IBM SPSS Modeler
Solve your toughest challenges with data mining
IBM SPSS Modeler Professional and IBM SPSS Modeler Premium is available in both a desktop-based client deployment as well as a client/server deployment model. The features shown in the chart below are accessed from the client. IBM SPSS Modeler Server, available as both a Professional and Premium edition, provides server-based processing and performance enhancement as well as additional features such as batch processing, SQL pushback and in-database mining.
| Modeler Professional | Modeler Premium | |
|---|---|---|
| Features | ||
| Create a wide range of interactive graphs with automatic assistance | X | X |
| Use visual link analysis to see the associations in your data | X | X |
| Interact with data by selecting regions or items on a graph and view the selected information; or select key data for use in analysis | X | X |
| Access IBM SPSS Statistics tools directly from interface | X | X |
| Read from and write to operational data from a variety of operational datasources such as IBM DB2®, Oracle®, Microsoft SQL Server™, Informix®, Neoview, Netezza, mySQL (Sun) and Teradata. | X | X |
| Read from and write to data views and metadata stored in Cognos® 8 Business Intelligence | X | X |
| Import from and export to delimited and fixed-width text files, any IBM SPSS Statistics file, SAS, IBM Data Collection data sources, or XML | X | X |
| Data-cleaning options that remove or replace invalid data, automatically impute missing values and mitigate for outliers and extremes | X | X |
| Apply automatic data preparation to interrogate and condition data for analysis in a single step | X | X |
| Field filtering, naming, derivation, binning, re-categorization, value replacement, and field reordering | X | X |
| Record selection, sampling (including clustered and stratified sampling), merging (including inner joins, full outer joins, partial outer joins, and anti-joins), and concatenation; sorting, aggregation, and balancing | X | X |
| Data restructuring, partitioning and transposition | X | X |
| Extensive string functions: string creation, substitution, search and matching, whitespace removal, and truncation | X | X |
| RFM scoring: aggregate customer transactions to provide Recency, Frequency, and Monetary value scores and combine these to produce a complete RFM analysis. | X | X |
| Use interactive model and equation browsers and view advanced statistical output | X | X |
| Show relative impact of different data attributes on predicted outcomes with variable importance graphs | X | X |
| Combine multiple models or use one model to analyze a second model | X | X |
| Use automatic classification (both binary and numeric) and clustering models to eliminate need for selecting individual algorithm | X | X |
| Use Modeler’s Component-Level Extension Framework (CLEF) to build custom algorithms | X | X |
| Through the integration of IBM SPSS Statistics, use R to extend analysis options through customization | X | X |
| C&RT, CHAID & QUEST—Decision tree algorithms including interactive tree building | X | X |
| Decision List—Interactive rule-building algorithm | X | X |
| K-Means, Kohonen, Two Step, Discriminant, Support Vector Machine (SVM) — Clustering and segmentation algorithms | X | X |
| GRI—Generalized rule induction association discovery algorithm | X | X |
| Factor/PCA, Feature Selection—Data reduction algorithms | X | X |
| Regression, Linear, GenLin (GLM)—Linear equation modeling | X | X |
| Self-learning response model (SLRM)—Bayesian model with incremental learning | X | X |
| Time-series—Generate and automatically select time-series forecasting models | X | X |
| C5.0 decision tree and rule set algorithm | X | X |
| Neural Networks—Multi-layer perceptrons with back-propagation learning, and radial basis function networks | X | X |
| Support Vector Machines—Advanced algorithm with accurate performance for wide datasets | X | X |
| Bayesian Networks—graphical probabilistic models | X | X |
| Cox regression—calculate likely time to an event | X | X |
| Anomaly Detection—Detect unusual records through the use of a cluster-based algorithm | X | X |
| KNN – Nearest neighbor modeling and scoring algorithm | X | X |
| Apriori—Popular association discovery algorithm with advanced evaluation functions | X | X |
| CARMA—Association algorithm which supports multiple consequents | X | X |
| Sequence—Sequential association algorithm for order-sensitive analyses | X | X |
| Export models using SQL or PMML (the XML-based standard format for predictive models) | X | X |
| Extract text data from files, operational databases and RSS feeds (ie. blogs, web feeds) | X | |
| Select native language extractor options for Dutch, English, French, German, Italian, Portuguese, Spanish or Japanese or translate virtually any language using Language Weaver (separately licensed) | X | |
| Extract domain-specific concepts such as uniterms, expressions, abbreviations, acronyms, and more | X | |
| Calculate synonyms using sophisticated linguistic algorithms and embedded or user-specified linguistic resources | X | |
| Name concepts by person, organization, term, product, location, and other user- defined types | X | |
| Extract non-linguistic entities such as address, currency, time, phone number, and social security number (SSN) | X | |
| Use and customize pre-built templates and libraries for sentiment analysis, CRM, security and intelligence, market intelligence, life sciences, and IT | X | |
| Leverage pre-packaged Text Analytics Packages (TAPs) for the most common business applications and create your own | X | |
| Create clusters based on term co-occurrence using concept clustering algorithms, which provide an at-a-glance view of main topics and the way in which they are related | X | |
| Intelligently group text documents and records based on content, using text classification algorithms –Enable advanced concept selection and deselection for use in predictive modeling | X | |
| Use text based and visual reports to interrogate concept relationship, occurrence, frequency and type | X | |
| Identify and extract sentiments (for example, likes and dislikes) from text in Dutch, English, French, German, and Spanish | X | |
| Ability to read from IBM Classic Federation data sources | X | X |