The numeric field containing the observed values to be modeled and the type of value you are modelling. There are three types of values you can model

• Continuous—Represents continuous values. The model used is Gaussian, and the tool performs ordinary least squares regression.
• Binary—Represents presence or absence values. These must be 1s and 0s. The model used is Logistic Regression.
• Count—Represents discrete and represents events, for example, crime counts, disease incidents, or traffic accidents. The model used is Poisson regression.

Choose a layer to predict values for

A layer with features representing locations where estimates should be computed. Each feature in this dataset should contain values for all the explanatory variables specified. The dependent variable for these features will be estimated using the model calibrated for the input layer.

Choose the explanatory fields

One or more fields representing the explanatory variables (fields) that help predict the value. Only numeric fields will be visible.

Choose how explanatory fields are matched

How the corresponding variables in the input layer will match the variables in the prediction layer. Only the variables used in generating the model will be included in the table. Only numeric values can be used.

Result layer name

The name of the layer that will be created. If you are writing to an ArcGIS Data Store, your results will be saved in My Content and added to the map. If you are writing to a big data file share, your results will be stored in the big data file share and added to its manifest. It will not be added to the map. The default name is based on the tool name and the input layer name. If the layer already exists, the tool will fail.

The results returned will depend on the type of analysis. If you are fitting to assess model fit, results will contain a layer of input data fit to the model and result info assessing the model fit. If you are fitting and predicting, results will contain a layer of the input data fit to the model, a layer of predicted results, and result info assessing the model fit.

When writing to ArcGIS Data Store (relational or spatiotemporal big data store) using the Save result in drop-down box, you can specify the name of a folder in My Content where the result will be saved.