This tip is part of Learn by Example using SAS® Enterprise Miner™ series where a new data mining topic is introduced and explained with one or more example SAS Enterprise Miner process flow diagrams.
The topic covered is predictive modeling – building models to predict a target using labeled data (data that includes the target variable), also called supervised learning. The goal of this method is to find patterns in the input data that best predict the target and to use that information to score (predict) new data.
There are two types of supervised learning – regression where target is interval or classification where the target is categorical (binary, nominal or ordinal). SAS Enterprise Miner provides a comprehensive set of algorithms for supervised learning under the Model and HPDM tabs. The nodes under HPDM tab require a High-Performance Data Mining license to run in a distributed computing environment (Hadoop, Teradata, Greenplum and so on) for big data.
To get started with predictive modeling using SAS Enterprise Miner, download the process flow diagrams (XML files) and the accompanying PDF documentation for the following two examples from the GitHub repository at https://github.com/sassoftware/dm-flow/tree/master/PredictiveModeling.
1. Predictive Modeling: A simple example that predicts a binary target using the champion of three models - regression, decision tree and neural network. It subsequently scores data using the champion model.
2. High-Performance Predictive Modeling: A similar example using high-performance HPDM nodes to pick the champion of three models - regression, neural network and forest.
To run these examples, refer to the README file that is part of the GitHub repository at https://github.com/sassoftware/dm-flow. Please note that these examples were tested with SAS Enterprise Miner 13.2