| Oracle® Data Mining Concepts 11g Release 1 (11.1) Part Number B28129-01 |
|
|
View PDF |
| Oracle® Data Mining Concepts 11g Release 1 (11.1) Part Number B28129-01 |
|
|
View PDF |
This section describes the new features of Oracle Data Mining 11g Release 1 (11.1) and provides pointers to additional information. Descriptions of new features in the previous release are also retained to help users migrating to the current release.
The following topics describe the new features in Oracle Data Mining:
Mining Model schema objects
In Oracle 11g, Data Mining models are implemented as data dictionary objects in the SYS schema. A set of new data dictionary views present mining models and their properties. New system and object privileges control access to mining model objects.
In previous releases, Data Mining models were implemented as a collection of tables and metadata within the DMSYS schema. In Oracle 11g, the DMSYS schema no longer exists.
See Also:
Oracle Data Mining Administrator's Guide for information on privileges for accessing mining models
Oracle Data Mining Application Developer's Guide for information on Oracle Data Mining data dictionary views
Automatic Data Preparation (ADP)
In most cases, data must be transformed using techniques such as binning, normalization, or missing value treatment before it can be mined. Data for build, test, and apply must undergo the exact same transformations.
In previous releases, data transformation was the responsibility of the user. In Oracle 11g, the data preparation process can be automated. Algorithm-appropriate transformation instructions are embedded in the model and automatically applied to the build data and scoring data. The automatic transformations can be complemented by or replaced with user-specified transformations.
Because they contain the instructions for their own data preparation, mining models are known as supermodels. The embedded instructions can be implemented automatically and/or manually.
See Also:
Chapter 19 for information on automatic and custom data transformation for Data Mining
Oracle Database PL/SQL Packages and Types Reference for information on DBMS_DATA_MINING_TRANSFORM
Scoping of Nested Data and Enhanced Handling of Sparse Data
Oracle Data Mining supports nested data types for both categorical and numerical data. Multi-record case data must be transformed to nested columns for mining.
In Oracle Data Mining 10gR2, nested columns were processed as top-level attributes; the user was burdened with the task of ensuring that two nested columns did not contain an attribute with the same name. In Oracle Data Mining 11g, nested attributes are scoped with the column name, which relieves the user of this burden.
Handling of sparse data and missing values has been standardized across algorithms in Oracle Data Mining 11g. Data is sparse when a high percentage of the cells are empty but all the values are assumed to be known. This is the case in market basket data. When some cells are empty, and their values are not known, they are assumed to be missing at random. Oracle Data Mining assumes that missing data in a nested column is a sparse representation, and missing data in a non-nested column is assumed to be missing at random.
In Oracle Data Mining 11g, Decision Tree and O-Cluster algorithms do not support nested data.
Generalized Linear Models
A new algorithm, Generalized Linear Models, is introduced in Oracle 11g. It supports two mining functions: classification (logistic regression) and regression (linear regression).
See Also:
Chapter 12, "Generalized Linear Models"New SQL Data Mining Function
A new SQL Data Mining function, PREDICTION_BOUNDS, has been introduced for use with Generalized Linear Models. PREDICTION_BOUNDS returns the confidence bounds on predicted values (regression models) or predicted probabilities (classification).
Enhanced Support for Cost-Sensitive Decision Making
Cost matrix support is significantly enhanced in Oracle 11g. A cost matrix can be added or removed from any classification model using the new procedures, DBMS_DATA_MINING.ADD_COST_MATRIX and DBMS_DATA_MINING.REMOVE_COST_MATRIX.
The SQL Data Mining functions support new syntax for specifying an in-line cost matrix. With this new feature, cost-sensitive model results can be returned within a SQL statement even if the model does not have an associated cost matrix for scoring.
Only Decision Tree models can be built with a cost matrix.
Desupported Features
Adaptive Bayes Network classification algorithm (replaced with Decision Tree)
Basic Local Alignment Search Tool (BLAST)
DM_USER_MODELS view and functions that provide information about models, model signature, and model settings (for example, GET_MODEL_SETTINGS, GET_DEFAULT_SETTINGS, and GET_MODEL_SIGNATURE) are replaced by data dictionary views. See Oracle Data Mining Application Developer's Guide.
The Oracle Data Mining Java API (OJDM) fully supports the new features in Oracle Data Mining 11g Release 1 (11.1). This section provides a summary of the new features in the Java API. For details, see Oracle Data Mining Java API Reference (Javadoc).
