About Oracle Machine Learning for SQL

Oracle Machine Learning for SQL (OML4SQL) provides scalable in-database machine learning algorithms through PL/SQL and SQL APIs. The algorithms are fast and scalable, support algorithm-specific automatic data preparation, and can score in batch or real-time.

OML4SQL provides a powerful, state-of-the-art machine learning capability within Oracle Database. The parallelized algorithms in the database keep data under database control. There is no need to extract data to separate machine learning engines, which adds latency to data access and raises concerns about data security, storage, and recency. The algorithms are fast and scalable, support algorithm-specific automatic data preparation, and can score in batch or real-time. You can use OML4SQL to build and deploy predictive and descriptive machine learning applications, to add intelligent capabilities to existing applications, and to generate predictive queries for data exploration. OML4SQL provides explanatory prediction details when scoring data, so you can understand why an individual prediction is made.

OML4SQL offers a broad set of in-database algorithms for performing a variety of machine learning tasks, such as classification, regression, anomaly detection, feature extraction, clustering, and market basket analysis. The algorithms can work on standard case data, transactional data, star schemas, and unstructured text data. OML4SQL is uniquely suited to the analysis of very large data sets.

Oracle Machine Learning for SQL, along with Oracle Machine Learning for R and Oracle Machine Learning for Python, is a component of Oracle Machine Learning that provides three powerful APIs for in-database machine learning, among other features.

Oracle Machine Learning for SQL in the Database Kernel

Learn about the implementation of Oracle Machine Learning for SQL (OML4SQL) in Oracle Database kernel and its advantages.

OML4SQL is implemented in the Oracle Database kernel. OML4SQL models are first class database objects. Oracle Machine Learning for SQL processes use built-in features of Oracle Database to maximize scalability and make efficient use of system resources.

OML4SQL within Oracle Database offers many advantages:

• No Data Movement: Some machine learning products require that the data be exported from a corporate database and converted to a specialized format. With OML4SQL, no data movement or conversion is needed. This makes the entire process less complex, time-consuming, and error-prone, and it allows for the analysis of very large data sets.

• Security: Your data is protected by the extensive security mechanisms of Oracle Database. Moreover, specific database privileges are needed for different machine learning activities. Only users with the appropriate privileges can define, manipulate, or apply machine learning model objects.

• Data Preparation and Administration: Most data must be cleansed, filtered, normalized, sampled, and transformed in various ways before it can be mined. Up to 80% of the effort in a machine learning project is often devoted to data preparation. OML4SQL can automatically manage key steps in the data preparation process. Additionally, Oracle Database provides extensive administrative tools for preparing and managing data.

• Ease of Data Refresh: Machine learning processes within Oracle Database have ready access to refreshed data. OML4SQL can easily deliver machine learning results based on current data, thereby maximizing its timeliness and relevance.

• Oracle Database Analytics: Oracle Database offers many features for advanced analytics and business intelligence. You can easily integrate machine learning with other analytical features of the database, such as statistical analysis and OLAP.

• Oracle Technology Stack: You can take advantage of all aspects of Oracle's technology stack to integrate machine learning within a larger framework for business intelligence or scientific inquiry.

• Domain Environment: Machine learning models have to be built, tested, validated, managed, and deployed in their appropriate application domain environments. Machine learning results may need to be post-processed as part of domain specific computations (for example, calculating estimated risks and response probabilities) and then stored into permanent repositories or data warehouses. With OML4SQL, the pre- and post-machine learning activities can all be accomplished within the same environment.

• Application Programming Interfaces: The PL/SQL API and SQL language operators provide direct access to OML4SQL functionality in Oracle Database.

Oracle Machine Learning for SQL in Oracle Exadata

Understand how complex scoring and algorithmic processing is done using Oracle Exadata.

Scoring refers to the process of applying a OML4SQL model to data to generate predictions. The scoring process may require significant system resources. Vast amounts of data may be involved, and algorithmic processing may be very complex.

With OML4SQL, scoring can be off-loaded to intelligent Oracle Exadata Storage Servers where processing is extremely performant.

Oracle Exadata Storage Servers combine Oracle's smart storage software and Oracle's industry-standard hardware to deliver the industry's highest database storage performance. For more information about Oracle Exadata, visit the Oracle Technology Network.

Highlights of the Oracle Machine Learning for SQL API

Learn about the advantages of OML4SQL application programming interface (API).

Machine learning is a valuable technology in many application domains. It has become increasingly indispensable in the private sector as a tool for optimizing operations and maintaining a competitive edge. Machine learning also has critical applications in the public sector and in scientific research. However, the complexities of machine learning application development and the complexities inherent in managing and securing large stores of data can limit the adoption of machine learning technology.

OML4SQL is uniquely suited to addressing these challenges. The machine learning engine is implemented in the database kernel, and the robust administrative features of Oracle Database are available for managing and securing the data. While supporting a full range of machine learning algorithms and procedures, the API also has features that simplify the development of machine learning applications.

The OML4SQL API consists of extensions to Oracle SQL, the native language of the database. The API offers the following advantages:

• Scoring in the context of SQL queries. Scoring can be performed dynamically or by applying machine learning models.

• Automatic Data Preparation (ADP) and embedded transformations.

• Model transparency. Algorithm-specific queries return details about the attributes that were used to create the model.

• Scoring transparency. Details about the prediction, clustering, or feature extraction operation can be returned with the score.

• Simple routines for predictive analytics.

• A workflow-based graphical user interface (GUI) within Oracle SQL Developer. You can download SQL Developer free of charge from the following site:

  Oracle Data Miner

Note:

The examples in this publication are taken from the OML4SQL examples that are available on GitHub. For information on the examples, see About the OML4SQL Examples.