In-Database Algorithms Supported by OML4R

6.1.1 In-Database Algorithms Supported by OML4R

The functions in the OREdm package provide access to the in-database machine learning functionality of Oracle Database. You use these functions to build in-database models in the database.

The following table lists the OML4R functions that build in-database models and the corresponding in-database algorithms and functions.

Table 6-1 Oracle Machine Learning for R Model Functions

OML4R Function Name	Algorithm	Machine Learning Technique (Mining Function)
`ore.odmAI`	Minimum Description Length	Attribute importance for classification or regression
`ore.odmAssocRules`	Apriori	Association rules
`ore.odmDT`	Decision Tree	Classification
`ore.odmEM`	Expectation Maximization	Clustering
`ore.odmESA`	Explicit Semantic Analysis	Feature extraction
`ore.odmGLM`	Generalized Linear Models	Classification and regression
`ore.odmKMeans`	k-Means	Clustering
`ore.odmNB`	Naive Bayes	Classification
`ore.odmNMF`	Non-Negative Matrix Factorization	Feature extraction
`ore.odmOC`	Orthogonal Partitioning Cluster (O-Cluster)	Clustering
`ore.odmRAlg`	Extensible R Algorithm	Association rules, attribute importance, classification, clustering, feature extraction, and regression
`ore.odmSVD`	Singular Value Decomposition	Feature extraction
`ore.odmSVM`	Support Vector Machines	Classification, regression and anomaly detection.
`ore.odmNN`	Neural Network	Classification and regression
`ore.odmRF`	Random Forest	Classification
`ore.odmXGB`	XGBoost	Classification and regression Note: Available only in Oracle Database 21c and later
`ore.odmESM`	Exponential Smoothing Method	Regression

Parent topic: About Building In-Database Models using OML4R