As described in "Mining Model schema objects", mining models in 11g Release 1 (11.1) are data dictionary objects in the SYS schema. System and object privileges control access to mining models.
In the Oracle Data Mining Java API, a new extension method OraConnection.getObjectNames is added to support listing of mining objects that can be accessed by a user. This method provides various object filtering options that applications can use as needed.
As described in "Automatic Data Preparation (ADP)", Oracle Data Mining 11g Release 1 (11.1) supports automatic and embedded data preparation (supermodels).
In the Oracle Data Mining Java API, a new build setting extension method, OraBuildSettings.useAutomatedDataPreparations, is added to enable ADP. Using the new OraBuildTask.setTransformationSequenceName, applications can embed the transformations with the model.
Two new GLM packages are introduced: oracle.dmt.jdm.algorithm.glm and oracle.dmt.jdm.modeldetail.glm. These packages have GLM algorithm settings and model details interfaces respectively.
New apply content enumeration values, probabilityLowerBound and probabilityUpperBound, are added to specify probability bounds for classification apply output. The enumeration oracle.dmt.jdm.supervised.classification.OraClassificationApplyContent specifies these enumerations. Similarly apply contents enumeration values predictionLowerBound and predictionUpperBound are added to specify prediction bounds for regression model apply output. In this release only GLM models support this feature.
New static methods addCostMatrix and removeCostMatrix are added to OraClassificationModel to support associating a cost matrix with the model. This will greatly ease the deployment of costs along with the model.
Mining task features are enhanced to support the building of mining process workflows. Applications can specify dependent tasks using the new OraTask.addDependency method. Another notable new task feature is overwriteOutput, which can be enabled by calling the new OraTask.overwriteOutput method.
With these new features, applications can easily develop mining process workflows and deploy them to the database server. These task workflows can be monitored from the client side. For usage of these methods refer to the demo programs shipped with the product (See Oracle Data Mining Administrator's Guide for information about the demo programs.)
A new mining object, oracle.dmt.jdm.transform.OraTransformationSequence supports the specification of user-defined transformation sequences. These can either be embedded in the mining model or managed externally. In addition, the new OraExpressionTransform object can be used to specify SQL expressions to be included with the model.
New oracle.dmt.jdm.OraProfileTask is added to support the new predictive analytics profile functionality.
The Oracle Data Mining Java API can be used with Oracle Database 11g Release 1 (11.1) and with Oracle Database 10.2. When used with a 10.2 database, only the 10.2 features are available.
See Also:
Oracle Data Mining Java API Reference and Oracle Data Mining Application Developer's GuideJava Data Mining (JDM) compliant Java API
Oracle 10g Release 2 introduced a completely new Java API for Data Mining. The API implements JSR-000073, developed through the Java Community Process (http://jcp.org).
The new Java API is layered on the PL/SQL API, and the two APIs are fully interoperable. The new Java API is not compatible with the Java API available in the previous release (Oracle 10g Release 1).
SQL built-in functions for Data Mining
New built-in SQL functions support the scoring of classification, regression, clustering, and feature extraction models. Within the context of standard SQL statements, pre-created models can be applied to new data and the results returned for further processing. The Data Mining SQL functions are:
PREDICTION, PREDICTION_COST, PREDICTION_DETAILS, PREDICTION_PROBABILITY, PREDICTION_SET
CLUSTER_ID, CLUSTER_PROBABILITY, CLUSTER_SET
FEATURE_ID, FEATURE_SET, FEATURE_VALUE
Predictive Analytics
Predictive Analytics automates the process of data mining. Without user intervention, Predictive Analytics routines manage data preparation, algorithm selection, model building, and model scoring.
In the DBMS_PREDICTIVE_ANALYTICS PL/SQL package, Oracle Data Mining provides Predictive Analytics routines that calculate predictions and determine the relative influence of attributes on the prediction.
Oracle Spreadsheet Add-In for Predictive Analytics implements DBMS_PREDICTIVE_ANALYTICS within the context of an Excel spreadsheet. The Spreadsheet Add-In is distributed on Oracle Technology Network.
New and enhanced algorithms
The new Decision Tree algorithm generates human-understandable rules for a prediction.
The new One-Class Support Vector Machine algorithm supports anomaly detection.
The Support Vector Machine algorithm is enhanced with active learning for the management of large build data sets.
Both the PL/SQL and Java APIs support the O-Cluster algorithm. In Oracle 10g Release 1, O-Cluster was only supported in the Java API.
