In SPSS Modeler, you set up flows to process data and
experiment with different modeling techniques. Through the modeling process, you create
tuned model that you can use for predictive analytics.
Building flows
Copy link to section
A flow is a series of nodes that you connect on the canvas.
Flow
A flow is a group of data-processing operations that are connected in
sequences. Flows represent the flow of data through each operation. Data
flows from the data source through the sequence of operations to the end.
Usually, a flow ends in a model or type of data output, such as a table or
chart.
Flows are created by adding nodes on to the canvas and
connecting them.
Canvas
The canvas is the main work area in SPSS Modeler, and it is where you build your flows.
Nodes
A node is a modular, self-contained set of operations. Nodes are a graphical
way of representing these operations, and each node has a unique icon. These
nodes can be linked together on the canvas in a flow for more complex data
processing.
You can add modeling nodes to your flow. Each of the modeling nodes is a different
modeling technique. You can add several modeling nodes to your flow to try
different modeling techniques with your data. After you finish setting up your
flow, you can run it so that your data is processed and the analyzed by the
modeling nodes.
The modeling process
Copy link to section
The ability to predict an outcome is the central goal of predictive analytics, and
understanding the modeling process is the key to using SPSS Modeler.
A model is a set of rules, formulas, or equations that can be used to predict an
outcome based on a set of input fields or variables from your data. For example, a
financial institution might use a model to predict whether loan applicants are
likely to be good or bad risks, based on information that is already known about
past applicants. A tuned model is one of the objectives of working in SPSS Modeler.
Modeling is conducted in multiple iterations. Typically, you might run several
modeling nodes that use the default parameters. You can then fine-tune the
parameters for the modeling node, or you might return to the data preparation phase
to adjust the data for the modeling node.
SPSS Modeler offers various modeling methods that are
taken from machine learning, artificial intelligence, and statistics. You can use
the methods available on the node palette to derive new information from your data
and to develop predictive models. Each method has certain strengths and is best
suited for particular types of problems.
If you get promising results from one of these modeling nodes, then you can save the
modeling node as a model. This model can then be promoted and deployed for use in
real-time predictive analysis.
Nodes palette
Copy link to section
The nodes palette has all the nodes that are available in SPSS Modeler. They are organized into groups based on their
function. You can add any node in the nodes palette to your flow.
For more information about the nodes palette, see Nodes palette.
SuperNodes
Copy link to section
You can save all or part of your flow as a SuperNode. This SuperNode can then be used
just like a node in other flows. You can use a SuperNode to add complex layers of
processing to a flow without adding a long sequence of nodes that can clutter your
canvas.
For more information about SuperNodes, see SuperNodes.
About cookies on this siteOur websites require some cookies to function properly (required). In addition, other cookies may be used with your consent to analyze site usage, improve the user experience and for advertising.For more information, please review your cookie preferences options. By visiting our website, you agree to our processing of information as described in IBM’sprivacy statement. To provide a smooth navigation, your cookie preferences will be shared across the IBM web domains listed here.