How IBM SPSS Modeler works

The unique graphical interface in IBM® SPSS® Modeler is based around nodes and streams. Nodes are the icons or shapes that represent individual operations on your data. The nodes are linked together in a stream to represent the flow of data through each operation.

Algorithms are represented by a special type of node known as a modeling node. There is a different modeling node for each algorithm that IBM SPSS Modeler supplies. Modeling nodes are shown as a five-sided shape.

Other types of nodes include source nodes, process nodes, and output nodes. Source nodes are the ones that bring the data into the stream, and always appear at the beginning of the stream. Process nodes perform operations on individual data records and fields, and are usually found in the middle of the stream. Output nodes produce a variety of output for data, charts and model results, or they enable you to export the results to another application, such as a database or a spreadsheet. Output nodes usually appear as the last node in a stream or a branch of a stream.

When you run a stream that contains a modeling node, the resulting model is added to stream, and is represented by a special type of node known as a model nugget--it has a shape that looks just like a gold nugget.