Auto Classifier Node Expert Options

The Expert tab of the Auto Classifier node enables you to apply a partition (if available), select the algorithms to use, and specify stopping rules.

Models used. Use the check boxes in the column on the left to select the model types (algorithms) to include in the comparison. The more types you select, the more models will be created and the longer the processing time will be.

Model type. Lists the available algorithms (see below).

Model parameters. For each model type, you can use the default settings or select Specify to choose options for each model type. The specific options are similar to those available in the separate modeling nodes, with the difference that multiple options or combinations can be selected. For example, if comparing Neural Net models, rather than choosing one of the six training methods, you can choose all of them to train six models in a single pass.

Number of models. Lists the number of models produced for each algorithm based on current settings. When combining options, the number of models can quickly add up, so paying close attention to this number is strongly recommended, particularly when using large datasets.

Restrict maximum time spent building a single model. (K-Means, Kohonen, TwoStep, SVM, KNN, Bayes Net and Decision List models only) Sets a maximum time limit for any one model. For example, if a particular model requires an unexpectedly long time to train because of some complex interaction, you probably don't want it to hold up your entire modeling run.

Supported Algorithms

The Support Vector Machine (SVM) node enables you to classify data into one of two groups without overfitting. SVM works well with wide data sets, such as those with a very large number of input fields.

The k-Nearest Neighbor (KNN) node associates a new case with the category or value of the k objects nearest to it in the predictor space, where k is an integer. Similar cases are near each other and dissimilar cases are distant from each other.

Discriminant analysis makes more stringent assumptions than logistic regression but can be a valuable alternative or supplement to a logistic regression analysis when those assumptions are met.

The Bayesian Network node enables you to build a probability model by combining observed and recorded evidence with real-world knowledge to establish the likelihood of occurrences. The node focuses on Tree Augmented Naïve Bayes (TAN) and Markov Blanket networks that are primarily used for classification.

The Decision List node identifies subgroups, or segments, that show a higher or lower likelihood of a given binary outcome relative to the overall population. For example, you might look for customers who are unlikely to churn or are most likely to respond favorably to a campaign. You can incorporate your business knowledge into the model by adding your own custom segments and previewing alternative models side by side to compare the results. Decision List models consist of a list of rules in which each rule has a condition and an outcome. Rules are applied in order, and the first rule that matches determines the outcome.

Logistic regression is a statistical technique for classifying records based on values of input fields. It is analogous to linear regression but takes a categorical target field instead of a numeric range.

The CHAID node generates decision trees using chi-square statistics to identify optimal splits. Unlike the C&R Tree and QUEST nodes, CHAID can generate nonbinary trees, meaning that some splits have more than two branches. Target and input fields can be numeric range (continuous) or categorical. Exhaustive CHAID is a modification of CHAID that does a more thorough job of examining all possible splits but takes longer to compute.

The QUEST node provides a binary classification method for building decision trees, designed to reduce the processing time required for large C&R Tree analyses while also reducing the tendency found in classification tree methods to favor inputs that allow more splits. Input fields can be numeric ranges (continuous), but the target field must be categorical. All splits are binary.

The Classification and Regression (C&R) Tree node generates a decision tree that allows you to predict or classify future observations. The method uses recursive partitioning to split the training records into segments by minimizing the impurity at each step, where a node in the tree is considered “pure” if 100% of cases in the node fall into a specific category of the target field. Target and input fields can be numeric ranges or categorical (nominal, ordinal, or flags); all splits are binary (only two subgroups).

The C5.0 node builds either a decision tree or a rule set. The model works by splitting the sample based on the field that provides the maximum information gain at each level. The target field must be categorical. Multiple splits into more than two subgroups are allowed.

The Neural Net node uses a simplified model of the way the human brain processes information. It works by simulating a large number of interconnected simple processing units that resemble abstract versions of neurons. Neural networks are powerful general function estimators and require minimal statistical or mathematical knowledge to train or apply.

Linear regression models predict a continuous target based on linear relationships between the target and one or more predictors.

The Linear Support Vector Machine (LSVM) node enables you to classify data into one of two groups without overfitting. LSVM is linear and works well with wide data sets, such as those with a very large number of records.

The Random Trees node is similar to the existing C&RT node; however, the Random Trees node is designed to process big data to create a single tree and displays the resulting model in the output viewer that was added in SPSS® Modeler version 17. The Random Trees tree node generates a decision tree that you use to predict or classify future observations. The method uses recursive partitioning to split the training records into segments by minimizing the impurity at each step, where a node in the tree is considered pure if 100% of cases in the node fall into a specific category of the target field. Target and input fields can be numeric ranges or categorical (nominal, ordinal, or flags); all splits are binary (only two subgroups).

The Tree-AS node is similar to the existing CHAID node; however, the Tree-AS node is designed to process big data to create a single tree and displays the resulting model in the output viewer that was added in SPSS Modeler version 17. The node generates a decision tree by using chi-square statistics (CHAID) to identify optimal splits. This use of CHAID can generate nonbinary trees, meaning that some splits have more than two branches. Target and input fields can be numeric range (continuous) or categorical. Exhaustive CHAID is a modification of CHAID that does a more thorough job of examining all possible splits but takes longer to compute.

XGBoost Tree© is an advanced implementation of a gradient boosting algorithm with a tree model as the base model. Boosting algorithms iteratively learn weak classifiers and then add them to a final strong classifier. XGBoost Tree is very flexible and provides many parameters that can be overwhelming to most users, so the XGBoost Tree node in SPSS Modeler exposes the core features and commonly used parameters. The node is implemented in Python.

XGBoost© is an advanced implementation of a gradient boosting algorithm. Boosting algorithms iteratively learn weak classifiers and then add them to a final strong classifier. XGBoost is very flexible and provides many parameters that can be overwhelming to most users, so the XGBoost-AS node in SPSS Modeler exposes the core features and commonly used parameters. The XGBoost-AS node is implemented in Spark.