Oracle Machine Learning AutoML User Interface makes it easy for citizen data scientists and expert data scientists to build and deploy machine learning models. OML AutoML UI, a new component of Oracle Machine Learning on Oracle Autonomous Database, provides a no-code browser-based interface that automates the machine learning modeling process and simplifies deployment to just a few clicks. OML AutoML UI is state-of-the-art, proprietary technology created by Oracle Labs that leverages the powerful in-database algorithms of Oracle Machine Learning.
While data scientists may prefer to write code, perhaps using the OML4Py AutoML feature, OML AutoML UI makes machine learning possible for a much broader set of users, who may “know enough ML to be dangerous” but are not familiar with specific algorithm details and the modeling process to refine usable models.
At the same time OML AutoML UI delivers significant productivity improvements for data scientists as a modeling accelerator—allowing automation to produce an initial model, but then get the specific hyperparameters to continue tuning or to augment the model directly in a notebook generated by OML AutoML UI that reproduces OML4Py code for the specified model.
With OML AutoML UI, users create experiments, which automate the machine learning modeling process pipeline – consisting of several time consuming and repetitive activities:
Summarizing, OML AutoML UI automates four major steps in the machine learning modeling process that are often time consuming and tedious: algorithm selection, data sampling, feature selection, and model tuning.
Define your business problem, prepare your data, then just specify the data table (or view) and the target you want to predict. OML AutoML UI does the rest to produce several models for you to consider. Note that the same in-database algorithm-specific automatic data preparation applies to you data so there are fewer steps for the user, who can focus on higher value feature engineering. Then just select the model you want to deploy through a REST endpoint in OML Services.
Of course you can also use such models directly through SQL queries in the database for developing custom enterprise applications, Oracle Analytics Cloud dashboards, or Oracle APEX applications.
For collaboration, users share experiments by using workspace and project features that support permissions for viewer, developer, and manager roles.
Features of OML AutoML UI include:
Access Oracle Machine Learning AutoML UI in Oracle Autonomous Database alongside Oracle Machine Learning Notebooks, where you create and run experiments, deploy models, and generate notebooks.